Showing 1–50 of 2,213 results for author: Liu, T

EndoGen: Conditional Autoregressive Endoscopic Video Generation

Authors: Xinyu Liu, Hengyu Liu, Cheng Wang, Tianming Liu, Yixuan Yuan

Abstract: Endoscopic video generation is crucial for advancing medical imaging and enhancing diagnostic capabilities. However, prior efforts in this field have either focused on static images, lacking the dynamic context required for practical applications, or have relied on unconditional generation that fails to provide meaningful references for clinicians. Therefore, in this paper, we propose the first co… ▽ More Endoscopic video generation is crucial for advancing medical imaging and enhancing diagnostic capabilities. However, prior efforts in this field have either focused on static images, lacking the dynamic context required for practical applications, or have relied on unconditional generation that fails to provide meaningful references for clinicians. Therefore, in this paper, we propose the first conditional endoscopic video generation framework, namely EndoGen. Specifically, we build an autoregressive model with a tailored Spatiotemporal Grid-Frame Patterning (SGP) strategy. It reformulates the learning of generating multiple frames as a grid-based image generation pattern, which effectively capitalizes the inherent global dependency modeling capabilities of autoregressive architectures. Furthermore, we propose a Semantic-Aware Token Masking (SAT) mechanism, which enhances the model's ability to produce rich and diverse content by selectively focusing on semantically meaningful regions during the generation process. Through extensive experiments, we demonstrate the effectiveness of our framework in generating high-quality, conditionally guided endoscopic content, and improves the performance of downstream task of polyp segmentation. Code released at https://www.github.com/CUHK-AIM-Group/EndoGen. △ Less

Submitted 23 July, 2025; originally announced July 2025.

Comments: MICCAI 2025

Optimizing Canaries for Privacy Auditing with Metagradient Descent

Authors: Matteo Boglioni, Terrance Liu, Andrew Ilyas, Zhiwei Steven Wu

Abstract: In this work we study black-box privacy auditing, where the goal is to lower bound the privacy parameter of a differentially private learning algorithm using only the algorithm's outputs (i.e., final trained model). For DP-SGD (the most successful method for training differentially private deep learning models), the canonical approach auditing uses membership inference-an auditor comes with a smal… ▽ More In this work we study black-box privacy auditing, where the goal is to lower bound the privacy parameter of a differentially private learning algorithm using only the algorithm's outputs (i.e., final trained model). For DP-SGD (the most successful method for training differentially private deep learning models), the canonical approach auditing uses membership inference-an auditor comes with a small set of special "canary" examples, inserts a random subset of them into the training set, and then tries to discern which of their canaries were included in the training set (typically via a membership inference attack). The auditor's success rate then provides a lower bound on the privacy parameters of the learning algorithm. Our main contribution is a method for optimizing the auditor's canary set to improve privacy auditing, leveraging recent work on metagradient optimization. Our empirical evaluation demonstrates that by using such optimized canaries, we can improve empirical lower bounds for differentially private image classification models by over 2x in certain instances. Furthermore, we demonstrate that our method is transferable and efficient: canaries optimized for non-private SGD with a small model architecture remain effective when auditing larger models trained with DP-SGD. △ Less

Submitted 21 July, 2025; originally announced July 2025.

From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Open-vocabulary Situation Recognition

Authors: Chen Cai, Tianyi Liu, Jianjun Gao, Wenyang Liu, Kejun Wu, Ruoyu Wang, Yi Wang, Soo Chin Liew

Abstract: Recent Multimodal Large Language Models (MLLMs) exhibit strong zero-shot abilities but struggle with complex Grounded Situation Recognition (GSR) and are resource-intensive for edge device deployment. Meanwhile, conventional GSR models often lack generalization ability, falling short in recognizing unseen and rare situations. In this paper, we exploit transferring knowledge from a teacher MLLM to… ▽ More Recent Multimodal Large Language Models (MLLMs) exhibit strong zero-shot abilities but struggle with complex Grounded Situation Recognition (GSR) and are resource-intensive for edge device deployment. Meanwhile, conventional GSR models often lack generalization ability, falling short in recognizing unseen and rare situations. In this paper, we exploit transferring knowledge from a teacher MLLM to a small GSR model to enhance its generalization and zero-shot abilities, thereby introducing the task of Open-vocabulary Grounded Situation Recognition (Ov-GSR). To achieve this, we propose Multimodal Interactive Prompt Distillation (MIPD), a novel framework that distills enriched multimodal knowledge from the foundation model, enabling the student Ov-GSR model to recognize unseen situations and be better aware of rare situations. Specifically, the MIPD framework first leverages the LLM-based Judgmental Rationales Generator (JRG) to construct positive and negative glimpse and gaze rationales enriched with contextual semantic information. The proposed scene-aware and instance-perception prompts are then introduced to align rationales with visual information from the MLLM teacher via the Negative-Guided Multimodal Prompting Alignment (NMPA) module, effectively capturing holistic and perceptual multimodal knowledge. Finally, the aligned multimodal knowledge is distilled into the student Ov-GSR model, providing a stronger foundation for generalization that enhances situation understanding, bridges the gap between seen and unseen scenarios, and mitigates prediction bias in rare cases. We evaluate MIPD on the refined Ov-SWiG dataset, achieving superior performance on seen, rare, and unseen situations, and further demonstrate improved unseen detection on the HICO-DET dataset. △ Less

Submitted 19 July, 2025; originally announced July 2025.

Best Practices for Large-Scale, Pixel-Wise Crop Mapping and Transfer Learning Workflows

Authors: Judy Long, Tao Liu, Sean Alexander Woznicki, Miljana Marković, Oskar Marko, Molly Sears

Abstract: Crop mapping involves identifying and classifying crop types using spatial data, primarily derived from remote sensing imagery. This study presents the first comprehensive review of large-scale, pixel-wise crop mapping workflows, encompassing both conventional supervised methods and emerging transfer learning approaches. To identify the optimal supervised crop mapping workflows, we conducted syste… ▽ More Crop mapping involves identifying and classifying crop types using spatial data, primarily derived from remote sensing imagery. This study presents the first comprehensive review of large-scale, pixel-wise crop mapping workflows, encompassing both conventional supervised methods and emerging transfer learning approaches. To identify the optimal supervised crop mapping workflows, we conducted systematic experiments, comparing six widely adopted satellite image-based preprocessing methods, alongside eleven supervised pixel-wise classification models. Additionally, we assessed the synergistic impact of varied training sample sizes and variable combinations. Moreover, we identified optimal transfer learning techniques for different magnitudes of domain shift. The evaluation of best methods was conducted across five diverse agricultural sites. Landsat 8 served as the primary satellite data source. Labels come from CDL trusted pixels and field surveys. Our findings reveal three key insights. First, fine-scale interval preprocessing paired with Transformer models consistently delivered optimal performance for both supervised and transferable workflows. RF offered rapid training and competitive performance in conventional supervised learning and direct transfer to similar domains. Second, transfer learning techniques enhanced workflow adaptability, with UDA being effective for homogeneous crop classes while fine-tuning remains robust across diverse scenarios. Finally, workflow choice depends heavily on the availability of labeled samples. With a sufficient sample size, supervised training typically delivers more accurate and generalizable results. Below a certain threshold, transfer learning that matches the level of domain shift is a viable alternative to achieve crop mapping. Repository: Best-Practices-for-Large-Scale-Pixel-Wise-Crop-Mapping-and-Transfer-Learning-Workflows △ Less

Submitted 16 July, 2025; originally announced July 2025.

Comments: A review article. 41 pages, 22 figures. Preprint

Biological Processing Units: Leveraging an Insect Connectome to Pioneer Biofidelic Neural Architectures

Authors: Siyu Yu, Zihan Qin, Tingshan Liu, Beiya Xu, R. Jacob Vogelstein, Jason Brown, Joshua T. Vogelstein

Abstract: The complete connectome of the Drosophila larva brain offers a unique opportunity to investigate whether biologically evolved circuits can support artificial intelligence. We convert this wiring diagram into a Biological Processing Unit (BPU), a fixed recurrent network derived directly from synaptic connectivity. Despite its modest size 3,000 neurons and 65,000 weights between them), the unmodifie… ▽ More The complete connectome of the Drosophila larva brain offers a unique opportunity to investigate whether biologically evolved circuits can support artificial intelligence. We convert this wiring diagram into a Biological Processing Unit (BPU), a fixed recurrent network derived directly from synaptic connectivity. Despite its modest size 3,000 neurons and 65,000 weights between them), the unmodified BPU achieves 98% accuracy on MNIST and 58% on CIFAR-10, surpassing size-matched MLPs. Scaling the BPU via structured connectome expansions further improves CIFAR-10 performance, while modality-specific ablations reveal the uneven contributions of different sensory subsystems. On the ChessBench dataset, a lightweight GNN-BPU model trained on only 10,000 games achieves 60% move accuracy, nearly 10x better than any size transformer. Moreover, CNN-BPU models with ~2M parameters outperform parameter-matched Transformers, and with a depth-6 minimax search at inference, reach 91.7% accuracy, exceeding even a 9M-parameter Transformer baseline. These results demonstrate the potential of biofidelic neural architectures to support complex cognitive tasks and motivate scaling to larger and more intelligent connectomes in future work. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Comments: Accepted to AGI 2025

Bridging Brains and Machines: A Unified Frontier in Neuroscience, Artificial Intelligence, and Neuromorphic Systems

Authors: Sohan Shankar, Yi Pan, Hanqi Jiang, Zhengliang Liu, Mohammad R. Darbandi, Agustin Lorenzo, Junhao Chen, Md Mehedi Hasan, Arif Hassan Zidan, Eliana Gelman, Joshua A. Konfrst, Jillian Y. Russell, Katelyn Fernandes, Tianze Yang, Yiwei Li, Huaqin Zhao, Afrar Jahin, Triparna Ganguly, Shair Dinesha, Yifan Zhou, Zihao Wu, Xinliang Li, Lokesh Adusumilli, Aziza Hussein, Sagar Nookarapu , et al. (20 additional authors not shown)

Abstract: This position and survey paper identifies the emerging convergence of neuroscience, artificial general intelligence (AGI), and neuromorphic computing toward a unified research paradigm. Using a framework grounded in brain physiology, we highlight how synaptic plasticity, sparse spike-based communication, and multimodal association provide design principles for next-generation AGI systems that pote… ▽ More This position and survey paper identifies the emerging convergence of neuroscience, artificial general intelligence (AGI), and neuromorphic computing toward a unified research paradigm. Using a framework grounded in brain physiology, we highlight how synaptic plasticity, sparse spike-based communication, and multimodal association provide design principles for next-generation AGI systems that potentially combine both human and machine intelligences. The review traces this evolution from early connectionist models to state-of-the-art large language models, demonstrating how key innovations like transformer attention, foundation-model pre-training, and multi-agent architectures mirror neurobiological processes like cortical mechanisms, working memory, and episodic consolidation. We then discuss emerging physical substrates capable of breaking the von Neumann bottleneck to achieve brain-scale efficiency in silicon: memristive crossbars, in-memory compute arrays, and emerging quantum and photonic devices. There are four critical challenges at this intersection: 1) integrating spiking dynamics with foundation models, 2) maintaining lifelong plasticity without catastrophic forgetting, 3) unifying language with sensorimotor learning in embodied agents, and 4) enforcing ethical safeguards in advanced neuromorphic autonomous systems. This combined perspective across neuroscience, computation, and hardware offers an integrative agenda for in each of these fields. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Benchmarking and Evaluation of AI Models in Biology: Outcomes and Recommendations from the CZI Virtual Cells Workshop

