Showing 1–50 of 3,166 results for author: Chen, C

SRMambaV2: Biomimetic Attention for Sparse Point Cloud Upsampling in Autonomous Driving

Authors: Chuang Chen, Xiaolin Qin, Jing Hu, Wenyi Ge

Abstract: Upsampling LiDAR point clouds in autonomous driving scenarios remains a significant challenge due to the inherent sparsity and complex 3D structures of the data. Recent studies have attempted to address this problem by converting the complex 3D spatial scenes into 2D image super-resolution tasks. However, due to the sparse and blurry feature representation of range images, accurately reconstructin… ▽ More Upsampling LiDAR point clouds in autonomous driving scenarios remains a significant challenge due to the inherent sparsity and complex 3D structures of the data. Recent studies have attempted to address this problem by converting the complex 3D spatial scenes into 2D image super-resolution tasks. However, due to the sparse and blurry feature representation of range images, accurately reconstructing detailed and complex spatial topologies remains a major difficulty. To tackle this, we propose a novel sparse point cloud upsampling method named SRMambaV2, which enhances the upsampling accuracy in long-range sparse regions while preserving the overall geometric reconstruction quality. Specifically, inspired by human driver visual perception, we design a biomimetic 2D selective scanning self-attention (2DSSA) mechanism to model the feature distribution in distant sparse areas. Meanwhile, we introduce a dual-branch network architecture to enhance the representation of sparse features. In addition, we introduce a progressive adaptive loss (PAL) function to further refine the reconstruction of fine-grained details during the upsampling process. Experimental results demonstrate that SRMambaV2 achieves superior performance in both qualitative and quantitative evaluations, highlighting its effectiveness and practical value in automotive sparse point cloud upsampling tasks. △ Less

Submitted 23 July, 2025; originally announced July 2025.

Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance

Authors: Yufei He, Ruoyu Li, Alex Chen, Yue Liu, Yulin Chen, Yuan Sui, Cheng Chen, Yi Zhu, Luca Luo, Frank Yang, Bryan Hooi

Abstract: Large language model (LLM) agents often struggle in environments where rules and required domain knowledge frequently change, such as regulatory compliance and user risk screening. Current approaches, like offline fine-tuning and standard prompting, are insufficient because they cannot effectively adapt to new knowledge during actual operation. To address this limitation, we propose the Adaptive R… ▽ More Large language model (LLM) agents often struggle in environments where rules and required domain knowledge frequently change, such as regulatory compliance and user risk screening. Current approaches, like offline fine-tuning and standard prompting, are insufficient because they cannot effectively adapt to new knowledge during actual operation. To address this limitation, we propose the Adaptive Reflective Interactive Agent (ARIA), an LLM agent framework designed specifically to continuously learn updated domain knowledge at test time. ARIA assesses its own uncertainty through structured self-dialogue, proactively identifying knowledge gaps and requesting targeted explanations or corrections from human experts. It then systematically updates an internal, timestamped knowledge repository with provided human guidance, detecting and resolving conflicting or outdated knowledge through comparisons and clarification queries. We evaluate ARIA on the realistic customer due diligence name screening task on TikTok Pay, alongside publicly available dynamic knowledge tasks. Results demonstrate significant improvements in adaptability and accuracy compared to baselines using standard offline fine-tuning and existing self-improving agents. ARIA is deployed within TikTok Pay serving over 150 million monthly active users, confirming its practicality and effectiveness for operational use in rapidly evolving environments. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Experience is the Best Teacher: Grounding VLMs for Robotics through Self-Generated Memory

Authors: Guowei Lan, Kaixian Qu, René Zurbrügg, Changan Chen, Christopher E. Mower, Haitham Bou-Ammar, Marco Hutter

Abstract: Vision-language models (VLMs) have been widely adopted in robotics to enable autonomous planning. However, grounding VLMs, originally trained on internet data, to diverse real-world robots remains a challenge. This paper presents ExpTeach, a framework that grounds VLMs to physical robots by building a self-generated memory of real-world experiences. In ExpTeach, the VLM autonomously plans actions,… ▽ More Vision-language models (VLMs) have been widely adopted in robotics to enable autonomous planning. However, grounding VLMs, originally trained on internet data, to diverse real-world robots remains a challenge. This paper presents ExpTeach, a framework that grounds VLMs to physical robots by building a self-generated memory of real-world experiences. In ExpTeach, the VLM autonomously plans actions, verifies outcomes, reflects on failures, and adapts robot behaviors in a closed loop. The self-generated experiences during this process are then summarized into a long-term memory, enabling retrieval of learned knowledge to guide future tasks via retrieval-augmented generation (RAG). Additionally, ExpTeach enhances the spatial understanding of VLMs with an on-demand image annotation module. In experiments, we show that reflection improves success rates from 36% to 84% on four challenging robotic tasks and observe the emergence of intelligent object interactions, including creative tool use. Across extensive tests on 12 real-world scenarios (including eight unseen ones), we find that grounding with long-term memory boosts single-trial success rates from 22% to 80%, demonstrating the effectiveness and generalizability of ExpTeach. △ Less

Submitted 22 July, 2025; originally announced July 2025.

FollowUpBot: An LLM-Based Conversational Robot for Automatic Postoperative Follow-up

Authors: Chen Chen, Jianing Yin, Jiannong Cao, Zhiyuan Wen, Mingjin Zhang, Weixun Gao, Xiang Wang, Haihua Shu

Abstract: Postoperative follow-up plays a crucial role in monitoring recovery and identifying complications. However, traditional approaches, typically involving bedside interviews and manual documentation, are time-consuming and labor-intensive. Although existing digital solutions, such as web questionnaires and intelligent automated calls, can alleviate the workload of nurses to a certain extent, they eit… ▽ More Postoperative follow-up plays a crucial role in monitoring recovery and identifying complications. However, traditional approaches, typically involving bedside interviews and manual documentation, are time-consuming and labor-intensive. Although existing digital solutions, such as web questionnaires and intelligent automated calls, can alleviate the workload of nurses to a certain extent, they either deliver an inflexible scripted interaction or face private information leakage issues. To address these limitations, this paper introduces FollowUpBot, an LLM-powered edge-deployed robot for postoperative care and monitoring. It allows dynamic planning of optimal routes and uses edge-deployed LLMs to conduct adaptive and face-to-face conversations with patients through multiple interaction modes, ensuring data privacy. Moreover, FollowUpBot is capable of automatically generating structured postoperative follow-up reports for healthcare institutions by analyzing patient interactions during follow-up. Experimental results demonstrate that our robot achieves high coverage and satisfaction in follow-up interactions, as well as high report generation accuracy across diverse field types. The demonstration video is available at https://www.youtube.com/watch?v=_uFgDO7NoK0. △ Less

Submitted 21 July, 2025; originally announced July 2025.

A Steel Surface Defect Detection Method Based on Lightweight Convolution Optimization

Authors: Cong Chen, Ming Chen, Hoileong Lee, Yan Li, Jiyang Yu

Abstract: Surface defect detection of steel, especially the recognition of multi-scale defects, has always been a major challenge in industrial manufacturing. Steel surfaces not only have defects of various sizes and shapes, which limit the accuracy of traditional image processing and detection methods in complex environments. However, traditional defect detection methods face issues of insufficient accurac… ▽ More Surface defect detection of steel, especially the recognition of multi-scale defects, has always been a major challenge in industrial manufacturing. Steel surfaces not only have defects of various sizes and shapes, which limit the accuracy of traditional image processing and detection methods in complex environments. However, traditional defect detection methods face issues of insufficient accuracy and high miss-detection rates when dealing with small target defects. To address this issue, this study proposes a detection framework based on deep learning, specifically YOLOv9s, combined with the C3Ghost module, SCConv module, and CARAFE upsampling operator, to improve detection accuracy and model performance. First, the SCConv module is used to reduce feature redundancy and optimize feature representation by reconstructing the spatial and channel dimensions. Second, the C3Ghost module is introduced to enhance the model's feature extraction ability by reducing redundant computations and parameter volume, thereby improving model efficiency. Finally, the CARAFE upsampling operator, which can more finely reorganize feature maps in a content-aware manner, optimizes the upsampling process and ensures detailed restoration of high-resolution defect regions. Experimental results demonstrate that the proposed model achieves higher accuracy and robustness in steel surface defect detection tasks compared to other methods, effectively addressing defect detection problems. △ Less

Submitted 21 July, 2025; originally announced July 2025.

Journal ref: International Journal of Advanced Computer Science and Applications (IJACSA), 16(6), 2025

EEG-based Epileptic Prediction via a Two-stage Channel-aware Set Transformer Network

Authors: Ruifeng Zheng, Cong Chen, Shuang Wang, Yiming Liu, Lin You, Jindong Lu, Ruizhe Zhu, Guodao Zhang, Kejie Huang

Abstract: Epilepsy is a chronic, noncommunicable brain disorder, and sudden seizure onsets can significantly impact patients' quality of life and health. However, wearable seizure-predicting devices are still limited, partly due to the bulky size of EEG-collecting devices. To relieve the problem, we proposed a novel two-stage channel-aware Set Transformer Network that could perform seizure prediction with f… ▽ More Epilepsy is a chronic, noncommunicable brain disorder, and sudden seizure onsets can significantly impact patients' quality of life and health. However, wearable seizure-predicting devices are still limited, partly due to the bulky size of EEG-collecting devices. To relieve the problem, we proposed a novel two-stage channel-aware Set Transformer Network that could perform seizure prediction with fewer EEG channel sensors. We also tested a seizure-independent division method which could prevent the adjacency of training and test data. Experiments were performed on the CHB-MIT dataset which includes 22 patients with 88 merged seizures. The mean sensitivity before channel selection was 76.4% with a false predicting rate (FPR) of 0.09/hour. After channel selection, dominant channels emerged in 20 out of 22 patients; the average number of channels was reduced to 2.8 from 18; and the mean sensitivity rose to 80.1% with an FPR of 0.11/hour. Furthermore, experimental results on the seizure-independent division supported our assertion that a more rigorous seizure-independent division should be used for patients with abundant EEG recordings. △ Less

Submitted 21 July, 2025; originally announced July 2025.

Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective

Authors: Yiming Xu, Zhen Peng, Bin Shi, Xu Hua, Bo Dong, Song Wang, Chen Chen

Abstract: The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-based models tend to excessively prioritize overall detection performance while neglecting robustness to structural imbalance, which can be problematic for many real-world networks following power-law degree distributions. P… ▽ More The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-based models tend to excessively prioritize overall detection performance while neglecting robustness to structural imbalance, which can be problematic for many real-world networks following power-law degree distributions. Particularly, GCL-based methods may fail to capture tail anomalies (abnormal nodes with low degrees). This raises concerns about the security and robustness of current anomaly detection algorithms and therefore hinders their applicability in a variety of realistic high-risk scenarios. To the best of our knowledge, research on the robustness of graph anomaly detection to structural imbalance has received little scrutiny. To address the above issues, this paper presents a novel GCL-based framework named AD-GCL. It devises the neighbor pruning strategy to filter noisy edges for head nodes and facilitate the detection of genuine tail nodes by aligning from head nodes to forged tail nodes. Moreover, AD-GCL actively explores potential neighbors to enlarge the receptive field of tail nodes through anomaly-guided neighbor completion. We further introduce intra- and inter-view consistency loss of the original and augmentation graph for enhanced representation. The performance evaluation of the whole, head, and tail nodes on multiple datasets validates the comprehensive superiority of the proposed AD-GCL in detecting both head anomalies and tail anomalies. △ Less

Submitted 19 July, 2025; originally announced July 2025.

Comments: Accepted by AAAI2025

Efficient Whole Slide Pathology VQA via Token Compression

Authors: Weimin Lyu, Qingqiao Hu, Kehan Qi, Zhan Shi, Wentao Huang, Saumya Gupta, Chao Chen

Abstract: Whole-slide images (WSIs) in pathology can reach up to 10,000 x 10,000 pixels, posing significant challenges for multimodal large language model (MLLM) due to long context length and high computational demands. Previous methods typically focus on patch-level analysis or slide-level classification using CLIP-based models with multi-instance learning, but they lack the generative capabilities needed… ▽ More Whole-slide images (WSIs) in pathology can reach up to 10,000 x 10,000 pixels, posing significant challenges for multimodal large language model (MLLM) due to long context length and high computational demands. Previous methods typically focus on patch-level analysis or slide-level classification using CLIP-based models with multi-instance learning, but they lack the generative capabilities needed for visual question answering (VQA). More recent MLLM-based approaches address VQA by feeding thousands of patch tokens directly into the language model, which leads to excessive resource consumption. To address these limitations, we propose Token Compression Pathology LLaVA (TCP-LLaVA), the first MLLM architecture to perform WSI VQA via token compression. TCP-LLaVA introduces a set of trainable compression tokens that aggregate visual and textual information through a modality compression module, inspired by the [CLS] token mechanism in BERT. Only the compressed tokens are forwarded to the LLM for answer generation, significantly reducing input length and computational cost. Experiments on ten TCGA tumor subtypes show that TCP-LLaVA outperforms existing MLLM baselines in VQA accuracy while reducing training resource consumption by a substantial margin. △ Less

Submitted 19 July, 2025; originally announced July 2025.

Learning Stochastic Hamiltonian Systems via Stochastic Generating Function Neural Network

Authors: Chen Chen, Lijin Wang, Yanzhao Cao, Xupeng Cheng

Abstract: In this paper we propose a novel neural network model for learning stochastic Hamiltonian systems (SHSs) from observational data, termed the stochastic generating function neural network (SGFNN). SGFNN preserves symplectic structure of the underlying stochastic Hamiltonian system and produces symplectic predictions. Our model utilizes the autoencoder framework to identify the randomness of the lat… ▽ More In this paper we propose a novel neural network model for learning stochastic Hamiltonian systems (SHSs) from observational data, termed the stochastic generating function neural network (SGFNN). SGFNN preserves symplectic structure of the underlying stochastic Hamiltonian system and produces symplectic predictions. Our model utilizes the autoencoder framework to identify the randomness of the latent system by the encoder network, and detects the stochastic generating function of the system through the decoder network based on the random variables extracted from the encoder. Symplectic predictions can then be generated by the stochastic generating function. Numerical experiments are performed on several stochastic Hamiltonian systems, varying from additive to multiplicative, and from separable to non-separable SHSs with single or multiple noises. Compared with the benchmark stochastic flow map learning (sFML) neural network, our SGFNN model exhibits higher accuracy across various prediction metrics, especially in long-term predictions, with the property of maintaining the symplectic structure of the underlying SHSs. △ Less

Submitted 18 July, 2025; originally announced July 2025.

X-Intelligence 3.0: Training and Evaluating Reasoning LLM for Semiconductor Display

Authors: Xiaolin Yan, Yangxing Liu, Jiazhang Zheng, Chi Liu, Mingyu Du, Caisheng Chen, Haoyang Liu, Ming Ding, Yuan Li, Qiuping Liao, Linfeng Li, Zhili Mei, Siyu Wan, Li Li, Ruyi Zhong, Jiangling Yu, Xule Liu, Huihui Hu, Jiameng Yue, Ruohui Cheng, Qi Yang, Liangqing Wu, Ke Zhu, Chi Zhang, Chufei Jing , et al. (31 additional authors not shown)

Abstract: Large language models (LLMs) have recently achieved significant advances in reasoning and demonstrated their advantages in solving challenging problems. Yet, their effectiveness in the semiconductor display industry remains limited due to a lack of domain-specific training and expertise. To bridge this gap, we present X-Intelligence 3.0, the first high-performance reasoning model specifically deve… ▽ More Large language models (LLMs) have recently achieved significant advances in reasoning and demonstrated their advantages in solving challenging problems. Yet, their effectiveness in the semiconductor display industry remains limited due to a lack of domain-specific training and expertise. To bridge this gap, we present X-Intelligence 3.0, the first high-performance reasoning model specifically developed for the semiconductor display industry. This model is designed to deliver expert-level understanding and reasoning for the industry's complex challenges. Leveraging a carefully curated industry knowledge base, the model undergoes supervised fine-tuning and reinforcement learning to enhance its reasoning and comprehension capabilities. To further accelerate development, we implemented an automated evaluation framework that simulates expert-level assessments. We also integrated a domain-specific retrieval-augmented generation (RAG) mechanism, resulting in notable performance gains on benchmark datasets. Despite its relatively compact size of 32 billion parameters, X-Intelligence 3.0 outperforms SOTA DeepSeek-R1-671B across multiple evaluations. This demonstrates its exceptional efficiency and establishes it as a powerful solution to the longstanding reasoning challenges faced by the semiconductor display industry. △ Less

Submitted 22 July, 2025; v1 submitted 18 July, 2025; originally announced July 2025.

Comments: Technical Report

CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Education

Authors: Jianing Zhao, Peng Gao, Jiannong Cao, Zhiyuan Wen, Chen Chen, Jianing Yin, Ruosong Yang, Bo Yuan

Abstract: Large Language Models (LLMs) have demonstrated considerable potential in improving coding education by providing support for code writing, explanation, and debugging. However, existing LLM-based approaches generally fail to assess students' abilities, design learning plans, provide personalized material aligned with individual learning goals, and enable interactive learning. Current work mostly us… ▽ More Large Language Models (LLMs) have demonstrated considerable potential in improving coding education by providing support for code writing, explanation, and debugging. However, existing LLM-based approaches generally fail to assess students' abilities, design learning plans, provide personalized material aligned with individual learning goals, and enable interactive learning. Current work mostly uses single LLM agents, which limits their ability to understand complex code repositories and schedule step-by-step tutoring. Recent research has shown that multi-agent LLMs can collaborate to solve complicated problems in various domains like software engineering, but their potential in the field of education remains unexplored. In this work, we introduce CodeEdu, an innovative multi-agent collaborative platform that combines LLMs with tool use to provide proactive and personalized education in coding. Unlike static pipelines, CodeEdu dynamically allocates agents and tasks to meet student needs. Various agents in CodeEdu undertake certain functions specifically, including task planning, personalized material generation, real-time QA, step-by-step tutoring, code execution, debugging, and learning report generation, facilitated with extensive external tools to improve task efficiency. Automated evaluations reveal that CodeEdu substantially enhances students' coding performance. △ Less

Submitted 18 July, 2025; originally announced July 2025.

Comments: 4 pages, 4 figures. Demo video available at: https://youtu.be/9iIVmTT4CVk

Apple Intelligence Foundation Language Models: Tech Report 2025

Authors: Hanzhi Zhou, Erik Hornberger, Pengsheng Guo, Xiyou Zhou, Saiwen Wang, Xin Wang, Yifei He, Xuankai Chang, Rene Rauch, Louis D'hauwe, John Peebles, Alec Doane, Kohen Chia, Jenna Thibodeau, Zi-Yi Dou, Yuanyang Zhang, Ruoming Pang, Reed Li, Zhifeng Chen, Jeremy Warner, Zhaoyang Xu, Sophy Lee, David Mizrahi, Ramsey Tantawi, Chris Chaney , et al. (370 additional authors not shown)

Abstract: We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transform… ▽ More We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transformer that combines track parallelism, mixture-of-experts sparse computation, and interleaved global-local attention to deliver high quality with competitive cost on Apple's Private Cloud Compute platform. Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling, licensed corpora, and high-quality synthetic data, then further refined with supervised fine-tuning and reinforcement learning on a new asynchronous platform. The resulting models support several additional languages while understanding images and executing tool calls. In public benchmarks and human evaluations, both the server model and the on-device model match or surpass comparably sized open baselines. A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning, allowing developers to integrate these capabilities with a few lines of code. The latest advancements in Apple Intelligence models are grounded in our Responsible AI approach with safeguards like content filtering and locale-specific evaluation, as well as our commitment to protecting our users' privacy with innovations like Private Cloud Compute. △ Less

Submitted 17 July, 2025; originally announced July 2025.

Camera-based implicit mind reading by capturing higher-order semantic dynamics of human gaze within environmental context

Authors: Mengke Song, Yuge Xie, Qi Cui, Luming Li, Xinyu Liu, Guotao Wang, Chenglizhao Chen, Shanchen Pang

Abstract: Emotion recognition,as a step toward mind reading,seeks to infer internal states from external cues.Most existing methods rely on explicit signals-such as facial expressions,speech,or gestures-that reflect only bodily responses and overlook the influence of environmental context.These cues are often voluntary,easy to mask,and insufficient for capturing deeper,implicit emotions. Physiological signa… ▽ More Emotion recognition,as a step toward mind reading,seeks to infer internal states from external cues.Most existing methods rely on explicit signals-such as facial expressions,speech,or gestures-that reflect only bodily responses and overlook the influence of environmental context.These cues are often voluntary,easy to mask,and insufficient for capturing deeper,implicit emotions. Physiological signal-based approaches offer more direct access to internal states but require complex sensors that compromise natural behavior and limit scalability.Gaze-based methods typically rely on static fixation analysis and fail to capture the rich,dynamic interactions between gaze and the environment,and thus cannot uncover the deep connection between emotion and implicit behavior.To address these limitations,we propose a novel camera-based,user-unaware emotion recognition approach that integrates gaze fixation patterns with environmental semantics and temporal dynamics.Leveraging standard HD cameras,our method unobtrusively captures users'eye appearance and head movements in natural settings-without the need for specialized hardware or active user participation.From these visual cues,the system estimates gaze trajectories over time and space, providing the basis for modeling the spatial, semantic,and temporal dimensions of gaze behavior. This allows us to capture the dynamic interplay between visual attention and the surrounding environment,revealing that emotions are not merely physiological responses but complex outcomes of human-environment interactions.The proposed approach enables user-unaware,real-time,and continuous emotion recognition,offering high generalizability and low deployment cost. △ Less

Submitted 17 July, 2025; originally announced July 2025.

Interactive Hybrid Rice Breeding with Parametric Dual Projection

Authors: Changjian Chen, Pengcheng Wang, Fei Lyu, Zhuo Tang, Li Yang, Long Wang, Yong Cai, Feng Yu, Kenli Li

Abstract: Hybrid rice breeding crossbreeds different rice lines and cultivates the resulting hybrids in fields to select those with desirable agronomic traits, such as higher yields. Recently, genomic selection has emerged as an efficient way for hybrid rice breeding. It predicts the traits of hybrids based on their genes, which helps exclude many undesired hybrids, largely reducing the workload of field cu… ▽ More Hybrid rice breeding crossbreeds different rice lines and cultivates the resulting hybrids in fields to select those with desirable agronomic traits, such as higher yields. Recently, genomic selection has emerged as an efficient way for hybrid rice breeding. It predicts the traits of hybrids based on their genes, which helps exclude many undesired hybrids, largely reducing the workload of field cultivation. However, due to the limited accuracy of genomic prediction models, breeders still need to combine their experience with the models to identify regulatory genes that control traits and select hybrids, which remains a time-consuming process. To ease this process, in this paper, we proposed a visual analysis method to facilitate interactive hybrid rice breeding. Regulatory gene identification and hybrid selection naturally ensemble a dual-analysis task. Therefore, we developed a parametric dual projection method with theoretical guarantees to facilitate interactive dual analysis. Based on this dual projection method, we further developed a gene visualization and a hybrid visualization to verify the identified regulatory genes and hybrids. The effectiveness of our method is demonstrated through the quantitative evaluation of the parametric dual projection method, identified regulatory genes and desired hybrids in the case study, and positive feedback from breeders. △ Less

Submitted 15 July, 2025; originally announced July 2025.

Reprogramming Vision Foundation Models for Spatio-Temporal Forecasting

Authors: Changlu Chen, Yanbin Liu, Chaoxi Niu, Ling Chen, Tianqing Zhu

Abstract: Foundation models have achieved remarkable success in natural language processing and computer vision, demonstrating strong capabilities in modeling complex patterns. While recent efforts have explored adapting large language models (LLMs) for time-series forecasting, LLMs primarily capture one-dimensional sequential dependencies and struggle to model the richer spatio-temporal (ST) correlations e… ▽ More Foundation models have achieved remarkable success in natural language processing and computer vision, demonstrating strong capabilities in modeling complex patterns. While recent efforts have explored adapting large language models (LLMs) for time-series forecasting, LLMs primarily capture one-dimensional sequential dependencies and struggle to model the richer spatio-temporal (ST) correlations essential for accurate ST forecasting. In this paper, we present \textbf{ST-VFM}, a novel framework that systematically reprograms Vision Foundation Models (VFMs) for general-purpose spatio-temporal forecasting. While VFMs offer powerful spatial priors, two key challenges arise when applying them to ST tasks: (1) the lack of inherent temporal modeling capacity and (2) the modality gap between visual and ST data. To address these, ST-VFM adopts a \emph{dual-branch architecture} that integrates raw ST inputs with auxiliary ST flow inputs, where the flow encodes lightweight temporal difference signals interpretable as dynamic spatial cues. To effectively process these dual-branch inputs, ST-VFM introduces two dedicated reprogramming stages. The \emph{pre-VFM reprogramming} stage applies a Temporal-Aware Token Adapter to embed temporal context and align both branches into VFM-compatible feature spaces. The \emph{post-VFM reprogramming} stage introduces a Bilateral Cross-Prompt Coordination module, enabling dynamic interaction between branches through prompt-based conditioning, thus enriching joint representation learning without modifying the frozen VFM backbone. Extensive experiments on ten spatio-temporal datasets show that ST-VFM outperforms state-of-the-art baselines, demonstrating effectiveness and robustness across VFM backbones (e.g., DINO, CLIP, DEIT) and ablation studies, establishing it as a strong general framework for spatio-temporal forecasting. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Latent Space Consistency for Sparse-View CT Reconstruction

Authors: Duoyou Chen, Yunqing Chen, Can Zhang, Zhou Wang, Cheng Chen, Ruoxiu Xiao

Abstract: Computed Tomography (CT) is a widely utilized imaging modality in clinical settings. Using densely acquired rotational X-ray arrays, CT can capture 3D spatial features. However, it is confronted with challenged such as significant time consumption and high radiation exposure. CT reconstruction methods based on sparse-view X-ray images have garnered substantial attention from researchers as they pr… ▽ More Computed Tomography (CT) is a widely utilized imaging modality in clinical settings. Using densely acquired rotational X-ray arrays, CT can capture 3D spatial features. However, it is confronted with challenged such as significant time consumption and high radiation exposure. CT reconstruction methods based on sparse-view X-ray images have garnered substantial attention from researchers as they present a means to mitigate costs and risks. In recent years, diffusion models, particularly the Latent Diffusion Model (LDM), have demonstrated promising potential in the domain of 3D CT reconstruction. Nonetheless, due to the substantial differences between the 2D latent representation of X-ray modalities and the 3D latent representation of CT modalities, the vanilla LDM is incapable of achieving effective alignment within the latent space. To address this issue, we propose the Consistent Latent Space Diffusion Model (CLS-DM), which incorporates cross-modal feature contrastive learning to efficiently extract latent 3D information from 2D X-ray images and achieve latent space alignment between modalities. Experimental results indicate that CLS-DM outperforms classical and state-of-the-art generative models in terms of standard voxel-level metrics (PSNR, SSIM) on the LIDC-IDRI and CTSpine1K datasets. This methodology not only aids in enhancing the effectiveness and economic viability of sparse X-ray reconstructed CT but can also be generalized to other cross-modal transformation tasks, such as text-to-image synthesis. We have made our code publicly available at https://anonymous.4open.science/r/CLS-DM-50D6/ to facilitate further research and applications in other domains. △ Less

Submitted 15 July, 2025; originally announced July 2025.

Comments: ACMMM2025 Accepted

Enhance Stability of Network by Edge Anchor

Authors: Hongbo Qiu, Renjie Sun, Chen chen, Xiaoyang Wang

Abstract: With the rapid growth of online social networks, strengthening their stability has emerged as a key research focus. This study aims to identify influential relationships that significantly impact community stability. In this paper, we introduce and explore the anchor trussness reinforcement problem to reinforce the overall user engagement of networks by anchoring some edges. Specifically, for a gi… ▽ More With the rapid growth of online social networks, strengthening their stability has emerged as a key research focus. This study aims to identify influential relationships that significantly impact community stability. In this paper, we introduce and explore the anchor trussness reinforcement problem to reinforce the overall user engagement of networks by anchoring some edges. Specifically, for a given graph $G$ and a budget $b$, we aim to identify $b$ edges whose anchoring maximizes the trussness gain, which is the cumulative increment of trussness across all edges in $G$. We establish the NP-hardness of the problem. To address this problem, we introduce a greedy framework that iteratively selects the current best edge. To scale for larger networks, we first propose an upward-route method to constrain potential trussness increment edges. Augmented with a support check strategy, this approach enables the efficient computation of the trussness gain for anchoring one edge. Then, we design a classification tree structure to minimize redundant computations in each iteration by organizing edges based on their trussness. We conduct extensive experiments on 8 real-world networks to validate the efficiency and effectiveness of the proposed model and methods. △ Less

Submitted 15 July, 2025; originally announced July 2025.

Joint angle model based learning to refine kinematic human pose estimation

Authors: Chang Peng, Yifei Zhou, Huifeng Xi, Shiqing Huang, Chuangye Chen, Jianming Yang, Bao Yang, Zhenyu Jiang

Abstract: Marker-free human pose estimation (HPE) has found increasing applications in various fields. Current HPE suffers from occasional errors in keypoint recognition and random fluctuation in keypoint trajectories when analyzing kinematic human poses. The performance of existing deep learning-based models for HPE refinement is considerably limited by inaccurate training datasets in which the keypoints a… ▽ More Marker-free human pose estimation (HPE) has found increasing applications in various fields. Current HPE suffers from occasional errors in keypoint recognition and random fluctuation in keypoint trajectories when analyzing kinematic human poses. The performance of existing deep learning-based models for HPE refinement is considerably limited by inaccurate training datasets in which the keypoints are manually annotated. This paper proposed a novel method to overcome the difficulty through joint angle-based modeling. The key techniques include: (i) A joint angle-based model of human pose, which is robust to describe kinematic human poses; (ii) Approximating temporal variation of joint angles through high order Fourier series to get reliable "ground truth"; (iii) A bidirectional recurrent network is designed as a post-processing module to refine the estimation of well-established HRNet. Trained with the high-quality dataset constructed using our method, the network demonstrates outstanding performance to correct wrongly recognized joints and smooth their spatiotemporal trajectories. Tests show that joint angle-based refinement (JAR) outperforms the state-of-the-art HPE refinement network in challenging cases like figure skating and breaking. △ Less

Submitted 15 July, 2025; originally announced July 2025.