Authors: Elizabeth Fahsbender, Alma Andersson, Jeremy Ash, Polina Binder, Daniel Burkhardt, Benjamin Chang, Georg K. Gerber, Anthony Gitter, Patrick Godau, Ankit Gupta, Genevieve Haliburton, Siyu He, Trey Ideker, Ivana Jelic, Aly Khan, Yang-Joon Kim, Aditi Krishnapriyan, Jon M. Laurent, Tianyu Liu, Emma Lundberg, Shalin B. Mehta, Rob Moccia, Angela Oliveira Pisco, Katherine S. Pollard, Suresh Ramani , et al. (10 additional authors not shown)

Abstract: Artificial intelligence holds immense promise for transforming biology, yet a lack of standardized, cross domain, benchmarks undermines our ability to build robust, trustworthy models. Here, we present insights from a recent workshop that convened machine learning and computational biology experts across imaging, transcriptomics, proteomics, and genomics to tackle this gap. We identify major techn… ▽ More Artificial intelligence holds immense promise for transforming biology, yet a lack of standardized, cross domain, benchmarks undermines our ability to build robust, trustworthy models. Here, we present insights from a recent workshop that convened machine learning and computational biology experts across imaging, transcriptomics, proteomics, and genomics to tackle this gap. We identify major technical and systemic bottlenecks such as data heterogeneity and noise, reproducibility challenges, biases, and the fragmented ecosystem of publicly available resources and propose a set of recommendations for building benchmarking frameworks that can efficiently compare ML models of biological systems across tasks and data modalities. By promoting high quality data curation, standardized tooling, comprehensive evaluation metrics, and open, collaborative platforms, we aim to accelerate the development of robust benchmarks for AI driven Virtual Cells. These benchmarks are crucial for ensuring rigor, reproducibility, and biological relevance, and will ultimately advance the field toward integrated models that drive new discoveries, therapeutic insights, and a deeper understanding of cellular systems. △ Less

Submitted 15 July, 2025; v1 submitted 14 July, 2025; originally announced July 2025.

User Long-Term Multi-Interest Retrieval Model for Recommendation

Authors: Yue Meng, Cheng Guo, Xiaohui Hu, Honghu Deng, Yi Cao, Tong Liu, Bo Zheng

Abstract: User behavior sequence modeling, which captures user interest from rich historical interactions, is pivotal for industrial recommendation systems. Despite breakthroughs in ranking-stage models capable of leveraging ultra-long behavior sequences with length scaling up to thousands, existing retrieval models remain constrained to sequences of hundreds of behaviors due to two main challenges. One is… ▽ More User behavior sequence modeling, which captures user interest from rich historical interactions, is pivotal for industrial recommendation systems. Despite breakthroughs in ranking-stage models capable of leveraging ultra-long behavior sequences with length scaling up to thousands, existing retrieval models remain constrained to sequences of hundreds of behaviors due to two main challenges. One is strict latency budget imposed by real-time service over large-scale candidate pool. The other is the absence of target-aware mechanisms and cross-interaction architectures, which prevent utilizing ranking-like techniques to simplify long sequence modeling. To address these limitations, we propose a new framework named User Long-term Multi-Interest Retrieval Model(ULIM), which enables thousand-scale behavior modeling in retrieval stages. ULIM includes two novel components: 1)Category-Aware Hierarchical Dual-Interest Learning partitions long behavior sequences into multiple category-aware subsequences representing multi-interest and jointly optimizes long-term and short-term interests within specific interest cluster. 2)Pointer-Enhanced Cascaded Category-to-Item Retrieval introduces Pointer-Generator Interest Network(PGIN) for next-category prediction, followed by next-item retrieval upon the top-K predicted categories. Comprehensive experiments on Taobao dataset show that ULIM achieves substantial improvement over state-of-the-art methods, and brings 5.54% clicks, 11.01% orders and 4.03% GMV lift for Taobaomiaosha, a notable mini-app of Taobao. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Domain-Adaptive Diagnosis of Lewy Body Disease with Transferability Aware Transformer

Authors: Xiaowei Yu, Jing Zhang, Tong Chen, Yan Zhuang, Minheng Chen, Chao Cao, Yanjun Lyu, Lu Zhang, Li Su, Tianming Liu, Dajiang Zhu

Abstract: Lewy Body Disease (LBD) is a common yet understudied form of dementia that imposes a significant burden on public health. It shares clinical similarities with Alzheimer's disease (AD), as both progress through stages of normal cognition, mild cognitive impairment, and dementia. A major obstacle in LBD diagnosis is data scarcity, which limits the effectiveness of deep learning. In contrast, AD data… ▽ More Lewy Body Disease (LBD) is a common yet understudied form of dementia that imposes a significant burden on public health. It shares clinical similarities with Alzheimer's disease (AD), as both progress through stages of normal cognition, mild cognitive impairment, and dementia. A major obstacle in LBD diagnosis is data scarcity, which limits the effectiveness of deep learning. In contrast, AD datasets are more abundant, offering potential for knowledge transfer. However, LBD and AD data are typically collected from different sites using different machines and protocols, resulting in a distinct domain shift. To effectively leverage AD data while mitigating domain shift, we propose a Transferability Aware Transformer (TAT) that adapts knowledge from AD to enhance LBD diagnosis. Our method utilizes structural connectivity (SC) derived from structural MRI as training data. Built on the attention mechanism, TAT adaptively assigns greater weights to disease-transferable features while suppressing domain-specific ones, thereby reducing domain shift and improving diagnostic accuracy with limited LBD data. The experimental results demonstrate the effectiveness of TAT. To the best of our knowledge, this is the first study to explore domain adaptation from AD to LBD under conditions of data scarcity and domain shift, providing a promising framework for domain-adaptive diagnosis of rare diseases. △ Less

Submitted 7 July, 2025; originally announced July 2025.

Comments: MICCAI 2025

HieraRS: A Hierarchical Segmentation Paradigm for Remote Sensing Enabling Multi-Granularity Interpretation and Cross-Domain Transfer

Authors: Tianlong Ai, Tianzhu Liu, Haochen Jiang, Yanfeng Gu

Abstract: Hierarchical land cover and land use (LCLU) classification aims to assign pixel-wise labels with multiple levels of semantic granularity to remote sensing (RS) imagery. However, existing deep learning-based methods face two major challenges: 1) They predominantly adopt a flat classification paradigm, which limits their ability to generate end-to-end multi-granularity hierarchical predictions align… ▽ More Hierarchical land cover and land use (LCLU) classification aims to assign pixel-wise labels with multiple levels of semantic granularity to remote sensing (RS) imagery. However, existing deep learning-based methods face two major challenges: 1) They predominantly adopt a flat classification paradigm, which limits their ability to generate end-to-end multi-granularity hierarchical predictions aligned with tree-structured hierarchies used in practice. 2) Most cross-domain studies focus on performance degradation caused by sensor or scene variations, with limited attention to transferring LCLU models to cross-domain tasks with heterogeneous hierarchies (e.g., LCLU to crop classification). These limitations hinder the flexibility and generalization of LCLU models in practical applications. To address these challenges, we propose HieraRS, a novel hierarchical interpretation paradigm that enables multi-granularity predictions and supports the efficient transfer of LCLU models to cross-domain tasks with heterogeneous tree-structured hierarchies. We introduce the Bidirectional Hierarchical Consistency Constraint Mechanism (BHCCM), which can be seamlessly integrated into mainstream flat classification models to generate hierarchical predictions, while improving both semantic consistency and classification accuracy. Furthermore, we present TransLU, a dual-branch cross-domain transfer framework comprising two key components: Cross-Domain Knowledge Sharing (CDKS) and Cross-Domain Semantic Alignment (CDSA). TransLU supports dynamic category expansion and facilitates the effective adaptation of LCLU models to heterogeneous hierarchies. In addition, we construct MM-5B, a large-scale multi-modal hierarchical land use dataset featuring pixel-wise annotations. The code and MM-5B dataset will be released at: https://github.com/AI-Tianlong/HieraRS. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Comments: 17 pages, 11 figures

Multilingual Multimodal Software Developer for Code Generation

Authors: Linzheng Chai, Jian Yang, Shukai Liu, Wei Zhang, Liran Wang, Ke Jin, Tao Sun, Congnan Liu, Chenchen Zhang, Hualei Zhu, Jiaheng Liu, Xianjie Wu, Ge Zhang, Tianyu Liu, Zhoujun Li

Abstract: The rapid advancement of Large Language Models (LLMs) has significantly improved code generation, yet most models remain text-only, neglecting crucial visual aids like diagrams and flowcharts used in real-world software development. To bridge this gap, we introduce MM-Coder, a Multilingual Multimodal software developer. MM-Coder integrates visual design inputs-Unified Modeling Language (UML) diagr… ▽ More The rapid advancement of Large Language Models (LLMs) has significantly improved code generation, yet most models remain text-only, neglecting crucial visual aids like diagrams and flowcharts used in real-world software development. To bridge this gap, we introduce MM-Coder, a Multilingual Multimodal software developer. MM-Coder integrates visual design inputs-Unified Modeling Language (UML) diagrams and flowcharts (termed Visual Workflow)-with textual instructions to enhance code generation accuracy and architectural alignment. To enable this, we developed MMc-Instruct, a diverse multimodal instruction-tuning dataset including visual-workflow-based code generation, allowing MM-Coder to synthesize textual and graphical information like human developers, distinct from prior work on narrow tasks. Furthermore, we introduce MMEval, a new benchmark for evaluating multimodal code generation, addressing existing text-only limitations. Our evaluations using MMEval highlight significant remaining challenges for models in precise visual information capture, instruction following, and advanced programming knowledge. Our work aims to revolutionize industrial programming by enabling LLMs to interpret and implement complex specifications conveyed through both text and visual designs. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Comments: Preprint

SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes

Authors: Jiaxin Huang, Ziwen Li, Hanlve Zhang, Runnan Chen, Xiao He, Yandong Guo, Wenping Wang, Tongliang Liu, Mingming Gong

Abstract: The integration of language and 3D perception is critical for embodied AI and robotic systems to perceive, understand, and interact with the physical world. Spatial reasoning, a key capability for understanding spatial relationships between objects, remains underexplored in current 3D vision-language research. Existing datasets often mix semantic cues (e.g., object name) with spatial context, lead… ▽ More The integration of language and 3D perception is critical for embodied AI and robotic systems to perceive, understand, and interact with the physical world. Spatial reasoning, a key capability for understanding spatial relationships between objects, remains underexplored in current 3D vision-language research. Existing datasets often mix semantic cues (e.g., object name) with spatial context, leading models to rely on superficial shortcuts rather than genuinely interpreting spatial relationships. To address this gap, we introduce S\textsc{urprise}3D, a novel dataset designed to evaluate language-guided spatial reasoning segmentation in complex 3D scenes. S\textsc{urprise}3D consists of more than 200k vision language pairs across 900+ detailed indoor scenes from ScanNet++ v2, including more than 2.8k unique object classes. The dataset contains 89k+ human-annotated spatial queries deliberately crafted without object name, thereby mitigating shortcut biases in spatial understanding. These queries comprehensively cover various spatial reasoning skills, such as relative position, narrative perspective, parametric perspective, and absolute distance reasoning. Initial benchmarks demonstrate significant challenges for current state-of-the-art expert 3D visual grounding methods and 3D-LLMs, underscoring the necessity of our dataset and the accompanying 3D Spatial Reasoning Segmentation (3D-SRS) benchmark suite. S\textsc{urprise}3D and 3D-SRS aim to facilitate advancements in spatially aware AI, paving the way for effective embodied interaction and robotic planning. The code and datasets can be found in https://github.com/liziwennba/SUPRISE. △ Less

Submitted 10 July, 2025; originally announced July 2025.