ACM Class: I.4.9; I.5.4; J.3

Arcturus: A Cloud Overlay Network for Global Accelerator with Enhanced Performance and Stability

Authors: Matthew Yang Liu, Chuang Chen, Pengcheng Lv, Hui Guo, Yanan Zhang, Cong Wang, Yusen Li, Zhenyu Li, Yu-Chu Tian

Abstract: Global Accelerator (GA) services play a vital role in ensuring low-latency, high-reliability communication for real-time interactive applications. However, existing GA offerings are tightly bound to specific cloud providers, resulting in high costs, rigid deployment, and limited flexibility, especially for large-scale or budget-sensitive deployments. Arcturus is a cloud-native GA framework that re… ▽ More Global Accelerator (GA) services play a vital role in ensuring low-latency, high-reliability communication for real-time interactive applications. However, existing GA offerings are tightly bound to specific cloud providers, resulting in high costs, rigid deployment, and limited flexibility, especially for large-scale or budget-sensitive deployments. Arcturus is a cloud-native GA framework that revisits the design of GA systems by leveraging low-cost, heterogeneous cloud resources across multiple providers. Rather than relying on fixed, high-end infrastructure, Arcturus dynamically constructs its acceleration network and balances performance, stability, and resource efficiency. To achieve this, Arcturus introduces a two-plane design: a forwarding plane that builds a proxy network with adaptive control, and a scheduling plane that coordinates load and routing through lightweight, quantitative optimization. Evaluations under millions of RPS show that Arcturus outperforms commercial GA services by up to 1.7X in acceleration performance, reduces cost by 71%, and maintains over 80% resource efficiency--demonstrating efficient use of cloud resources at scale. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Efficient Temporal Simple Path Graph Generation

Authors: Zhiyang Tang, Yanping Wu, Xiangjun Zai, Chen Chen, Xiaoyang Wang, Ying Zhang

Abstract: Interactions between two entities often occur at specific timestamps, which can be modeled as a temporal graph. Exploring the relationships between vertices based on temporal paths is one of the fundamental tasks. In this paper, we conduct the first research to propose and investigate the problem of generating the temporal simple path graph (tspG), which is the subgraph consisting of all temporal… ▽ More Interactions between two entities often occur at specific timestamps, which can be modeled as a temporal graph. Exploring the relationships between vertices based on temporal paths is one of the fundamental tasks. In this paper, we conduct the first research to propose and investigate the problem of generating the temporal simple path graph (tspG), which is the subgraph consisting of all temporal simple paths from the source vertex to the target vertex within the given time interval. Directly enumerating all temporal simple paths and constructing the tspG is computationally expensive. To accelerate the processing, we propose an efficient method named Verification in Upper-bound Graph. It first incorporates the temporal path constraint and simple path constraint to exclude unpromising edges from the original graph, which obtains a tight upper-bound graph as a high-quality approximation of the tspG in polynomial time. Then, an Escape Edges Verification algorithm is further applied in the upper-bound graph to construct the exact tspG without exhaustively enumerating all temporal simple paths between given vertices. Finally, comprehensive experiments on 10 real-world graphs are conducted to demonstrate the efficiency and effectiveness of the proposed techniques. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Interactive Drawing Guidance for Anime Illustrations with Diffusion Model

Authors: Chuang Chen, Xiaoxuan Xie, Yongming Zhang, Tianyu Zhang, Haoran Xie

Abstract: Creating high-quality anime illustrations presents notable challenges, particularly for beginners, due to the intricate styles and fine details inherent in anime art. We present an interactive drawing guidance system specifically designed for anime illustrations to address this issue. It offers real-time guidance to help users refine their work and streamline the creative process. Our system is bu… ▽ More Creating high-quality anime illustrations presents notable challenges, particularly for beginners, due to the intricate styles and fine details inherent in anime art. We present an interactive drawing guidance system specifically designed for anime illustrations to address this issue. It offers real-time guidance to help users refine their work and streamline the creative process. Our system is built upon the StreamDiffusion pipeline to deliver real-time drawing assistance. We fine-tune Stable Diffusion with LoRA to synthesize anime style RGB images from user-provided hand-drawn sketches and prompts. Leveraging the Informative Drawings model, we transform these RGB images into rough sketches, which are further refined into structured guidance sketches using a custom-designed optimizer. The proposed system offers precise, real-time guidance aligned with the creative intent of the user, significantly enhancing both the efficiency and accuracy of the drawing process. To assess the effectiveness of our approach, we conducted a user study, gathering empirical feedback on both system performance and interface usability. △ Less

Submitted 12 July, 2025; originally announced July 2025.

Comments: 9 pages, 7 figures. In proceedings of NICOGRAPH International 2025

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference

Authors: Chun-Ting Chen, HanGyeol Mun, Jian Meng, Mohamed S. Abdelfattah, Jae-sun Seo

Abstract: Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during the memory-bound decode stage, while maintaining high energy efficiency during the compute intensive prefill stage. This paper proposes an edge LLM inference acce… ▽ More Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during the memory-bound decode stage, while maintaining high energy efficiency during the compute intensive prefill stage. This paper proposes an edge LLM inference accelerator featuring a hybrid systolic array (HSA) architecture that optimizes inference efficiency in both stages. To further reduce EMA, we adopt MXINT4 weight quantization and propose an optimized dataflow tailored for HSA, ensuring negligible dequantization overhead and achieving 100% hardware utilization with minimal accuracy loss under edge DRAM bandwidth constraints. For non-linear operations, we incorporate optimized root mean square normalization (RMSNorm) and rotary position embedding (RoPE) units, reducing their latency, area, and memory access overhead while enabling end-to-end inference on our accelerator. Our solution achieves 247/117 (token/s/mm2) while running a 1.3B LLM on long-input/long-output scenarios, providing >2.45x/13.5x improvement over existing approaches, while maintaining superior energy efficiency in token generation. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Comments: Accepted as a conference paper at the 2025 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)

Multimodal Cardiovascular Risk Profiling Using Self-Supervised Learning of Polysomnography

Authors: Zhengxiao He, Huayu Li, Geng Yuan, William D. S. Killgore, Stuart F. Quan, Chen X. Chen, Ao Li

Abstract: Methods: We developed a self-supervised deep learning model that extracts meaningful patterns from multi-modal signals (Electroencephalography (EEG), Electrocardiography (ECG), and respiratory signals). The model was trained on data from 4,398 participants. Projection scores were derived by contrasting embeddings from individuals with and without CVD outcomes. External validation was conducted in… ▽ More Methods: We developed a self-supervised deep learning model that extracts meaningful patterns from multi-modal signals (Electroencephalography (EEG), Electrocardiography (ECG), and respiratory signals). The model was trained on data from 4,398 participants. Projection scores were derived by contrasting embeddings from individuals with and without CVD outcomes. External validation was conducted in an independent cohort with 1,093 participants. The source code is available on https://github.com/miraclehetech/sleep-ssl. Results: The projection scores revealed distinct and clinically meaningful patterns across modalities. ECG-derived features were predictive of both prevalent and incident cardiac conditions, particularly CVD mortality. EEG-derived features were predictive of incident hypertension and CVD mortality. Respiratory signals added complementary predictive value. Combining these projection scores with the Framingham Risk Score consistently improved predictive performance, achieving area under the curve values ranging from 0.607 to 0.965 across different outcomes. Findings were robustly replicated and validated in the external testing cohort. Conclusion: Our findings demonstrate that the proposed framework can generate individualized CVD risk scores directly from PSG data. The resulting projection scores have the potential to be integrated into clinical practice, enhancing risk assessment and supporting personalized care. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees

Authors: Chuyan Chen, Yutong He, Pengrui Li, Weichen Jia, Kun Yuan

Abstract: Distributed optimization is pivotal for large-scale signal processing and machine learning, yet communication overhead remains a major bottleneck. Low-rank gradient compression, in which the transmitted gradients are approximated by low-rank matrices to reduce communication, offers a promising remedy. Existing methods typically adopt either randomized or greedy compression strategies: randomized a… ▽ More Distributed optimization is pivotal for large-scale signal processing and machine learning, yet communication overhead remains a major bottleneck. Low-rank gradient compression, in which the transmitted gradients are approximated by low-rank matrices to reduce communication, offers a promising remedy. Existing methods typically adopt either randomized or greedy compression strategies: randomized approaches project gradients onto randomly chosen subspaces, introducing high variance and degrading empirical performance; greedy methods select the most informative subspaces, achieving strong empirical results but lacking convergence guarantees. To address this gap, we propose GreedyLore--the first Greedy Low-Rank gradient compression algorithm for distributed learning with rigorous convergence guarantees. GreedyLore incorporates error feedback to correct the bias introduced by greedy compression and introduces a semi-lazy subspace update that ensures the compression operator remains contractive throughout all iterations. With these techniques, we prove that GreedyLore achieves a convergence rate of $\mathcal{O}(σ/\sqrt{NT} + 1/T)$ under standard optimizers such as MSGD and Adam--marking the first linear speedup convergence rate for low-rank gradient compression. Extensive experiments are conducted to validate our theoretical findings. △ Less

Submitted 20 July, 2025; v1 submitted 11 July, 2025; originally announced July 2025.

Comments: 18 pages, 5 figures

Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Network

Authors: Chuanqi Chen, Zhongrui Wang, Nan Chen, Jin-Long Wu

Abstract: A discrete-time conditional Gaussian Koopman network (CGKN) is developed in this work to learn surrogate models that can perform efficient state forecast and data assimilation (DA) for high-dimensional complex dynamical systems, e.g., systems governed by nonlinear partial differential equations (PDEs). Focusing on nonlinear partially observed systems that are common in many engineering and earth s… ▽ More A discrete-time conditional Gaussian Koopman network (CGKN) is developed in this work to learn surrogate models that can perform efficient state forecast and data assimilation (DA) for high-dimensional complex dynamical systems, e.g., systems governed by nonlinear partial differential equations (PDEs). Focusing on nonlinear partially observed systems that are common in many engineering and earth science applications, this work exploits Koopman embedding to discover a proper latent representation of the unobserved system states, such that the dynamics of the latent states are conditional linear, i.e., linear with the given observed system states. The modeled system of the observed and latent states then becomes a conditional Gaussian system, for which the posterior distribution of the latent states is Gaussian and can be efficiently evaluated via analytical formulae. The analytical formulae of DA facilitate the incorporation of DA performance into the learning process of the modeled system, which leads to a framework that unifies scientific machine learning (SciML) and data assimilation. The performance of discrete-time CGKN is demonstrated on several canonical problems governed by nonlinear PDEs with intermittency and turbulent features, including the viscous Burgers' equation, the Kuramoto-Sivashinsky equation, and the 2-D Navier-Stokes equations, with which we show that the discrete-time CGKN framework achieves comparable performance as the state-of-the-art SciML methods in state forecast and provides efficient and accurate DA results. The discrete-time CGKN framework also serves as an example to illustrate unifying the development of SciML models and their other outer-loop applications such as design optimization, inverse problems, and optimal control. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation

Authors: Liu He, Xiao Zeng, Yizhi Song, Albert Y. C. Chen, Lu Xia, Shashwat Verma, Sankalp Dayal, Min Sun, Cheng-Hao Kuo, Daniel Aliaga

Abstract: Multimodal Large Language Models (MLLMs) struggle with accurately capturing camera-object relations, especially for object orientation, camera viewpoint, and camera shots. This stems from the fact that existing MLLMs are trained on images with limited diverse camera-object relations and corresponding textual descriptions. To address this, we propose a synthetic generation pipeline to create large-… ▽ More Multimodal Large Language Models (MLLMs) struggle with accurately capturing camera-object relations, especially for object orientation, camera viewpoint, and camera shots. This stems from the fact that existing MLLMs are trained on images with limited diverse camera-object relations and corresponding textual descriptions. To address this, we propose a synthetic generation pipeline to create large-scale 3D visual instruction datasets. Our framework takes 3D assets as input and uses rendering and diffusion-based image generation models to create photorealistic images preserving precise camera-object relations. Additionally, large language models (LLMs) are used to generate text prompts for guiding visual instruction tuning and controlling image generation. We create Ultimate3D, a dataset of 240K VQAs with precise camera-object annotations, and corresponding benchmark. MLLMs fine-tuned on our proposed dataset outperform commercial models by a large margin, achieving an average accuracy improvement of 33.4% on camera-object relation recognition tasks. Our code, dataset, and benchmark will contribute to broad MLLM applications. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation

Authors: Liliang Ren, Congcong Chen, Haoran Xu, Young Jin Kim, Adam Atkinson, Zheng Zhan, Jiankai Sun, Baolin Peng, Liyuan Liu, Shuohang Wang, Hao Cheng, Jianfeng Gao, Weizhu Chen, Yelong Shen

Abstract: Recent advances in language modeling have demonstrated the effectiveness of State Space Models (SSMs) for efficient sequence modeling. While hybrid architectures such as Samba and the decoder-decoder architecture, YOCO, have shown promising performance gains over Transformers, prior works have not investigated the efficiency potential of representation sharing between SSM layers. In this paper, we… ▽ More Recent advances in language modeling have demonstrated the effectiveness of State Space Models (SSMs) for efficient sequence modeling. While hybrid architectures such as Samba and the decoder-decoder architecture, YOCO, have shown promising performance gains over Transformers, prior works have not investigated the efficiency potential of representation sharing between SSM layers. In this paper, we introduce the Gated Memory Unit (GMU), a simple yet effective mechanism for efficient memory sharing across layers. We apply it to create SambaY, a decoder-hybrid-decoder architecture that incorporates GMUs in the cross-decoder to share memory readout states from a Samba-based self-decoder. SambaY significantly enhances decoding efficiency, preserves linear pre-filling time complexity, and boosts long-context performance, all while eliminating the need for explicit positional encoding. Through extensive scaling experiments, we demonstrate that our model exhibits a significantly lower irreducible loss compared to a strong YOCO baseline, indicating superior performance scalability under large-scale compute regimes. Our largest model enhanced with Differential Attention, Phi4-mini-Flash-Reasoning, achieves significantly better performance than Phi4-mini-Reasoning on reasoning tasks such as Math500, AIME24/25, and GPQA Diamond without any reinforcement learning, while delivering up to 10x higher decoding throughput on 2K-length prompts with 32K generation length under the vLLM inference framework. We release our training codebase on open-source data at https://github.com/microsoft/ArchScale. △ Less

Submitted 16 July, 2025; v1 submitted 9 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 Comparative Study and Implementation of Key Derivation Functions Standardized by NIST and IEEE

Authors: Abel C. H. Chen

Abstract: Since many applications and services require pseudorandom numbers (PRNs), it is feasible to generate specific PRNs under given key values and input messages using Key Derivation Functions (KDFs). These KDFs are primarily constructed based on Message Authentication Codes (MACs), where the MAC serves as a core component in the generation of pseudorandom numbers. In light of this, the study first exa… ▽ More Since many applications and services require pseudorandom numbers (PRNs), it is feasible to generate specific PRNs under given key values and input messages using Key Derivation Functions (KDFs). These KDFs are primarily constructed based on Message Authentication Codes (MACs), where the MAC serves as a core component in the generation of pseudorandom numbers. In light of this, the study first examines three MAC algorithms defined by the National Institute of Standards and Technology (NIST): the Keyed-Hash Message Authentication Code (HMAC), the Cipher-based Message Authentication Code (CMAC), and the Keccak-based Message Authentication Code (KMAC). Subsequently, the study explores KDFs based on these MACs, including the Counter Mode KDF, the KMAC-based KDF, and the KDF defined in IEEE 1609.2.1. In experiments, the computation times for generating MACs and the corresponding pseudorandom numbers using each KDF are evaluated. The study further analyzes the advantages, disadvantages, and applicable scenarios for each method. Experimental results indicate that the CMAC and the CMAC-based KDF exhibit the shortest computation times, averaging approximately 0.007 milliseconds and 0.014 milliseconds, respectively. △ Less

Submitted 23 June, 2025; originally announced July 2025.

Comments: in Chinese language

Domain adaptation of large language models for geotechnical applications

Authors: Lei Fan, Fangxue Liu, Cheng Chen

Abstract: Recent developments in large language models (LLMs) are opening up new opportunities in geotechnical engineering and engineering geology. While general-purpose LLMs possess broad capabilities, effective application in geotechnics often requires domain-specific adaptation. Such tailored LLMs are increasingly employed to streamline geotechnical workflows. This paper presents the first survey of the… ▽ More Recent developments in large language models (LLMs) are opening up new opportunities in geotechnical engineering and engineering geology. While general-purpose LLMs possess broad capabilities, effective application in geotechnics often requires domain-specific adaptation. Such tailored LLMs are increasingly employed to streamline geotechnical workflows. This paper presents the first survey of the adaptation and application of LLMs in geotechnical engineering. It outlines key methodologies for adaptation to geotechnical domain, including prompt engineering, retrieval-augmented generation, domain-adaptive pretraining, and fine-tuning. The survey examines the state-of-the-art applications of geotechnical-adapted LLMs, including geological interpretation, subsurface characterization, site planning, design calculations, numerical modeling, safety and risk assessment, and educational tutoring. It also analyzes benefits and limitations of geotechnical-adapted LLMs, and identifies promising directions for future research in this interdisciplinary discipline. The findings serve as a valuable resource for practitioners seeking to integrate LLMs into geotechnical practice, while also providing a foundation to stimulate further investigation within the academic community. △ Less

Submitted 7 July, 2025; originally announced July 2025.

Semi-Supervised Defect Detection via Conditional Diffusion and CLIP-Guided Noise Filtering

Authors: Shuai Li, Shihan Chen, Wanru Geng, Zhaohua Xu, Xiaolu Liu, Can Dong, Zhen Tian, Changlin Chen

Abstract: In the realm of industrial quality inspection, defect detection stands as a critical component, particularly in high-precision, safety-critical sectors such as automotive components aerospace, and medical devices. Traditional methods, reliant on manual inspection or early image processing algorithms, suffer from inefficiencies, high costs, and limited robustness. This paper introduces a semi-super… ▽ More In the realm of industrial quality inspection, defect detection stands as a critical component, particularly in high-precision, safety-critical sectors such as automotive components aerospace, and medical devices. Traditional methods, reliant on manual inspection or early image processing algorithms, suffer from inefficiencies, high costs, and limited robustness. This paper introduces a semi-supervised defect detection framework based on conditional diffusion (DSYM), leveraging a two-stage collaborative training mechanism and a staged joint optimization strategy. The framework utilizes labeled data for initial training and subsequently incorporates unlabeled data through the generation of pseudo-labels. A conditional diffusion model synthesizes multi-scale pseudo-defect samples, while a CLIP cross-modal feature-based noise filtering mechanism mitigates label contamination. Experimental results on the NEU-DET dataset demonstrate a 78.4% mAP@0.5 with the same amount of labeled data as traditional supervised methods, and 75.1% mAP@0.5 with only 40% of the labeled data required by the original supervised model, showcasing significant advantages in data efficiency. This research provides a high-precision, low-labeling-dependent solution for defect detection in industrial quality inspection scenarios. The work of this article has been open-sourced at https://github.com/cLin-c/Semisupervised-DSYM. △ Less

Submitted 7 July, 2025; originally announced July 2025.

NavigScene: Bridging Local Perception and Global Navigation for Beyond-Visual-Range Autonomous Driving

Authors: Qucheng Peng, Chen Bai, Guoxiang Zhang, Bo Xu, Xiaotong Liu, Xiaoyin Zheng, Chen Chen, Cheng Lu

Abstract: Autonomous driving systems have made significant advances in Q&A, perception, prediction, and planning based on local visual information, yet they struggle to incorporate broader navigational context that human drivers routinely utilize. We address this critical gap between local sensor data and global navigation information by proposing NavigScene, an auxiliary navigation-guided natural language… ▽ More Autonomous driving systems have made significant advances in Q&A, perception, prediction, and planning based on local visual information, yet they struggle to incorporate broader navigational context that human drivers routinely utilize. We address this critical gap between local sensor data and global navigation information by proposing NavigScene, an auxiliary navigation-guided natural language dataset that simulates a human-like driving environment within autonomous driving systems. Moreover, we develop three complementary paradigms to leverage NavigScene: (1) Navigation-guided Reasoning, which enhances vision-language models by incorporating navigation context into the prompting approach; (2) Navigation-guided Preference Optimization, a reinforcement learning method that extends Direct Preference Optimization to improve vision-language model responses by establishing preferences for navigation-relevant summarized information; and (3) Navigation-guided Vision-Language-Action model, which integrates navigation guidance and vision-language models with conventional driving models through feature fusion. Extensive experiments demonstrate that our approaches significantly improve performance across perception, prediction, planning, and question-answering tasks by enabling reasoning capabilities beyond visual range and improving generalization to diverse driving scenarios. This work represents a significant step toward more comprehensive autonomous driving systems capable of navigating complex, unfamiliar environments with greater reliability and safety. △ Less

Submitted 7 July, 2025; originally announced July 2025.