USD: A User-Intent-Driven Sampling and Dual-Debiasing Framework for Large-Scale Homepage Recommendations

Authors: Jiaqi Zheng, Cheng Guo, Yi Cao, Chaoqun Hou, Tong Liu, Bo Zheng

Abstract: Large-scale homepage recommendations face critical challenges from pseudo-negative samples caused by exposure bias, where non-clicks may indicate inattention rather than disinterest. Existing work lacks thorough analysis of invalid exposures and typically addresses isolated aspects (e.g., sampling strategies), overlooking the critical impact of pseudo-positive samples - such as homepage clicks mer… ▽ More Large-scale homepage recommendations face critical challenges from pseudo-negative samples caused by exposure bias, where non-clicks may indicate inattention rather than disinterest. Existing work lacks thorough analysis of invalid exposures and typically addresses isolated aspects (e.g., sampling strategies), overlooking the critical impact of pseudo-positive samples - such as homepage clicks merely to visit marketing portals. We propose a unified framework for large-scale homepage recommendation sampling and debiasing. Our framework consists of two key components: (1) a user intent-aware negative sampling module to filter invalid exposure samples, and (2) an intent-driven dual-debiasing module that jointly corrects exposure bias and click bias. Extensive online experiments on Taobao demonstrate the efficacy of our framework, achieving significant improvements in user click-through rates (UCTR) by 35.4% and 14.5% in two variants of the marketing block on the Taobao homepage, Baiyibutie and Taobaomiaosha. △ Less

Submitted 10 July, 2025; v1 submitted 8 July, 2025; originally announced July 2025.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Authors: Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu , et al. (3284 additional authors not shown)

Abstract: In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal unde… ▽ More In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving. △ Less

Submitted 22 July, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: 72 pages, 17 figures

A Survey on Latent Reasoning

Authors: Rui-Jie Zhu, Tianhao Peng, Tianhao Cheng, Xingwei Qu, Jinfa Huang, Dawei Zhu, Hao Wang, Kaiwen Xue, Xuanliang Zhang, Yong Shan, Tianle Cai, Taylor Kergan, Assel Kembay, Andrew Smith, Chenghua Lin, Binh Nguyen, Yuqi Pan, Yuhong Chou, Zefan Cai, Zhenhe Wu, Yongchi Zhao, Tianyu Liu, Jian Yang, Wangchunshu Zhou, Chujie Zheng , et al. (8 additional authors not shown)

Abstract: Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate steps. While CoT improves both interpretability and accuracy, its dependence on natural language reasoning limits the model's expressive bandwidth. Latent reasoning tackles this bottleneck by performing multi-step inferen… ▽ More Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate steps. While CoT improves both interpretability and accuracy, its dependence on natural language reasoning limits the model's expressive bandwidth. Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state, eliminating token-level supervision. To advance latent reasoning research, this survey provides a comprehensive overview of the emerging field of latent reasoning. We begin by examining the foundational role of neural network layers as the computational substrate for reasoning, highlighting how hierarchical representations support complex transformations. Next, we explore diverse latent reasoning methodologies, including activation-based recurrence, hidden state propagation, and fine-tuning strategies that compress or internalize explicit reasoning traces. Finally, we discuss advanced paradigms such as infinite-depth latent reasoning via masked diffusion models, which enable globally consistent and reversible reasoning processes. By unifying these perspectives, we aim to clarify the conceptual landscape of latent reasoning and chart future directions for research at the frontier of LLM cognition. An associated GitHub repository collecting the latest papers and repos is available at: https://github.com/multimodal-art-projection/LatentCoT-Horizon/. △ Less

Submitted 10 July, 2025; v1 submitted 8 July, 2025; originally announced July 2025.

Bridging Prediction and Intervention Problems in Social Systems

Authors: Lydia T. Liu, Inioluwa Deborah Raji, Angela Zhou, Luke Guerdan, Jessica Hullman, Daniel Malinsky, Bryan Wilder, Simone Zhang, Hammaad Adam, Amanda Coston, Ben Laufer, Ezinne Nwankwo, Michael Zanger-Tishler, Eli Ben-Michael, Solon Barocas, Avi Feller, Marissa Gerchick, Talia Gillis, Shion Guha, Daniel Ho, Lily Hu, Kosuke Imai, Sayash Kapoor, Joshua Loftus, Razieh Nabi , et al. (10 additional authors not shown)

Abstract: Many automated decision systems (ADS) are designed to solve prediction problems -- where the goal is to learn patterns from a sample of the population and apply them to individuals from the same population. In reality, these prediction systems operationalize holistic policy interventions in deployment. Once deployed, ADS can shape impacted population outcomes through an effective policy change in… ▽ More Many automated decision systems (ADS) are designed to solve prediction problems -- where the goal is to learn patterns from a sample of the population and apply them to individuals from the same population. In reality, these prediction systems operationalize holistic policy interventions in deployment. Once deployed, ADS can shape impacted population outcomes through an effective policy change in how decision-makers operate, while also being defined by past and present interactions between stakeholders and the limitations of existing organizational, as well as societal, infrastructure and context. In this work, we consider the ways in which we must shift from a prediction-focused paradigm to an interventionist paradigm when considering the impact of ADS within social systems. We argue this requires a new default problem setup for ADS beyond prediction, to instead consider predictions as decision support, final decisions, and outcomes. We highlight how this perspective unifies modern statistical frameworks and other tools to study the design, implementation, and evaluation of ADS systems, and point to the research directions necessary to operationalize this paradigm shift. Using these tools, we characterize the limitations of focusing on isolated prediction tasks, and lay the foundation for a more intervention-oriented approach to developing and deploying ADS. △ Less

Submitted 7 July, 2025; originally announced July 2025.

Harnessing Pairwise Ranking Prompting Through Sample-Efficient Ranking Distillation

Authors: Junru Wu, Le Yan, Zhen Qin, Honglei Zhuang, Paul Suganthan G. C., Tianqi Liu, Zhe Dong, Xuanhui Wang, Harrie Oosterhuis

Abstract: While Pairwise Ranking Prompting (PRP) with Large Language Models (LLMs) is one of the most effective zero-shot document ranking methods, it has a quadratic computational complexity with respect to the number of documents to be ranked, as it requires an enumeration over all possible document pairs. Consequently, the outstanding ranking performance of PRP has remained unreachable for most real-worl… ▽ More While Pairwise Ranking Prompting (PRP) with Large Language Models (LLMs) is one of the most effective zero-shot document ranking methods, it has a quadratic computational complexity with respect to the number of documents to be ranked, as it requires an enumeration over all possible document pairs. Consequently, the outstanding ranking performance of PRP has remained unreachable for most real-world ranking applications. In this work, we propose to harness the effectiveness of PRP through pairwise distillation. Specifically, we distill a pointwise student ranker from pairwise teacher labels generated by PRP, resulting in an efficient student model that retains the performance of PRP with substantially lower computational costs. Furthermore, we find that the distillation process can be made sample-efficient: with only 2% of pairs, we are able to obtain the same performance as using all pairs for teacher labels. Thus, our novel approach provides a solution to harness the ranking performance of PRP without incurring high computational costs during both distillation and serving. △ Less

Submitted 7 July, 2025; originally announced July 2025.

Comments: ReNeuIR 2025 (at SIGIR 2025) - 4th Workshop on Reaching Efficiency in Neural Information Retrieval, July 17, 2025, Padua, Italy

Exploring Remote Physiological Signal Measurement under Dynamic Lighting Conditions at Night: Dataset, Experiment, and Analysis

Authors: Zhipeng Li, Kegang Wang, Hanguang Xiao, Xingyue Liu, Feizhong Zhou, Jiaxin Jiang, Tianqi Liu

Abstract: Remote photoplethysmography (rPPG) is a non-contact technique for measuring human physiological signals. Due to its convenience and non-invasiveness, it has demonstrated broad application potential in areas such as health monitoring and emotion recognition. In recent years, the release of numerous public datasets has significantly advanced the performance of rPPG algorithms under ideal lighting co… ▽ More Remote photoplethysmography (rPPG) is a non-contact technique for measuring human physiological signals. Due to its convenience and non-invasiveness, it has demonstrated broad application potential in areas such as health monitoring and emotion recognition. In recent years, the release of numerous public datasets has significantly advanced the performance of rPPG algorithms under ideal lighting conditions. However, the effectiveness of current rPPG methods in realistic nighttime scenarios with dynamic lighting variations remains largely unknown. Moreover, there is a severe lack of datasets specifically designed for such challenging environments, which has substantially hindered progress in this area of research. To address this gap, we present and release a large-scale rPPG dataset collected under dynamic lighting conditions at night, named DLCN. The dataset comprises approximately 13 hours of video data and corresponding synchronized physiological signals from 98 participants, covering four representative nighttime lighting scenarios. DLCN offers high diversity and realism, making it a valuable resource for evaluating algorithm robustness in complex conditions. Built upon the proposed Happy-rPPG Toolkit, we conduct extensive experiments and provide a comprehensive analysis of the challenges faced by state-of-the-art rPPG methods when applied to DLCN. The dataset and code are publicly available at https://github.com/dalaoplan/Happp-rPPG-Toolkit. △ Less

Submitted 6 July, 2025; originally announced July 2025.