Comments: Accepted by ACM Multimedia 2025

Robust Incomplete-Modality Alignment for Ophthalmic Disease Grading and Diagnosis via Labeled Optimal Transport

Authors: Qinkai Yu, Jianyang Xie, Yitian Zhao, Cheng Chen, Lijun Zhang, Liming Chen, Jun Cheng, Lu Liu, Yalin Zheng, Yanda Meng

Abstract: Multimodal ophthalmic imaging-based diagnosis integrates color fundus image with optical coherence tomography (OCT) to provide a comprehensive view of ocular pathologies. However, the uneven global distribution of healthcare resources often results in real-world clinical scenarios encountering incomplete multimodal data, which significantly compromises diagnostic accuracy. Existing commonly used p… ▽ More Multimodal ophthalmic imaging-based diagnosis integrates color fundus image with optical coherence tomography (OCT) to provide a comprehensive view of ocular pathologies. However, the uneven global distribution of healthcare resources often results in real-world clinical scenarios encountering incomplete multimodal data, which significantly compromises diagnostic accuracy. Existing commonly used pipelines, such as modality imputation and distillation methods, face notable limitations: 1)Imputation methods struggle with accurately reconstructing key lesion features, since OCT lesions are localized, while fundus images vary in style. 2)distillation methods rely heavily on fully paired multimodal training data. To address these challenges, we propose a novel multimodal alignment and fusion framework capable of robustly handling missing modalities in the task of ophthalmic diagnostics. By considering the distinctive feature characteristics of OCT and fundus images, we emphasize the alignment of semantic features within the same category and explicitly learn soft matching between modalities, allowing the missing modality to utilize existing modality information, achieving robust cross-modal feature alignment under the missing modality. Specifically, we leverage the Optimal Transport for multi-scale modality feature alignment: class-wise alignment through predicted class prototypes and feature-wise alignment via cross-modal shared feature transport. Furthermore, we propose an asymmetric fusion strategy that effectively exploits the distinct characteristics of OCT and fundus modalities. Extensive evaluations on three large ophthalmic multimodal datasets demonstrate our model's superior performance under various modality-incomplete scenarios, achieving Sota performance in both complete modality and inter-modality incompleteness conditions. Code is available at https://github.com/Qinkaiyu/RIMA △ Less

Submitted 7 July, 2025; originally announced July 2025.

Comments: MICCAI 2025

TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation

Authors: Zonglin Lyu, Chen Chen

Abstract: Video Frame Interpolation (VFI) aims to predict the intermediate frame $I_n$ (we use n to denote time in videos to avoid notation overload with the timestep $t$ in diffusion models) based on two consecutive neighboring frames $I_0$ and $I_1$. Recent approaches apply diffusion models (both image-based and video-based) in this task and achieve strong performance. However, image-based diffusion model… ▽ More Video Frame Interpolation (VFI) aims to predict the intermediate frame $I_n$ (we use n to denote time in videos to avoid notation overload with the timestep $t$ in diffusion models) based on two consecutive neighboring frames $I_0$ and $I_1$. Recent approaches apply diffusion models (both image-based and video-based) in this task and achieve strong performance. However, image-based diffusion models are unable to extract temporal information and are relatively inefficient compared to non-diffusion methods. Video-based diffusion models can extract temporal information, but they are too large in terms of training scale, model size, and inference time. To mitigate the above issues, we propose Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation (TLB-VFI), an efficient video-based diffusion model. By extracting rich temporal information from video inputs through our proposed 3D-wavelet gating and temporal-aware autoencoder, our method achieves 20% improvement in FID on the most challenging datasets over recent SOTA of image-based diffusion models. Meanwhile, due to the existence of rich temporal information, our method achieves strong performance while having 3times fewer parameters. Such a parameter reduction results in 2.3x speed up. By incorporating optical flow guidance, our method requires 9000x less training data and achieves over 20x fewer parameters than video-based diffusion models. Codes and results are available at our project page: https://zonglinl.github.io/tlbvfi_page. △ Less

Submitted 7 July, 2025; originally announced July 2025.

ChipSeek-R1: Generating Human-Surpassing RTL with LLM via Hierarchical Reward-Driven Reinforcement Learning

Authors: Zhirong Chen, Kaiyan Chang, Zhuolin Li, Xinyang He, Chujie Chen, Cangyuan Li, Mengdi Wang, Haobo Xu, Yinhe Han, Ying Wang

Abstract: Large Language Models (LLMs) show significant potential for automating Register-Transfer Level (RTL) code generation. However, current approaches face a critical challenge: they can not simultaneously optimize for functional correctness and hardware quality (Power, Performance, Area - PPA). Methods based on supervised fine-tuning often generate functionally correct but PPA-suboptimal code, lacking… ▽ More Large Language Models (LLMs) show significant potential for automating Register-Transfer Level (RTL) code generation. However, current approaches face a critical challenge: they can not simultaneously optimize for functional correctness and hardware quality (Power, Performance, Area - PPA). Methods based on supervised fine-tuning often generate functionally correct but PPA-suboptimal code, lacking mechanisms to learn optimization principles. In contrast, post-processing techniques that attempt to improve PPA metrics after generation are often inefficient because they operate externally without updating the LLM's parameters, thus failing to enhance the model's intrinsic design capabilities. To bridge this gap, we introduce ChipSeek-R1, a hierarchical reward-driven reinforcement learning framework to train LLMs to generate RTL code that achieves both functional correctness and optimized PPA metrics. ChipSeek-R1 employs a hierarchical reward system, which incorporates direct feedback on syntax, functional correctness (from simulators) and PPA metrics (from synthesis tools) during reinforcement learning. This enables the model to learn complex hardware design trade-offs via trial-and-error, generating RTL code that is both functionally correct and PPA-optimized. Evaluating ChipSeek-R1 on standard benchmarks (VerilogEval, RTLLM), we achieve state-of-the-art results in functional correctness. Notably, on the RTLLM benchmark, ChipSeek-R1 generated 27 RTL designs surpassing the PPA metrics of the original human-written code. Our findings demonstrate the effectiveness of integrating toolchain feedback into LLM training and highlight the potential for reinforcement learning to enable automated generation of human-surpassing RTL code. We open-source our code in anonymous github. △ Less

Submitted 7 July, 2025; originally announced July 2025.

MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalization

Authors: Zhendong Xiao, Wu Wei, Shujie Ji, Shan Yang, Changhao Chen

Abstract: Camera relocalization, a cornerstone capability of modern computer vision, accurately determines a camera's position and orientation (6-DoF) from images and is essential for applications in augmented reality (AR), mixed reality (MR), autonomous driving, delivery drones, and robotic navigation. Unlike traditional deep learning-based methods that regress camera pose from images in a single scene, wh… ▽ More Camera relocalization, a cornerstone capability of modern computer vision, accurately determines a camera's position and orientation (6-DoF) from images and is essential for applications in augmented reality (AR), mixed reality (MR), autonomous driving, delivery drones, and robotic navigation. Unlike traditional deep learning-based methods that regress camera pose from images in a single scene, which often lack generalization and robustness in diverse environments, we propose MVL-Loc, a novel end-to-end multi-scene 6-DoF camera relocalization framework. MVL-Loc leverages pretrained world knowledge from vision-language models (VLMs) and incorporates multimodal data to generalize across both indoor and outdoor settings. Furthermore, natural language is employed as a directive tool to guide the multi-scene learning process, facilitating semantic understanding of complex scenes and capturing spatial relationships among objects. Extensive experiments on the 7Scenes and Cambridge Landmarks datasets demonstrate MVL-Loc's robustness and state-of-the-art performance in real-world multi-scene camera relocalization, with improved accuracy in both positional and orientational estimates. △ Less

Submitted 6 July, 2025; originally announced July 2025.

Comments: PRCV

BiFair: A Fairness-aware Training Framework for LLM-enhanced Recommender Systems via Bi-level Optimization

Authors: Jiaming Zhang, Yuyuan Li, Yiqun Xu, Li Zhang, Xiaohua Feng, Zhifei Ren, Chaochao Chen

Abstract: Large Language Model-enhanced Recommender Systems (LLM-enhanced RSs) have emerged as a powerful approach to improving recommendation quality by leveraging LLMs to generate item representations. Despite these advancements, the integration of LLMs raises severe fairness concerns. Existing studies reveal that LLM-based RSs exhibit greater unfairness than traditional RSs, yet fairness issues in LLM-en… ▽ More Large Language Model-enhanced Recommender Systems (LLM-enhanced RSs) have emerged as a powerful approach to improving recommendation quality by leveraging LLMs to generate item representations. Despite these advancements, the integration of LLMs raises severe fairness concerns. Existing studies reveal that LLM-based RSs exhibit greater unfairness than traditional RSs, yet fairness issues in LLM-enhanced RSs remain largely unexplored. In this paper, our empirical study reveals that while LLM-enhanced RSs improve fairness across item groups, a significant fairness gap persists. Further enhancement remains challenging due to the architectural differences and varying sources of unfairness inherent in LLM-enhanced RSs. To bridge this gap, we first decompose unfairness into i) \textit{prior unfairness} in LLM-generated representations and ii) \textit{training unfairness} in recommendation models. Then, we propose BiFair, a bi-level optimization-based fairness-aware training framework designed to mitigate both prior and training unfairness simultaneously. BiFair optimizes two sets of learnable parameters: LLM-generated representations and a trainable projector in the recommendation model, using a two-level nested optimization process. Additionally, we introduce an adaptive inter-group balancing mechanism, leveraging multi-objective optimization principles to dynamically balance fairness across item groups. Extensive experiments on three real-world datasets demonstrate that BiFair significantly mitigates unfairness and outperforms previous state-of-the-art methods. △ Less

Submitted 6 July, 2025; originally announced July 2025.