When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need

Authors: Ziming Hong, Runnan Chen, Zengmao Wang, Bo Han, Bo Du, Tongliang Liu

Abstract: Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access the real in-distribution (ID) data. Its common solution is to use a generator to synthesize fake data and use them as a substitute for real ID data. However, existing works typically assume teachers are trustworthy, leaving the robustness and security of DFKD from untrusted teachers largely unexp… ▽ More Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access the real in-distribution (ID) data. Its common solution is to use a generator to synthesize fake data and use them as a substitute for real ID data. However, existing works typically assume teachers are trustworthy, leaving the robustness and security of DFKD from untrusted teachers largely unexplored. In this work, we conduct the first investigation into distilling non-transferable learning (NTL) teachers using DFKD, where the transferability from an ID domain to an out-of-distribution (OOD) domain is prohibited. We find that NTL teachers fool DFKD through divert the generator's attention from the useful ID knowledge to the misleading OOD knowledge. This hinders ID knowledge transfer but prioritizes OOD knowledge transfer. To mitigate this issue, we propose Adversarial Trap Escaping (ATEsc) to benefit DFKD by identifying and filtering out OOD-like synthetic samples. Specifically, inspired by the evidence that NTL teachers show stronger adversarial robustness on OOD samples than ID samples, we split synthetic samples into two groups according to their robustness. The fragile group is treated as ID-like data and used for normal knowledge distillation, while the robust group is seen as OOD-like data and utilized for forgetting OOD knowledge. Extensive experiments demonstrate the effectiveness of ATEsc for improving DFKD against NTL teachers. Code is released at https://github.com/tmllab/2025_ICML_ATEsc. △ Less

Submitted 5 July, 2025; originally announced July 2025.

Comments: Accepted by ICML 2025

SAMed-2: Selective Memory Enhanced Medical Segment Anything Model

Authors: Zhiling Yan, Sifan Song, Dingjie Song, Yiwei Li, Rong Zhou, Weixiang Sun, Zhennong Chen, Sekeun Kim, Hui Ren, Tianming Liu, Quanzheng Li, Xiang Li, Lifang He, Lichao Sun

Abstract: Recent "segment anything" efforts show promise by learning from large-scale data, but adapting such models directly to medical images remains challenging due to the complexity of medical data, noisy annotations, and continual learning requirements across diverse modalities and anatomical structures. In this work, we propose SAMed-2, a new foundation model for medical image segmentation built upon… ▽ More Recent "segment anything" efforts show promise by learning from large-scale data, but adapting such models directly to medical images remains challenging due to the complexity of medical data, noisy annotations, and continual learning requirements across diverse modalities and anatomical structures. In this work, we propose SAMed-2, a new foundation model for medical image segmentation built upon the SAM-2 architecture. Specifically, we introduce a temporal adapter into the image encoder to capture image correlations and a confidence-driven memory mechanism to store high-certainty features for later retrieval. This memory-based strategy counters the pervasive noise in large-scale medical datasets and mitigates catastrophic forgetting when encountering new tasks or modalities. To train and evaluate SAMed-2, we curate MedBank-100k, a comprehensive dataset spanning seven imaging modalities and 21 medical segmentation tasks. Our experiments on both internal benchmarks and 10 external datasets demonstrate superior performance over state-of-the-art baselines in multi-task scenarios. The code is available at: https://github.com/ZhilingYan/Medical-SAM-Bench. △ Less

Submitted 4 July, 2025; originally announced July 2025.

Comments: Accepted by MICCAI 2025

The Book of Life approach: Enabling richness and scale for life course research

Authors: Mark D. Verhagen, Benedikt Stroebl, Tiffany Liu, Lydia T. Liu, Matthew J. Salganik

Abstract: For over a century, life course researchers have faced a choice between two dominant methodological approaches: qualitative methods that analyze rich data but are constrained to small samples, and quantitative survey-based methods that study larger populations but sacrifice data richness for scale. Two recent technological developments now enable us to imagine a hybrid approach that combines some… ▽ More For over a century, life course researchers have faced a choice between two dominant methodological approaches: qualitative methods that analyze rich data but are constrained to small samples, and quantitative survey-based methods that study larger populations but sacrifice data richness for scale. Two recent technological developments now enable us to imagine a hybrid approach that combines some of the depth of the qualitative approach with the scale of quantitative methods. The first development is the steady rise of ''complex log data,'' behavioral data that is logged for purposes other than research but that can be repurposed to construct rich accounts of people's lives. The second is the emergence of large language models (LLMs) with exceptional pattern recognition capabilities on plain text. In this paper, we take a necessary step toward creating this hybrid approach by developing a flexible procedure to transform complex log data into a textual representation of an individual's life trajectory across multiple domains, over time, and in context. We call this data representation a ''book of life.'' We illustrate the feasibility of our approach by writing over 100 million books of life covering many different facets of life, over time and placed in social context using Dutch population-scale registry data. We open source the book of life toolkit (BOLT), and invite the research community to explore the many potential applications of this approach. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Comments: 25 pages, 4 figures

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation

Authors: Tianyu Liu, Qitan Lv, Hao Li, Xing Gao, Xiao Sun

Abstract: Speculative decoding (SD), where a small draft model is employed to propose draft tokens in advance and then the target model validates them in parallel, has emerged as a promising technique for LLM inference acceleration. Many endeavors to improve SD are to eliminate the need for a draft model and generate draft tokens in a retrieval-based manner in order to further alleviate the drafting overhea… ▽ More Speculative decoding (SD), where a small draft model is employed to propose draft tokens in advance and then the target model validates them in parallel, has emerged as a promising technique for LLM inference acceleration. Many endeavors to improve SD are to eliminate the need for a draft model and generate draft tokens in a retrieval-based manner in order to further alleviate the drafting overhead and significantly reduce the difficulty in deployment and applications. However, retrieval-based SD relies on a matching paradigm to retrieval the most relevant reference as the draft tokens, where these methods often fail to find matched and accurate draft tokens. To address this challenge, we propose LogitSpec to effectively expand the retrieval range and find the most relevant reference as drafts. Our LogitSpec is motivated by the observation that the logit of the last token can not only predict the next token, but also speculate the next next token. Specifically, LogitSpec generates draft tokens in two steps: (1) utilizing the last logit to speculate the next next token; (2) retrieving relevant reference for both the next token and the next next token. LogitSpec is training-free and plug-and-play, which can be easily integrated into existing LLM inference frameworks. Extensive experiments on a wide range of text generation benchmarks demonstrate that LogitSpec can achieve up to 2.61 $\times$ speedup and 3.28 mean accepted tokens per decoding step. Our code is available at https://github.com/smart-lty/LogitSpec. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Distributional Soft Actor-Critic with Diffusion Policy

Authors: Tong Liu, Yinuo Wang, Xujie Song, Wenjun Zou, Liangfa Chen, Likun Wang, Bin Shuai, Jingliang Duan, Shengbo Eben Li

Abstract: Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However, unimodal distribution often and easily causes bias in value function estimation, leading to poor algorithm performance. This paper proposes a distributional rei… ▽ More Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However, unimodal distribution often and easily causes bias in value function estimation, leading to poor algorithm performance. This paper proposes a distributional reinforcement learning algorithm called DSAC-D (Distributed Soft Actor Critic with Diffusion Policy) to address the challenges of estimating bias in value functions and obtaining multimodal policy representations. A multimodal distributional policy iteration framework that can converge to the optimal policy was established by introducing policy entropy and value distribution function. A diffusion value network that can accurately characterize the distribution of multi peaks was constructed by generating a set of reward samples through reverse sampling using a diffusion model. Based on this, a distributional reinforcement learning algorithm with dual diffusion of the value network and the policy network was derived. MuJoCo testing tasks demonstrate that the proposed algorithm not only learns multimodal policy, but also achieves state-of-the-art (SOTA) performance in all 9 control tasks, with significant suppression of estimation bias and total average return improvement of over 10% compared to existing mainstream algorithms. The results of real vehicle testing show that DSAC-D can accurately characterize the multimodal distribution of different driving styles, and the diffusion policy network can characterize multimodal trajectories. △ Less

Submitted 10 July, 2025; v1 submitted 2 July, 2025; originally announced July 2025.

Comments: Accepted IEEE ITSC 2025

Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation

Authors: Xingting Yao, Qinghao Hu, Fei Zhou, Tielong Liu, Gang Li, Peisong Wang, Jian Cheng

Abstract: Multi-bit spiking neural networks (SNNs) have recently become a heated research spot, pursuing energy-efficient and high-accurate AI. However, with more bits involved, the associated memory and computation demands escalate to the point where the performance improvements become disproportionate. Based on the insight that different layers demonstrate different importance and extra bits could be wast… ▽ More Multi-bit spiking neural networks (SNNs) have recently become a heated research spot, pursuing energy-efficient and high-accurate AI. However, with more bits involved, the associated memory and computation demands escalate to the point where the performance improvements become disproportionate. Based on the insight that different layers demonstrate different importance and extra bits could be wasted and interfering, this paper presents an adaptive bit allocation strategy for direct-trained SNNs, achieving fine-grained layer-wise allocation of memory and computation resources. Thus, SNN's efficiency and accuracy can be improved. Specifically, we parametrize the temporal lengths and the bit widths of weights and spikes, and make them learnable and controllable through gradients. To address the challenges caused by changeable bit widths and temporal lengths, we propose the refined spiking neuron, which can handle different temporal lengths, enable the derivation of gradients for temporal lengths, and suit spike quantization better. In addition, we theoretically formulate the step-size mismatch problem of learnable bit widths, which may incur severe quantization errors to SNN, and accordingly propose the step-size renewal mechanism to alleviate this issue. Experiments on various datasets, including the static CIFAR and ImageNet and the dynamic CIFAR-DVS and DVS-GESTURE, demonstrate that our methods can reduce the overall memory and computation cost while achieving higher accuracy. Particularly, our SEWResNet-34 can achieve a 2.69\% accuracy gain and 4.16$\times$ lower bit budgets over the advanced baseline work on ImageNet. This work will be fully open-sourced. △ Less

Submitted 30 June, 2025; originally announced June 2025.

CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models

Authors: Qiming Li, Zekai Ye, Xiaocheng Feng, Weihong Zhong, Libo Qin, Ruihan Chen, Baohang Li, Kui Jiang, Yaowei Wang, Ting Liu, Bing Qin

Abstract: Although Large Vision-Language Models (LVLMs) have demonstrated powerful capabilities in interpreting visual information, they frequently produce content that deviates from visual information, leading to object hallucination. To tackle this, recent works mostly depend on expensive manual annotations and training cost, or significantly increase inference time. In this work, we observe that LVLMs' a… ▽ More Although Large Vision-Language Models (LVLMs) have demonstrated powerful capabilities in interpreting visual information, they frequently produce content that deviates from visual information, leading to object hallucination. To tackle this, recent works mostly depend on expensive manual annotations and training cost, or significantly increase inference time. In this work, we observe that LVLMs' attention to visual information is significantly stronger when answering caption queries compared to non-caption queries. Inspired by this phenomenon, we propose Caption-sensitive Attention Intervention (CAI), a training-free, plug-and-play hallucination mitigation method that leverages the attention activation pattern in response to caption queries to enhance LVLMs' visual perception capability. Extensive experimental results across four benchmarks covering both discriminative and generative tasks, demonstrate that CAI achieves state-of-the-art (SOTA) hallucination mitigating performance only with minimal additional inference cost. △ Less

Submitted 30 June, 2025; originally announced June 2025.

MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting

Authors: Jun Huang, Ting Liu, Yihang Wu, Xiaochao Qu, Luoqi Liu, Xiaolin Hu

Abstract: Advancements in generative models have enabled image inpainting models to generate content within specific regions of an image based on provided prompts and masks. However, existing inpainting methods often suffer from problems such as semantic misalignment, structural distortion, and style inconsistency. In this work, we present MTADiffusion, a Mask-Text Alignment diffusion model designed for obj… ▽ More Advancements in generative models have enabled image inpainting models to generate content within specific regions of an image based on provided prompts and masks. However, existing inpainting methods often suffer from problems such as semantic misalignment, structural distortion, and style inconsistency. In this work, we present MTADiffusion, a Mask-Text Alignment diffusion model designed for object inpainting. To enhance the semantic capabilities of the inpainting model, we introduce MTAPipeline, an automatic solution for annotating masks with detailed descriptions. Based on the MTAPipeline, we construct a new MTADataset comprising 5 million images and 25 million mask-text pairs. Furthermore, we propose a multi-task training strategy that integrates both inpainting and edge prediction tasks to improve structural stability. To promote style consistency, we present a novel inpainting style-consistency loss using a pre-trained VGG network and the Gram matrix. Comprehensive evaluations on BrushBench and EditBench demonstrate that MTADiffusion achieves state-of-the-art performance compared to other methods. △ Less

Submitted 29 June, 2025; originally announced June 2025.

Comments: CVPR 2025

Towards foundational LiDAR world models with efficient latent flow matching

Authors: Tianran Liu, Shengwen Zhao, Nicholas Rhinehart

Abstract: LiDAR-based world models offer more structured and geometry-aware representations than their image-based counterparts. However, existing LiDAR world models are narrowly trained; each model excels only in the domain for which it was built. Can we develop LiDAR world models that exhibit strong transferability across multiple domains? We conduct the first systematic domain transfer study across three… ▽ More LiDAR-based world models offer more structured and geometry-aware representations than their image-based counterparts. However, existing LiDAR world models are narrowly trained; each model excels only in the domain for which it was built. Can we develop LiDAR world models that exhibit strong transferability across multiple domains? We conduct the first systematic domain transfer study across three demanding scenarios: (i) outdoor to indoor generalization, (ii) sparse-beam \& dense-beam adaptation, and (iii) non-semantic to semantic transfer. Given different amounts of fine-tuning data, our experiments show that a single pre-trained model can achieve up to 11% absolute improvement (83\% relative) over training from scratch and outperforms training from scratch in 30/36 of our comparisons. This transferability of dynamic learning significantly reduces the reliance on manually annotated data for semantic occupancy forecasting: our method exceed the previous semantic occupancy forecasting models with only 5% of the labeled training data required by prior models. We also observed inefficiencies of current LiDAR world models, mainly through their under-compression of LiDAR data and inefficient training objectives. To address this, we propose a latent conditional flow matching (CFM)-based frameworks that achieves state-of-the-art reconstruction accuracy using only half the training data and a compression ratio 6 times higher than that of prior methods. Our model achieves SOTA performance on future-trajectory-conditioned semantic occupancy forecasting while being 23x more computationally efficient (a 28x FPS speedup); and achieves SOTA performance on semantic occupancy forecasting while being 2x more computationally efficient (a 1.1x FPS speedup). △ Less

Submitted 29 June, 2025; originally announced June 2025.

Comments: 25 pages, 13 figures

Layer Decomposition and Morphological Reconstruction for Task-Oriented Infrared Image Enhancement

Authors: Siyuan Chai, Xiaodong Guo, Tong Liu

Abstract: Infrared image helps improve the perception capabilities of autonomous driving in complex weather conditions such as fog, rain, and low light. However, infrared image often suffers from low contrast, especially in non-heat-emitting targets like bicycles, which significantly affects the performance of downstream high-level vision tasks. Furthermore, achieving contrast enhancement without amplifying… ▽ More Infrared image helps improve the perception capabilities of autonomous driving in complex weather conditions such as fog, rain, and low light. However, infrared image often suffers from low contrast, especially in non-heat-emitting targets like bicycles, which significantly affects the performance of downstream high-level vision tasks. Furthermore, achieving contrast enhancement without amplifying noise and losing important information remains a challenge. To address these challenges, we propose a task-oriented infrared image enhancement method. Our approach consists of two key components: layer decomposition and saliency information extraction. First, we design an layer decomposition method for infrared images, which enhances scene details while preserving dark region features, providing more features for subsequent saliency information extraction. Then, we propose a morphological reconstruction-based saliency extraction method that effectively extracts and enhances target information without amplifying noise. Our method improves the image quality for object detection and semantic segmentation tasks. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods. △ Less

Submitted 29 June, 2025; originally announced June 2025.

Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop

Authors: Tianxing Chen, Kaixuan Wang, Zhaohui Yang, Yuhao Zhang, Zanxin Chen, Baijun Chen, Wanxi Dong, Ziyuan Liu, Dong Chen, Tianshuo Yang, Haibao Yu, Xiaokang Yang, Yusen Qin, Zhiqiang Xie, Yao Mu, Ping Luo, Tian Nian, Weiliang Deng, Yiheng Ge, Yibin Liu, Zixuan Li, Dehui Wang, Zhixuan Liang, Haohui Xie, Rijie Zeng , et al. (74 additional authors not shown)

Abstract: Embodied Artificial Intelligence (Embodied AI) is an emerging frontier in robotics, driven by the need for autonomous systems that can perceive, reason, and act in complex physical environments. While single-arm systems have shown strong task performance, collaborative dual-arm systems are essential for handling more intricate tasks involving rigid, deformable, and tactile-sensitive objects. To ad… ▽ More Embodied Artificial Intelligence (Embodied AI) is an emerging frontier in robotics, driven by the need for autonomous systems that can perceive, reason, and act in complex physical environments. While single-arm systems have shown strong task performance, collaborative dual-arm systems are essential for handling more intricate tasks involving rigid, deformable, and tactile-sensitive objects. To advance this goal, we launched the RoboTwin Dual-Arm Collaboration Challenge at the 2nd MEIS Workshop, CVPR 2025. Built on the RoboTwin Simulation platform (1.0 and 2.0) and the AgileX COBOT-Magic Robot platform, the competition consisted of three stages: Simulation Round 1, Simulation Round 2, and a final Real-World Round. Participants totally tackled 17 dual-arm manipulation tasks, covering rigid, deformable, and tactile-based scenarios. The challenge attracted 64 global teams and over 400 participants, producing top-performing solutions like SEM and AnchorDP3 and generating valuable insights into generalizable bimanual policy learning. This report outlines the competition setup, task design, evaluation methodology, key findings and future direction, aiming to support future research on robust and generalizable bimanual manipulation policies. The Challenge Webpage is available at https://robotwin-benchmark.github.io/cvpr-2025-challenge/. △ Less

Submitted 2 July, 2025; v1 submitted 29 June, 2025; originally announced June 2025.

Comments: Challenge Webpage: https://robotwin-benchmark.github.io/cvpr-2025-challenge/

UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding

Authors: Jie Feng, Shengyuan Wang, Tianhui Liu, Yanxin Xi, Yong Li

Abstract: Urban research involves a wide range of scenarios and tasks that require the understanding of multi-modal data. Current methods often focus on specific data types and lack a unified framework in urban field for processing them comprehensively. The recent success of multi-modal large language models (MLLMs) presents a promising opportunity to overcome this limitation. In this paper, we introduce… ▽ More Urban research involves a wide range of scenarios and tasks that require the understanding of multi-modal data. Current methods often focus on specific data types and lack a unified framework in urban field for processing them comprehensively. The recent success of multi-modal large language models (MLLMs) presents a promising opportunity to overcome this limitation. In this paper, we introduce $\textit{UrbanLLaVA}$, a multi-modal large language model designed to process these four types of data simultaneously and achieve strong performance across diverse urban tasks compared with general MLLMs. In $\textit{UrbanLLaVA}$, we first curate a diverse urban instruction dataset encompassing both single-modal and cross-modal urban data, spanning from location view to global view of urban environment. Additionally, we propose a multi-stage training framework that decouples spatial reasoning enhancement from domain knowledge learning, thereby improving the compatibility and downstream performance of $\textit{UrbanLLaVA}$ across diverse urban tasks. Finally, we also extend existing benchmark for urban research to assess the performance of MLLMs across a wide range of urban tasks. Experimental results from three cities demonstrate that $\textit{UrbanLLaVA}$ outperforms open-source and proprietary MLLMs in both single-modal tasks and complex cross-modal tasks and shows robust generalization abilities across cities. Source codes and data are openly accessible to the research community via https://github.com/tsinghua-fib-lab/UrbanLLaVA. △ Less

Submitted 29 June, 2025; originally announced June 2025.

Comments: Accepted by ICCV 2025

VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs

Authors: Raghavv Goel, Sudhanshu Agrawal, Mukul Gagrani, Junyoung Park, Yifan Zao, He Zhang, Tian Liu, Yiping Yang, Xin Yuan, Jiuyan Lu, Chris Lott, Mingu Lee

Abstract: In this paper, we introduce a simple training-free technique to improve the performance of drafter-based speculative decoding (SpD) methods that incorporates language modeling head (LM head) during drafting process. A drafter-based speculative decoding leverages one or more smaller language models, a.k.a. drafters or draft models, to sample a draft sequence or tree consisting of multiple tokens, f… ▽ More In this paper, we introduce a simple training-free technique to improve the performance of drafter-based speculative decoding (SpD) methods that incorporates language modeling head (LM head) during drafting process. A drafter-based speculative decoding leverages one or more smaller language models, a.k.a. drafters or draft models, to sample a draft sequence or tree consisting of multiple tokens, followed by verification by a base LLM, a target model, accepting a subset as its valid generation. As it is usually considered that the speculative decoding requires one-to-one mapping between vocabularies of the target model and the draft model, it has been natural to share the vocabulary between them, or even share the LM head as in EAGLE or Medusa. We first identify that this draft token sampling scheme inherently contains an unnecessary inference overhead in drafting, especially for some target LLMs with very large vocabularies. Then, we propose a simple technique, VocabTrim, to mitigate the drafting overhead to improve the generation speed in memory-bound environment. VocabTrim reconstructs the drafter LM head to contain only a limited set of tokens, selected by the most frequently sampled from the vocabulary of the target model. While limiting the vocabulary in drafting slightly degrades the acceptance rate, it significantly reduces the drafting latency in memory-bound process which is often the case on edge devices, resulting in higher memory-bound speed up (MBSU). We show that our method can boost the memory-bound speed-up for Llama-3 models on Spec-Bench, specifically by 16% for Llama-3.2-3B-Instruct. △ Less

Submitted 3 July, 2025; v1 submitted 27 June, 2025; originally announced June 2025.