VICI: VLM-Instructed Cross-view Image-localisation

Authors: Xiaohan Zhang, Tavis Shore, Chen Chen, Oscar Mendez, Simon Hadfield, Safwan Wshah

Abstract: In this paper, we present a high-performing solution to the UAVM 2025 Challenge, which focuses on matching narrow FOV street-level images to corresponding satellite imagery using the University-1652 dataset. As panoramic Cross-View Geo-Localisation nears peak performance, it becomes increasingly important to explore more practical problem formulations. Real-world scenarios rarely offer panoramic s… ▽ More In this paper, we present a high-performing solution to the UAVM 2025 Challenge, which focuses on matching narrow FOV street-level images to corresponding satellite imagery using the University-1652 dataset. As panoramic Cross-View Geo-Localisation nears peak performance, it becomes increasingly important to explore more practical problem formulations. Real-world scenarios rarely offer panoramic street-level queries; instead, queries typically consist of limited-FOV images captured with unknown camera parameters. Our work prioritises discovering the highest achievable performance under these constraints, pushing the limits of existing architectures. Our method begins by retrieving candidate satellite image embeddings for a given query, followed by a re-ranking stage that selectively enhances retrieval accuracy within the top candidates. This two-stage approach enables more precise matching, even under the significant viewpoint and scale variations inherent in the task. Through experimentation, we demonstrate that our approach achieves competitive results -specifically attaining R@1 and R@10 retrieval rates of \topone\% and \topten\% respectively. This underscores the potential of optimised retrieval and re-ranking strategies in advancing practical geo-localisation performance. Code is available at https://github.com/tavisshore/VICI. △ Less

Submitted 22 July, 2025; v1 submitted 5 July, 2025; originally announced July 2025.

Controlling Thinking Speed in Reasoning Models

Authors: Zhengkai Lin, Zhihang Fu, Ze Chen, Chao Chen, Liang Xie, Wenxiao Wang, Deng Cai, Zheng Wang, Jieping Ye

Abstract: Human cognition is theorized to operate in two modes: fast, intuitive System 1 thinking and slow, deliberate System 2 thinking. While current Large Reasoning Models (LRMs) excel at System 2 thinking, their inability to perform fast thinking leads to high computational overhead and latency. In this work, we enable LRMs to approximate human intelligence through dynamic thinking speed adjustment, opt… ▽ More Human cognition is theorized to operate in two modes: fast, intuitive System 1 thinking and slow, deliberate System 2 thinking. While current Large Reasoning Models (LRMs) excel at System 2 thinking, their inability to perform fast thinking leads to high computational overhead and latency. In this work, we enable LRMs to approximate human intelligence through dynamic thinking speed adjustment, optimizing accuracy-efficiency trade-offs. Our approach addresses two key questions: (1) how to control thinking speed in LRMs, and (2) when to adjust it for optimal performance. For the first question, we identify the steering vector that governs slow-fast thinking transitions in LRMs' representation space. Using this vector, we achieve the first representation editing-based test-time scaling effect, outperforming existing prompt-based scaling methods. For the second question, we apply real-time difficulty estimation to signal reasoning segments of varying complexity. Combining these techniques, we propose the first reasoning strategy that enables fast processing of easy steps and deeper analysis for complex reasoning. Without any training or additional cost, our plug-and-play method yields an average +1.3% accuracy with -8.6% token usage across leading LRMs and advanced reasoning benchmarks. All of our algorithms are implemented based on vLLM and are expected to support broader applications and inspire future research. △ Less

Submitted 4 July, 2025; originally announced July 2025.

DNN-Based Precoding in RIS-Aided mmWave MIMO Systems With Practical Phase Shift

Authors: Po-Heng Chou, Ching-Wen Chen, Wan-Jen Huang, Walid Saad, Yu Tsao, Ronald Y. Chang

Abstract: In this paper, the precoding design is investigated for maximizing the throughput of millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems with obstructed direct communication paths. In particular, a reconfigurable intelligent surface (RIS) is employed to enhance MIMO transmissions, considering mmWave characteristics related to line-of-sight (LoS) and multipath effects. The tradit… ▽ More In this paper, the precoding design is investigated for maximizing the throughput of millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems with obstructed direct communication paths. In particular, a reconfigurable intelligent surface (RIS) is employed to enhance MIMO transmissions, considering mmWave characteristics related to line-of-sight (LoS) and multipath effects. The traditional exhaustive search (ES) for optimal codewords in the continuous phase shift is computationally intensive and time-consuming. To reduce computational complexity, permuted discrete Fourier transform (DFT) vectors are used for finding codebook design, incorporating amplitude responses for practical or ideal RIS systems. However, even if the discrete phase shift is adopted in the ES, it results in significant computation and is time-consuming. Instead, the trained deep neural network (DNN) is developed to facilitate faster codeword selection. Simulation results show that the DNN maintains sub-optimal spectral efficiency even as the distance between the end-user and the RIS has variations in the testing phase. These results highlight the potential of DNN in advancing RIS-aided systems. △ Less

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

Comments: 5 pages, 4 figures, 2 tables, accepted by 2024 IEEE Globecom Workshops

DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment

Authors: Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, Chao-Han Huck Yang, Sung-Feng Huang, Chih-Kai Yang, Chee-En Yu, Chun-Wei Chen, Wei-Chih Chen, Chien-yu Huang, Yi-Cheng Lin, Yu-Xiang Lin, Chi-An Fu, Chun-Yi Kuan, Wenze Ren, Xuanjun Chen, Wei-Ping Huang, En-Pei Hu, Tzu-Quan Lin, Yuan-Kuei Wu, Kuan-Po Huang, Hsiao-Ying Huang, Huang-Cheng Chou, Kai-Wei Chang, Cheng-Han Chiang , et al. (3 additional authors not shown)

Abstract: We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following, without requiring task-specific audio instruction-tuning. Recent LALMs typically augment Large Language Models (LLMs) with auditory capabilities by training on large-scale, manually curated or LLM-synthesized audio-instruction datasets. However, these… ▽ More We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following, without requiring task-specific audio instruction-tuning. Recent LALMs typically augment Large Language Models (LLMs) with auditory capabilities by training on large-scale, manually curated or LLM-synthesized audio-instruction datasets. However, these approaches have often suffered from the catastrophic forgetting of the LLM's original language abilities. To address this, we revisit the data construction pipeline and propose DeSTA, a self-generated cross-modal alignment strategy in which the backbone LLM generates its own training targets. This approach preserves the LLM's native language proficiency while establishing effective audio-text alignment, thereby enabling zero-shot generalization without task-specific tuning. Using DeSTA, we construct DeSTA-AQA5M, a large-scale, task-agnostic dataset containing 5 million training samples derived from 7,000 hours of audio spanning 50 diverse datasets, including speech, environmental sounds, and music. DeSTA2.5-Audio achieves state-of-the-art or competitive performance across a wide range of audio-language benchmarks, including Dynamic-SUPERB, MMAU, SAKURA, Speech-IFEval, and VoiceBench. Comprehensive comparative studies demonstrate that our self-generated strategy outperforms widely adopted data construction and training strategies in both auditory perception and instruction-following capabilities. Our findings underscore the importance of carefully designed data construction in LALM development and offer practical insights for building robust, general-purpose LALMs. △ Less

Submitted 3 July, 2025; originally announced July 2025.

Comments: Model and code available at: https://github.com/kehanlu/DeSTA2.5-Audio

Decision-Oriented Text Evaluation

Authors: Yu-Shiang Huang, Chuan-Ju Wang, Chung-Chi Chen

Abstract: Natural language generation (NLG) is increasingly deployed in high-stakes domains, yet common intrinsic evaluation methods, such as n-gram overlap or sentence plausibility, weakly correlate with actual decision-making efficacy. We propose a decision-oriented framework for evaluating generated text by directly measuring its influence on human and large language model (LLM) decision outcomes. Using… ▽ More Natural language generation (NLG) is increasingly deployed in high-stakes domains, yet common intrinsic evaluation methods, such as n-gram overlap or sentence plausibility, weakly correlate with actual decision-making efficacy. We propose a decision-oriented framework for evaluating generated text by directly measuring its influence on human and large language model (LLM) decision outcomes. Using market digest texts--including objective morning summaries and subjective closing-bell analyses--as test cases, we assess decision quality based on the financial performance of trades executed by human investors and autonomous LLM agents informed exclusively by these texts. Our findings reveal that neither humans nor LLM agents consistently surpass random performance when relying solely on summaries. However, richer analytical commentaries enable collaborative human-LLM teams to outperform individual human or agent baselines significantly. Our approach underscores the importance of evaluating generated text by its ability to facilitate synergistic decision-making between humans and LLMs, highlighting critical limitations of traditional intrinsic metrics. △ Less

Submitted 3 July, 2025; v1 submitted 2 July, 2025; originally announced July 2025.

TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking

Authors: Bingxi Liu, Calvin Chen, Junhao Li, Guyang Yu, Haoqian Song, Xuchen Liu, Jinqiang Cui, Hong Zhang

Abstract: The Vision Transformer (ViT) model has long struggled with the challenge of quadratic complexity, a limitation that becomes especially critical in unmanned aerial vehicle (UAV) tracking systems, where data must be processed in real time. In this study, we explore the recently proposed State-Space Model, Mamba, leveraging its computational efficiency and capability for long-sequence modeling to eff… ▽ More The Vision Transformer (ViT) model has long struggled with the challenge of quadratic complexity, a limitation that becomes especially critical in unmanned aerial vehicle (UAV) tracking systems, where data must be processed in real time. In this study, we explore the recently proposed State-Space Model, Mamba, leveraging its computational efficiency and capability for long-sequence modeling to effectively process dense image sequences in tracking tasks. First, we highlight the issue of temporal inconsistency in existing Mamba-based methods, specifically the failure to account for temporal continuity in the Mamba scanning mechanism. Secondly, building upon this insight,we propose TrackingMiM, a Mamba-in-Mamba architecture, a minimal-computation burden model for handling image sequence of tracking problem. In our framework, the mamba scan is performed in a nested way while independently process temporal and spatial coherent patch tokens. While the template frame is encoded as query token and utilized for tracking in every scan. Extensive experiments conducted on five UAV tracking benchmarks confirm that the proposed TrackingMiM achieves state-of-the-art precision while offering noticeable higher speed in UAV tracking. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Comments: 12 pages

DocShaDiffusion: Diffusion Model in Latent Space for Document Image Shadow Removal

Authors: Wenjie Liu, Bingshu Wang, Ze Wang, C. L. Philip Chen

Abstract: Document shadow removal is a crucial task in the field of document image enhancement. However, existing methods tend to remove shadows with constant color background and ignore color shadows. In this paper, we first design a diffusion model in latent space for document image shadow removal, called DocShaDiffusion. It translates shadow images from pixel space to latent space, enabling the model to… ▽ More Document shadow removal is a crucial task in the field of document image enhancement. However, existing methods tend to remove shadows with constant color background and ignore color shadows. In this paper, we first design a diffusion model in latent space for document image shadow removal, called DocShaDiffusion. It translates shadow images from pixel space to latent space, enabling the model to more easily capture essential features. To address the issue of color shadows, we design a shadow soft-mask generation module (SSGM). It is able to produce accurate shadow mask and add noise into shadow regions specially. Guided by the shadow mask, a shadow mask-aware guided diffusion module (SMGDM) is proposed to remove shadows from document images by supervising the diffusion and denoising process. We also propose a shadow-robust perceptual feature loss to preserve details and structures in document images. Moreover, we develop a large-scale synthetic document color shadow removal dataset (SDCSRD). It simulates the distribution of realistic color shadows and provides powerful supports for the training of models. Experiments on three public datasets validate the proposed method's superiority over state-of-the-art. Our code and dataset will be publicly available. △ Less

Submitted 2 July, 2025; originally announced July 2025.