Comments: 8 pages, 4 figures, 5 tables, accepted at ICML 2025 workshop on Efficient Systems for Foundational Models

CoATA: Effective Co-Augmentation of Topology and Attribute for Graph Neural Networks

Authors: Tao Liu, Longlong Lin, Yunfeng Yu, Xi Ou, Youan Zhang, Zhiqiu Ye, Tao Jia

Abstract: Graph Neural Networks (GNNs) have garnered substantial attention due to their remarkable capability in learning graph representations. However, real-world graphs often exhibit substantial noise and incompleteness, which severely degrades the performance of GNNs. Existing methods typically address this issue through single-dimensional augmentation, focusing either on refining topology structures or… ▽ More Graph Neural Networks (GNNs) have garnered substantial attention due to their remarkable capability in learning graph representations. However, real-world graphs often exhibit substantial noise and incompleteness, which severely degrades the performance of GNNs. Existing methods typically address this issue through single-dimensional augmentation, focusing either on refining topology structures or perturbing node attributes, thereby overlooking the deeper interplays between the two. To bridge this gap, this paper presents CoATA, a dual-channel GNN framework specifically designed for the Co-Augmentation of Topology and Attribute. Specifically, CoATA first propagates structural signals to enrich and denoise node attributes. Then, it projects the enhanced attribute space into a node-attribute bipartite graph for further refinement or reconstruction of the underlying structure. Subsequently, CoATA introduces contrastive learning, leveraging prototype alignment and consistency constraints, to facilitate mutual corrections between the augmented and original graphs. Finally, extensive experiments on seven benchmark datasets demonstrate that the proposed CoATA outperforms eleven state-of-the-art baseline methods, showcasing its effectiveness in capturing the synergistic relationship between topology and attributes. △ Less

Submitted 27 June, 2025; originally announced June 2025.

Comments: icmr

ACM Class: I.2

Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?

Authors: Haoang Chi, He Li, Wenjing Yang, Feng Liu, Long Lan, Xiaoguang Ren, Tongliang Liu, Bo Han

Abstract: Causal reasoning capability is critical in advancing large language models (LLMs) toward strong artificial intelligence. While versatile LLMs appear to have demonstrated capabilities in understanding contextual causality and providing responses that obey the laws of causality, it remains unclear whether they perform genuine causal reasoning akin to humans. However, current evidence indicates the c… ▽ More Causal reasoning capability is critical in advancing large language models (LLMs) toward strong artificial intelligence. While versatile LLMs appear to have demonstrated capabilities in understanding contextual causality and providing responses that obey the laws of causality, it remains unclear whether they perform genuine causal reasoning akin to humans. However, current evidence indicates the contrary. Specifically, LLMs are only capable of performing shallow (level-1) causal reasoning, primarily attributed to the causal knowledge embedded in their parameters, but they lack the capacity for genuine human-like (level-2) causal reasoning. To support this hypothesis, methodologically, we delve into the autoregression mechanism of transformer-based LLMs, revealing that it is not inherently causal. Empirically, we introduce a new causal Q&A benchmark called CausalProbe-2024, whose corpora are fresh and nearly unseen for the studied LLMs. The LLMs exhibit a significant performance drop on CausalProbe-2024 compared to earlier benchmarks, indicating the fact that they primarily engage in level-1 causal reasoning. To bridge the gap towards level-2 causal reasoning, we draw inspiration from the fact that human reasoning is usually facilitated by general knowledge and intended goals. We propose G^2-Reasoner, a method that incorporates general knowledge and goal-oriented prompts into LLMs' causal reasoning processes. Experiments demonstrate that G^2-Reasoner significantly enhances LLMs' causal reasoning capability, particularly in fresh and counterfactual contexts. This work sheds light on a new path for LLMs to advance towards genuine causal reasoning, going beyond level-1 and making strides towards level-2. △ Less

Submitted 26 June, 2025; originally announced June 2025.

Comments: 24 pages, accepted at NeurIPS 2024

Journal ref: Advances in Neural Information Processing Systems, 2024, 37: 96640-96670

From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging

Authors: Tao Liu, Dafeng Zhang, Gengchen Li, Shizhuo Liu, Yongqi Song, Senmao Li, Shiqi Yang, Boqian Li, Kai Wang, Yaxing Wang

Abstract: Face aging has become a crucial task in computer vision, with applications ranging from entertainment to healthcare. However, existing methods struggle with achieving a realistic and seamless transformation across the entire lifespan, especially when handling large age gaps or extreme head poses. The core challenge lies in balancing age accuracy and identity preservation--what we refer to as the A… ▽ More Face aging has become a crucial task in computer vision, with applications ranging from entertainment to healthcare. However, existing methods struggle with achieving a realistic and seamless transformation across the entire lifespan, especially when handling large age gaps or extreme head poses. The core challenge lies in balancing age accuracy and identity preservation--what we refer to as the Age-ID trade-off. Most prior methods either prioritize age transformation at the expense of identity consistency or vice versa. In this work, we address this issue by proposing a two-pass face aging framework, named Cradle2Cane, based on few-step text-to-image (T2I) diffusion models. The first pass focuses on solving age accuracy by introducing an adaptive noise injection (AdaNI) mechanism. This mechanism is guided by including prompt descriptions of age and gender for the given person as the textual condition. Also, by adjusting the noise level, we can control the strength of aging while allowing more flexibility in transforming the face. However, identity preservation is weakly ensured here to facilitate stronger age transformations. In the second pass, we enhance identity preservation while maintaining age-specific features by conditioning the model on two identity-aware embeddings (IDEmb): SVR-ArcFace and Rotate-CLIP. This pass allows for denoising the transformed image from the first pass, ensuring stronger identity preservation without compromising the aging accuracy. Both passes are jointly trained in an end-to-end way. Extensive experiments on the CelebA-HQ test dataset, evaluated through Face++ and Qwen-VL protocols, show that our Cradle2Cane outperforms existing face aging methods in age accuracy and identity consistency. △ Less

Submitted 25 June, 2025; originally announced June 2025.

Comments: 30 pages, 12 figures

EANS: Reducing Energy Consumption for UAV with an Environmental Adaptive Navigation Strategy

Authors: Tian Liu, Han Liu, Boyang Li, Long Chen, Kai Huang

Abstract: Unmanned Aerial Vehicles (UAVS) are limited by the onboard energy. Refinement of the navigation strategy directly affects both the flight velocity and the trajectory based on the adjustment of key parameters in the UAVS pipeline, thus reducing energy consumption. However, existing techniques tend to adopt static and conservative strategies in dynamic scenarios, leading to inefficient energy reduct… ▽ More Unmanned Aerial Vehicles (UAVS) are limited by the onboard energy. Refinement of the navigation strategy directly affects both the flight velocity and the trajectory based on the adjustment of key parameters in the UAVS pipeline, thus reducing energy consumption. However, existing techniques tend to adopt static and conservative strategies in dynamic scenarios, leading to inefficient energy reduction. Dynamically adjusting the navigation strategy requires overcoming the challenges including the task pipeline interdependencies, the environmental-strategy correlations, and the selecting parameters. To solve the aforementioned problems, this paper proposes a method to dynamically adjust the navigation strategy of the UAVS by analyzing its dynamic characteristics and the temporal characteristics of the autonomous navigation pipeline, thereby reducing UAVS energy consumption in response to environmental changes. We compare our method with the baseline through hardware-in-the-loop (HIL) simulation and real-world experiments, showing our method 3.2X and 2.6X improvements in mission time, 2.4X and 1.6X improvements in energy, respectively. △ Less

Submitted 25 June, 2025; originally announced June 2025.

What Makes the Best Decomposition? Investigating Binary Decomposition Under FCG Variance

Authors: Ang Jia, He Jiang, Zhilei Ren, Xiaochen Li, Ming Fan, Ting Liu

Abstract: Binary decomposition, which decomposes binary files into modules, plays a critical role in binary reuse detection. Existing binary decomposition works either apply anchor-based methods by extending anchor functions to generate modules, or apply clustering-based methods by using clustering algorithms to group binary functions, which all rely on that reused code shares similar function call relation… ▽ More Binary decomposition, which decomposes binary files into modules, plays a critical role in binary reuse detection. Existing binary decomposition works either apply anchor-based methods by extending anchor functions to generate modules, or apply clustering-based methods by using clustering algorithms to group binary functions, which all rely on that reused code shares similar function call relationships. However, we find that function call graphs (FCGs) vary a lot when using different compilation settings, especially with diverse function inlining decisions. In this work, we conduct the first systematic empirical study on the variance of FCGs compiled by various compilation settings and explore its effect on binary decomposition methods. We first construct a dataset compiled by 17 compilers, using 6 optimizations to 4 architectures and analyze the changes and mappings of the FCGs. We find that the size of FCGs changes dramatically, while the FCGs are still linked by three different kinds of mappings. Then we evaluate the existing works under the FCG variance, and results show that existing works are facing great challenges when conducting cross-compiler evaluation with diverse optimization settings. Finally, we propose a method to identify the optimal decomposition and compare the existing decomposition works with the optimal decomposition. Existing works either suffer from low coverage or cannot generate stable community similarities. △ Less

Submitted 24 June, 2025; originally announced June 2025.

Survey of HPC in US Research Institutions

Authors: Peng Shu, Junhao Chen, Zhengliang Liu, Huaqin Zhao, Xinliang Li, Tianming Liu

Abstract: The rapid growth of AI, data-intensive science, and digital twin technologies has driven an unprecedented demand for high-performance computing (HPC) across the research ecosystem. While national laboratories and industrial hyperscalers have invested heavily in exascale and GPU-centric architectures, university-operated HPC systems remain comparatively under-resourced. This survey presents a compr… ▽ More The rapid growth of AI, data-intensive science, and digital twin technologies has driven an unprecedented demand for high-performance computing (HPC) across the research ecosystem. While national laboratories and industrial hyperscalers have invested heavily in exascale and GPU-centric architectures, university-operated HPC systems remain comparatively under-resourced. This survey presents a comprehensive assessment of the HPC landscape across U.S. universities, benchmarking their capabilities against Department of Energy (DOE) leadership-class systems and industrial AI infrastructures. We examine over 50 premier research institutions, analyzing compute capacity, architectural design, governance models, and energy efficiency. Our findings reveal that university clusters, though vital for academic research, exhibit significantly lower growth trajectories (CAGR $\approx$ 18%) than their national ($\approx$ 43%) and industrial ($\approx$ 78%) counterparts. The increasing skew toward GPU-dense AI workloads has widened the capability gap, highlighting the need for federated computing, idle-GPU harvesting, and cost-sharing models. We also identify emerging paradigms, such as decentralized reinforcement learning, as promising opportunities for democratizing AI training within campus environments. Ultimately, this work provides actionable insights for academic leaders, funding agencies, and technology partners to ensure more equitable and sustainable HPC access in support of national research priorities. △ Less

Submitted 23 June, 2025; originally announced June 2025.

DiffRIS: Enhancing Referring Remote Sensing Image Segmentation with Pre-trained Text-to-Image Diffusion Models

Authors: Zhe Dong, Yuzhe Sun, Tianzhu Liu, Yanfeng Gu

Abstract: Referring remote sensing image segmentation (RRSIS) enables the precise delineation of regions within remote sensing imagery through natural language descriptions, serving critical applications in disaster response, urban development, and environmental monitoring. Despite recent advances, current approaches face significant challenges in processing aerial imagery due to complex object characterist… ▽ More Referring remote sensing image segmentation (RRSIS) enables the precise delineation of regions within remote sensing imagery through natural language descriptions, serving critical applications in disaster response, urban development, and environmental monitoring. Despite recent advances, current approaches face significant challenges in processing aerial imagery due to complex object characteristics including scale variations, diverse orientations, and semantic ambiguities inherent to the overhead perspective. To address these limitations, we propose DiffRIS, a novel framework that harnesses the semantic understanding capabilities of pre-trained text-to-image diffusion models for enhanced cross-modal alignment in RRSIS tasks. Our framework introduces two key innovations: a context perception adapter (CP-adapter) that dynamically refines linguistic features through global context modeling and object-aware reasoning, and a progressive cross-modal reasoning decoder (PCMRD) that iteratively aligns textual descriptions with visual regions for precise segmentation. The CP-adapter bridges the domain gap between general vision-language understanding and remote sensing applications, while PCMRD enables fine-grained semantic alignment through multi-scale feature interaction. Comprehensive experiments on three benchmark datasets-RRSIS-D, RefSegRS, and RISBench-demonstrate that DiffRIS consistently outperforms existing methods across all standard metrics, establishing a new state-of-the-art for RRSIS tasks. The significant performance improvements validate the effectiveness of leveraging pre-trained diffusion models for remote sensing applications through our proposed adaptive framework. △ Less

Submitted 22 June, 2025; originally announced June 2025.

RPHunter: Unveiling Rug Pull Schemes in Crypto Token via Code-and-Transaction Fusion Analysis

Authors: Hao Wu, Haijun Wang, Shangwang Li, Yin Wu, Ming Fan, Wuxia Jin, Ting Liu

Abstract: Rug pull scams have emerged as a persistent threat to cryptocurrency, causing significant financial losses. A typical scenario involves scammers deploying honeypot contracts to attract investments, restricting token sales, and draining the funds, which leaves investors with worthless tokens. Current methods either rely on predefined patterns to detect code risks or utilize statistical transaction… ▽ More Rug pull scams have emerged as a persistent threat to cryptocurrency, causing significant financial losses. A typical scenario involves scammers deploying honeypot contracts to attract investments, restricting token sales, and draining the funds, which leaves investors with worthless tokens. Current methods either rely on predefined patterns to detect code risks or utilize statistical transaction data to train detection models. However, real-world Rug Pull schemes often involve a complex interplay between malicious code and suspicious transaction behaviors. These methods, which solely focus on one aspect, fall short in detecting such schemes effectively. In this paper, we propose RPHunter, a novel technique that integrates code and transaction for Rug Pull detection. First, RPHunter establishes declarative rules and performs flow analysis to extract code risk information, further constructing a semantic risk code graph (SRCG). Meanwhile, to leverage transaction information, RPHunter formulates dynamic token transaction activities as a token flow behavior graph (TFBG) in which nodes and edges are characterized from network structure and market manipulation perspectives. Finally, RPHunter employs graph neural networks to extract complementary features from SRCG and TFBG, integrating them through an attention fusion model to enhance the detection of Rug Pull. We manually analyzed 645 Rug Pull incidents from code and transaction aspects and constructed a ground-truth dataset. We evaluated RPHunter on our dataset, achieving a precision of 95.3%, a recall of 93.8% and an F1 score of 94.5%, which highlights superior performance compared to existing methods. Furthermore, when applied to the real-world scenarios, RPHunter has identified 4801 Rug Pull tokens, achieving a precision of 90.7%. △ Less

Submitted 8 July, 2025; v1 submitted 23 June, 2025; originally announced June 2025.

Cross-modal State Space Modeling for Real-time RGB-thermal Wild Scene Semantic Segmentation

Authors: Xiaodong Guo, Zi'ang Lin, Luwen Hu, Zhihong Deng, Tong Liu, Wujie Zhou

Abstract: The integration of RGB and thermal data can significantly improve semantic segmentation performance in wild environments for field robots. Nevertheless, multi-source data processing (e.g. Transformer-based approaches) imposes significant computational overhead, presenting challenges for resource-constrained systems. To resolve this critical limitation, we introduced CM-SSM, an efficient RGB-therma… ▽ More The integration of RGB and thermal data can significantly improve semantic segmentation performance in wild environments for field robots. Nevertheless, multi-source data processing (e.g. Transformer-based approaches) imposes significant computational overhead, presenting challenges for resource-constrained systems. To resolve this critical limitation, we introduced CM-SSM, an efficient RGB-thermal semantic segmentation architecture leveraging a cross-modal state space modeling (SSM) approach. Our framework comprises two key components. First, we introduced a cross-modal 2D-selective-scan (CM-SS2D) module to establish SSM between RGB and thermal modalities, which constructs cross-modal visual sequences and derives hidden state representations of one modality from the other. Second, we developed a cross-modal state space association (CM-SSA) module that effectively integrates global associations from CM-SS2D with local spatial features extracted through convolutional operations. In contrast with Transformer-based approaches, CM-SSM achieves linear computational complexity with respect to image resolution. Experimental results show that CM-SSM achieves state-of-the-art performance on the CART dataset with fewer parameters and lower computational cost. Further experiments on the PST900 dataset demonstrate its generalizability. Codes are available at https://github.com/xiaodonguo/CMSSM. △ Less

Submitted 21 June, 2025; originally announced June 2025.

MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization

Authors: Tingting Liu, Yuan Liu, Jinhui Tang, Liyin Yuan, Chengyu Liu, Chunlai Li, Xiubao Sui, Qian Chen

Abstract: Thermal infrared (TIR) images, acquired through thermal radiation imaging, are unaffected by variations in lighting conditions and atmospheric haze. However, TIR images inherently lack color and texture information, limiting downstream tasks and potentially causing visual fatigue. Existing colorization methods primarily rely on single-band images with limited spectral information and insufficient… ▽ More Thermal infrared (TIR) images, acquired through thermal radiation imaging, are unaffected by variations in lighting conditions and atmospheric haze. However, TIR images inherently lack color and texture information, limiting downstream tasks and potentially causing visual fatigue. Existing colorization methods primarily rely on single-band images with limited spectral information and insufficient feature extraction capabilities, which often result in image distortion and semantic ambiguity. In contrast, multiband infrared imagery provides richer spectral data, facilitating the preservation of finer details and enhancing semantic accuracy. In this paper, we propose a generative adversarial network (GAN)-based framework designed to integrate spectral information to enhance the colorization of infrared images. The framework employs a multi-stage spectral self-attention Transformer network (MTSIC) as the generator. Each spectral feature is treated as a token for self-attention computation, and a multi-head self-attention mechanism forms a spatial-spectral attention residual block (SARB), achieving multi-band feature mapping and reducing semantic confusion. Multiple SARB units are integrated into a Transformer-based single-stage network (STformer), which uses a U-shaped architecture to extract contextual information, combined with multi-scale wavelet blocks (MSWB) to align semantic information in the spatial-frequency dual domain. Multiple STformer modules are cascaded to form MTSIC, progressively optimizing the reconstruction quality. Experimental results demonstrate that the proposed method significantly outperforms traditional techniques and effectively enhances the visual quality of infrared images. △ Less

Submitted 20 June, 2025; originally announced June 2025.

Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details

Authors: Zeqiang Lai, Yunfei Zhao, Haolin Liu, Zibo Zhao, Qingxiang Lin, Huiwen Shi, Xianghui Yang, Mingxin Yang, Shuhui Yang, Yifei Feng, Sheng Zhang, Xin Huang, Di Luo, Fan Yang, Fang Yang, Lifu Wang, Sicong Liu, Yixuan Tang, Yulin Cai, Zebin He, Tian Liu, Yuhong Liu, Jie Jiang, Linus, Jingwei Huang , et al. (1 additional authors not shown)

Abstract: In this report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which… ▽ More In this report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which is trained with scaled high-quality datasets, model-size, and compute. Our largest model reaches 10B parameters and generates sharp and detailed 3D shape with precise image-3D following while keeping mesh surface clean and smooth, significantly closing the gap between generated and handcrafted 3D shapes. In terms of texture generation, it is upgraded with phyiscal-based rendering (PBR) via a novel multi-view architecture extended from Hunyuan3D 2.0 Paint model. Our extensive evaluation shows that Hunyuan3D 2.5 significantly outperforms previous methods in both shape and end-to-end texture generation. △ Less

Submitted 19 June, 2025; originally announced June 2025.

Comments: Technical report

OJBench: A Competition Level Code Benchmark For Large Language Models

Authors: Zhexu Wang, Yiping Liu, Yejie Wang, Wenyang He, Bofei Gao, Muxi Diao, Yanxu Chen, Kelin Fu, Flood Sung, Zhilin Yang, Tianyu Liu, Weiran Xu

Abstract: Recent advancements in large language models (LLMs) have demonstrated significant progress in math and code reasoning capabilities. However, existing code benchmark are limited in their ability to evaluate the full spectrum of these capabilities, particularly at the competitive level. To bridge this gap, we introduce OJBench, a novel and challenging benchmark designed to assess the competitive-lev… ▽ More Recent advancements in large language models (LLMs) have demonstrated significant progress in math and code reasoning capabilities. However, existing code benchmark are limited in their ability to evaluate the full spectrum of these capabilities, particularly at the competitive level. To bridge this gap, we introduce OJBench, a novel and challenging benchmark designed to assess the competitive-level code reasoning abilities of LLMs. OJBench comprises 232 programming competition problems from NOI and ICPC, providing a more rigorous test of models' reasoning skills. We conducted a comprehensive evaluation using OJBench on 37 models, including both closed-source and open-source models, reasoning-oriented and non-reasoning-oriented models. Our results indicate that even state-of-the-art reasoning-oriented models, such as o4-mini and Gemini-2.5-pro-exp, struggle with highly challenging competition-level problems. This highlights the significant challenges that models face in competitive-level code reasoning. △ Less

Submitted 19 June, 2025; originally announced June 2025.

Comments: 9 pages, 5 figures

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

Authors: Puhao Li, Yingying Wu, Ziheng Xi, Wanlin Li, Yuzhe Huang, Zhiyuan Zhang, Yinghan Chen, Jianan Wang, Song-Chun Zhu, Tengyu Liu, Siyuan Huang

Abstract: Learning real-world robotic manipulation is challenging, particularly when limited demonstrations are available. Existing methods for few-shot manipulation often rely on simulation-augmented data or pre-built modules like grasping and pose estimation, which struggle with sim-to-real gaps and lack extensibility. While large-scale imitation pre-training shows promise, adapting these general-purpose… ▽ More Learning real-world robotic manipulation is challenging, particularly when limited demonstrations are available. Existing methods for few-shot manipulation often rely on simulation-augmented data or pre-built modules like grasping and pose estimation, which struggle with sim-to-real gaps and lack extensibility. While large-scale imitation pre-training shows promise, adapting these general-purpose policies to specific tasks in data-scarce settings remains unexplored. To achieve this, we propose ControlVLA, a novel framework that bridges pre-trained VLA models with object-centric representations via a ControlNet-style architecture for efficient fine-tuning. Specifically, to introduce object-centric conditions without overwriting prior knowledge, ControlVLA zero-initializes a set of projection layers, allowing them to gradually adapt the pre-trained manipulation policies. In real-world experiments across 6 diverse tasks, including pouring cubes and folding clothes, our method achieves a 76.7% success rate while requiring only 10-20 demonstrations -- a significant improvement over traditional approaches that require more than 100 demonstrations to achieve comparable success. Additional experiments highlight ControlVLA's extensibility to long-horizon tasks and robustness to unseen objects and backgrounds. △ Less

Submitted 19 June, 2025; originally announced June 2025.

Comments: Website: https://controlvla.github.io

ETrace:Event-Driven Vulnerability Detection in Smart Contracts via LLM-Based Trace Analysis

Authors: Chenyang Peng, Haijun Wang, Yin Wu, Hao Wu, Ming Fan, Yitao Zhao, Ting Liu

Abstract: With the advance application of blockchain technology in various fields, ensuring the security and stability of smart contracts has emerged as a critical challenge. Current security analysis methodologies in vulnerability detection can be categorized into static analysis and dynamic analysis methods.However, these existing traditional vulnerability detection methods predominantly rely on analyzing… ▽ More With the advance application of blockchain technology in various fields, ensuring the security and stability of smart contracts has emerged as a critical challenge. Current security analysis methodologies in vulnerability detection can be categorized into static analysis and dynamic analysis methods.However, these existing traditional vulnerability detection methods predominantly rely on analyzing original contract code, not all smart contracts provide accessible code.We present ETrace, a novel event-driven vulnerability detection framework for smart contracts, which uniquely identifies potential vulnerabilities through LLM-powered trace analysis without requiring source code access. By extracting fine-grained event sequences from transaction logs, the framework leverages Large Language Models (LLMs) as adaptive semantic interpreters to reconstruct event analysis through chain-of-thought reasoning. ETrace implements pattern-matching to establish causal links between transaction behavior patterns and known attack behaviors. Furthermore, we validate the effectiveness of ETrace through preliminary experimental results. △ Less

Submitted 8 July, 2025; v1 submitted 18 June, 2025; originally announced June 2025.

Comments: 4 pages, 1 figure. Submitted to the 16th Asia-Pacific Symposium on Internetware (Internetware 2025)

MSC Class: 68N01 ACM Class: D.2.0

Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement

Authors: Weixiang Zhao, Jiahe Guo, Yang Deng, Xingyu Sui, Yulin Hu, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu

Abstract: Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative thinking. However, these models often exhibit overthinking (i.e., the generation of unnecessarily verbose and redundant content), which hinders efficiency and inflates inference cost. In this work, we explore the representati… ▽ More Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative thinking. However, these models often exhibit overthinking (i.e., the generation of unnecessarily verbose and redundant content), which hinders efficiency and inflates inference cost. In this work, we explore the representational and behavioral origins of this inefficiency, revealing that LRMs inherently possess the capacity for more concise reasoning. Empirical analyses show that correct reasoning paths vary significantly in length, and the shortest correct responses often suffice, indicating untapped efficiency potential. Exploiting these findings, we propose two lightweight methods to enhance LRM efficiency. First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction in the model's representation space. Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity by rewarding concise correct solutions. Extensive experiments on seven LRM backbones across multiple mathematical reasoning benchmarks demonstrate that our methods significantly reduce reasoning length while preserving or improving task performance. Our results highlight that reasoning efficiency can be improved by leveraging and guiding the intrinsic capabilities of existing models in a self-guided manner. △ Less

Submitted 18 June, 2025; originally announced June 2025.

Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Authors: Team Hunyuan3D, Shuhui Yang, Mingxin Yang, Yifei Feng, Xin Huang, Sheng Zhang, Zebin He, Di Luo, Haolin Liu, Yunfei Zhao, Qingxiang Lin, Zeqiang Lai, Xianghui Yang, Huiwen Shi, Zibo Zhao, Bowen Zhang, Hongyu Yan, Lifu Wang, Sicong Liu, Jihong Zhang, Meng Chen, Liang Dong, Yiwen Jia, Yulin Cai, Jiaao Yu , et al. (28 additional authors not shown)

Abstract: 3D AI-generated content (AIGC) is a passionate field that has significantly accelerated the creation of 3D models in gaming, film, and design. Despite the development of several groundbreaking models that have revolutionized 3D generation, the field remains largely accessible only to researchers, developers, and designers due to the complexities involved in collecting, processing, and training 3D… ▽ More 3D AI-generated content (AIGC) is a passionate field that has significantly accelerated the creation of 3D models in gaming, film, and design. Despite the development of several groundbreaking models that have revolutionized 3D generation, the field remains largely accessible only to researchers, developers, and designers due to the complexities involved in collecting, processing, and training 3D models. To address these challenges, we introduce Hunyuan3D 2.1 as a case study in this tutorial. This tutorial offers a comprehensive, step-by-step guide on processing 3D data, training a 3D generative model, and evaluating its performance using Hunyuan3D 2.1, an advanced system for producing high-resolution, textured 3D assets. The system comprises two core components: the Hunyuan3D-DiT for shape generation and the Hunyuan3D-Paint for texture synthesis. We will explore the entire workflow, including data preparation, model architecture, training strategies, evaluation metrics, and deployment. By the conclusion of this tutorial, you will have the knowledge to finetune or develop a robust 3D generative model suitable for applications in gaming, virtual reality, and industrial design. △ Less

Submitted 18 June, 2025; originally announced June 2025.

Comments: Github link: https://github.com/Tencent-Hunyuan/Hunyuan3D-2.1

Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference

Authors: Terrance Liu, Matteo Boglioni, Yiwei Fu, Shengyuan Hu, Pratiksha Thaker, Zhiwei Steven Wu

Abstract: Differential privacy (DP) auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many training runs that are prohibitively costly, recent work introduces one-run auditing approaches that effectively audit DP-SGD in white-box settings while still being computationally efficient. However, in the more practical bl… ▽ More Differential privacy (DP) auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many training runs that are prohibitively costly, recent work introduces one-run auditing approaches that effectively audit DP-SGD in white-box settings while still being computationally efficient. However, in the more practical black-box setting where gradients cannot be manipulated during training and only the last model iterate is observed, prior work shows that there is still a large gap between the empirical lower bounds and theoretical upper bounds. Consequently, in this work, we study how incorporating approaches for stronger membership inference attacks (MIA) can improve one-run auditing in the black-box setting. Evaluating on image classification models trained on CIFAR-10 with DP-SGD, we demonstrate that our proposed approach, which utilizes quantile regression for MIA, achieves tighter bounds while crucially maintaining the computational efficiency of one-run methods. △ Less

Submitted 18 June, 2025; originally announced June 2025.

ChatModel: Automating Reference Model Design and Verification with LLMs

Authors: Jianmin Ye, Tianyang Liu, Qi Tian, Shengchu Su, Zhe Jiang, Xi Wang

Abstract: As the complexity of integrated circuit designs continues to escalate, the functional verification becomes increasingly challenging. Reference models, critical for accelerating the verification process, are themselves becoming more intricate and time-consuming to develop. Despite the promise shown by large language models (LLMs) in code programming, effectively generating complex reference models… ▽ More As the complexity of integrated circuit designs continues to escalate, the functional verification becomes increasingly challenging. Reference models, critical for accelerating the verification process, are themselves becoming more intricate and time-consuming to develop. Despite the promise shown by large language models (LLMs) in code programming, effectively generating complex reference models remains a significant hurdle. To address these challenges, we introduce ChatModel, the first LLM-aided agile reference model generation and verification platform. ChatModel streamlines the transition from design specifications to fully functional reference models by integrating design standardization and hierarchical agile modeling. Employing a building-block generation strategy, it not only enhances the design capabilities of LLMs for reference models but also significantly boosts verification efficiency. We evaluated ChatModel on 300 designs of varying complexity, demonstrating substantial improvements in both efficiency and quality of reference model generation. ChatModel achieved a peak performance improvement of 55.02% compared to alternative methods, with notable enhancements in generation stability, and delivered a 9.18x increase in its capacity to produce reference model designs. Furthermore, it accelerated the iterative process of reference model design and validation by an average of 5.90x compared to traditional approaches. These results highlight the potential of ChatModel to significantly advance the automation of reference model generation and validation. △ Less

Submitted 24 June, 2025; v1 submitted 17 June, 2025; originally announced June 2025.

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Authors: Zhoujun Cheng, Shibo Hao, Tianyang Liu, Fan Zhou, Yutao Xie, Feng Yao, Yuexin Bian, Yonghao Zhuang, Nilabjo Dey, Yuheng Zha, Yi Gu, Kun Zhou, Yuqi Wang, Yuan Li, Richard Fan, Jianshu She, Chengqian Gao, Abulhair Saparov, Haonan Li, Taylor W. Killian, Mikhail Yurochkin, Zhengzhong Liu, Eric P. Xing, Zhiting Hu

Abstract: Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general reasoning. A key challenge lies in the lack of reliable, scalable RL reward signals across diverse reasoning domains. We introduce Guru, a curated RL reasoning corpu… ▽ More Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general reasoning. A key challenge lies in the lack of reliable, scalable RL reward signals across diverse reasoning domains. We introduce Guru, a curated RL reasoning corpus of 92K verifiable examples spanning six reasoning domains--Math, Code, Science, Logic, Simulation, and Tabular--each built through domain-specific reward design, deduplication, and filtering to ensure reliability and effectiveness for RL training. Based on Guru, we systematically revisit established findings in RL for LLM reasoning and observe significant variation across domains. For example, while prior work suggests that RL primarily elicits existing knowledge from pretrained models, our results reveal a more nuanced pattern: domains frequently seen during pretraining (Math, Code, Science) easily benefit from cross-domain RL training, while domains with limited pretraining exposure (Logic, Simulation, and Tabular) require in-domain training to achieve meaningful performance gains, suggesting that RL is likely to facilitate genuine skill acquisition. Finally, we present Guru-7B and Guru-32B, two models that achieve state-of-the-art performance among open models RL-trained with publicly available data, outperforming best baselines by 7.9% and 6.7% on our 17-task evaluation suite across six reasoning domains. We also show that our models effectively improve the Pass@k performance of their base models, particularly on complex tasks less likely to appear in pretraining data. We release data, models, training and evaluation code to facilitate general-purpose reasoning at: https://github.com/LLM360/Reasoning360 △ Less

Submitted 17 June, 2025; originally announced June 2025.

Comments: 38 pages, 9 figures. Under review