RapidStore: An Efficient Dynamic Graph Storage System for Concurrent Queries

Authors: Chiyu Hao, Jixian Su, Shixuan Sun, Hao Zhang, Sen Gao, Jianwen Zhao, Chenyi Zhang, Jieru Zhao, Chen Chen, Minyi Guo

Abstract: Dynamic graph storage systems are essential for real-time applications such as social networks and recommendation, where graph data continuously evolves. However, they face significant challenges in efficiently handling concurrent read and write operations. We find that existing methods suffer from write queries interfering with read efficiency, substantial time and space overhead due to per-edge… ▽ More Dynamic graph storage systems are essential for real-time applications such as social networks and recommendation, where graph data continuously evolves. However, they face significant challenges in efficiently handling concurrent read and write operations. We find that existing methods suffer from write queries interfering with read efficiency, substantial time and space overhead due to per-edge versioning, and an inability to balance performance, such as slow searches under concurrent workloads. To address these issues, we propose RapidStore, a holistic approach for efficient in-memory dynamic graph storage designed for read-intensive workloads. Our key idea is to exploit the characteristics of graph queries through a decoupled system design that separates the management of read and write queries and decouples version data from graph data. Particularly, we design an efficient dynamic graph store to cooperate with the graph concurrency control mechanism. Experimental results demonstrate that RapidStore enables fast and scalable concurrent graph queries, effectively balancing the performance of inserts, searches, and scans, and significantly improving efficiency in dynamic graph storage systems. △ Less

Submitted 1 July, 2025; originally announced July 2025.

Comments: 17 pages, 18 figures

Accurate and Efficient Fetal Birth Weight Estimation from 3D Ultrasound

Authors: Jian Wang, Qiongying Ni, Hongkui Yu, Ruixuan Yao, Jinqiao Ying, Bin Zhang, Xingyi Yang, Jin Peng, Jiongquan Chen, Junxuan Yu, Wenlong Shi, Chaoyu Chen, Zhongnuo Yan, Mingyuan Luo, Gaocheng Cai, Dong Ni, Jing Lu, Xin Yang

Abstract: Accurate fetal birth weight (FBW) estimation is essential for optimizing delivery decisions and reducing perinatal mortality. However, clinical methods for FBW estimation are inefficient, operator-dependent, and challenging to apply in cases of complex fetal anatomy. Existing deep learning methods are based on 2D standard ultrasound (US) images or videos that lack spatial information, limiting the… ▽ More Accurate fetal birth weight (FBW) estimation is essential for optimizing delivery decisions and reducing perinatal mortality. However, clinical methods for FBW estimation are inefficient, operator-dependent, and challenging to apply in cases of complex fetal anatomy. Existing deep learning methods are based on 2D standard ultrasound (US) images or videos that lack spatial information, limiting their prediction accuracy. In this study, we propose the first method for directly estimating FBW from 3D fetal US volumes. Our approach integrates a multi-scale feature fusion network (MFFN) and a synthetic sample-based learning framework (SSLF). The MFFN effectively extracts and fuses multi-scale features under sparse supervision by incorporating channel attention, spatial attention, and a ranking-based loss function. SSLF generates synthetic samples by simply combining fetal head and abdomen data from different fetuses, utilizing semi-supervised learning to improve prediction performance. Experimental results demonstrate that our method achieves superior performance, with a mean absolute error of $166.4\pm155.9$ $g$ and a mean absolute percentage error of $5.1\pm4.6$%, outperforming existing methods and approaching the accuracy of a senior doctor. Code is available at: https://github.com/Qioy-i/EFW. △ Less

Submitted 30 June, 2025; originally announced July 2025.

Comments: Accepted by MICCAI 2025

Predictive Risk Analysis and Safe Trajectory Planning for Intelligent and Connected Vehicles

Authors: Zeyu Han, Mengchi Cai, Chaoyi Chen, Qingwen Meng, Guangwei Wang, Ying Liu, Qing Xu, Jianqiang Wang, Keqiang Li

Abstract: The safe trajectory planning of intelligent and connected vehicles is a key component in autonomous driving technology. Modeling the environment risk information by field is a promising and effective approach for safe trajectory planning. However, existing risk assessment theories only analyze the risk by current information, ignoring future prediction. This paper proposes a predictive risk analys… ▽ More The safe trajectory planning of intelligent and connected vehicles is a key component in autonomous driving technology. Modeling the environment risk information by field is a promising and effective approach for safe trajectory planning. However, existing risk assessment theories only analyze the risk by current information, ignoring future prediction. This paper proposes a predictive risk analysis and safe trajectory planning framework for intelligent and connected vehicles. This framework first predicts future trajectories of objects by a local risk-aware algorithm, following with a spatiotemporal-discretised predictive risk analysis using the prediction results. Then the safe trajectory is generated based on the predictive risk analysis. Finally, simulation and vehicle experiments confirm the efficacy and real-time practicability of our approach. △ Less

Submitted 30 June, 2025; originally announced June 2025.

Escher Tile Deformation via Closed-Form Solution

Authors: Crane He Chen, Vladimir G. Kim

Abstract: We present a real-time deformation method for Escher tiles -- interlocking organic forms that seamlessly tessellate the plane following symmetry rules. We formulate the problem as determining a periodic displacement field. The goal is to deform Escher tiles without introducing gaps or overlaps. The resulting displacement field is obtained in closed form by an analytical solution. Our method proces… ▽ More We present a real-time deformation method for Escher tiles -- interlocking organic forms that seamlessly tessellate the plane following symmetry rules. We formulate the problem as determining a periodic displacement field. The goal is to deform Escher tiles without introducing gaps or overlaps. The resulting displacement field is obtained in closed form by an analytical solution. Our method processes tiles of 17 wallpaper groups across various representations such as images and meshes. Rather than treating tiles as mere boundaries, we consider them as textured shapes, ensuring that both the boundary and interior deform simultaneously. To enable fine-grained artistic input, our interactive tool features a user-controllable adaptive fall-off parameter, allowing precise adjustment of locality and supporting deformations with meaningful semantic control. We demonstrate the effectiveness of our method through various examples, including photo editing and shape sculpting, showing its use in applications such as fabrication and animation. △ Less

Submitted 29 June, 2025; originally announced June 2025.

Journal ref: SIGGRAPH 2025

Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair via Repair Ingredients Search

Authors: Jiayi Zhang, Kai Huang, Jian Zhang, Yang Liu, Chunyang Chen

Abstract: Automated Program Repair (APR) techniques aim to automatically fix buggy programs. Among these, Large Language Model-based (LLM-based) approaches have shown great promise. Recent advances demonstrate that directly leveraging LLMs can achieve leading results. However, these techniques remain suboptimal in generating contextually relevant and accurate patches, as they often overlook repair ingredien… ▽ More Automated Program Repair (APR) techniques aim to automatically fix buggy programs. Among these, Large Language Model-based (LLM-based) approaches have shown great promise. Recent advances demonstrate that directly leveraging LLMs can achieve leading results. However, these techniques remain suboptimal in generating contextually relevant and accurate patches, as they often overlook repair ingredients crucial for practical program repair. In this paper, we propose ReinFix, a novel framework that enables LLMs to autonomously search for repair ingredients throughout both the reasoning and solution phases of bug fixing. In the reasoning phase, ReinFix integrates static analysis tools to retrieve internal ingredients, such as variable definitions, to assist the LLM in root cause analysis when it encounters difficulty understanding the context. During the solution phase, when the LLM lacks experience in fixing specific bugs, ReinFix searches for external ingredients from historical bug fixes with similar bug patterns, leveraging both the buggy code and its root cause to guide the LLM in identifying appropriate repair actions, thereby increasing the likelihood of generating correct patches. Evaluations on two popular benchmarks (Defects4J V1.2 and V2.0) demonstrate the effectiveness of our approach over SOTA baselines. Notably, ReinFix fixes 146 bugs, which is 32 more than the baselines on Defects4J V1.2. On Defects4J V2.0, ReinFix fixes 38 more bugs than the SOTA. Importantly, when evaluating on the recent benchmarks that are free of data leakage risk, ReinFix also maintains the best performance. △ Less

Submitted 29 June, 2025; originally announced June 2025.

Comments: Accepted by ICSE 2026. Jiayi Zhang and Kai Huang contributed equally to this work

MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models

Authors: Jian Chen, Wenye Ma, Penghang Liu, Wei Wang, Tengwei Song, Ming Li, Chenguang Wang, Ruiyi Zhang, Changyou Chen

Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable visual reasoning abilities in natural images, text-rich documents, and graphic designs. However, their ability to interpret music sheets remains underexplored. To bridge this gap, we introduce MusiXQA, the first comprehensive dataset for evaluating and advancing MLLMs in music sheet understanding. MusiXQA features high-quality synth… ▽ More Multimodal Large Language Models (MLLMs) have achieved remarkable visual reasoning abilities in natural images, text-rich documents, and graphic designs. However, their ability to interpret music sheets remains underexplored. To bridge this gap, we introduce MusiXQA, the first comprehensive dataset for evaluating and advancing MLLMs in music sheet understanding. MusiXQA features high-quality synthetic music sheets generated via MusiXTeX, with structured annotations covering note pitch and duration, chords, clefs, key/time signatures, and text, enabling diverse visual QA tasks. Through extensive evaluations, we reveal significant limitations of current state-of-the-art MLLMs in this domain. Beyond benchmarking, we developed Phi-3-MusiX, an MLLM fine-tuned on our dataset, achieving significant performance gains over GPT-based methods. The proposed dataset and model establish a foundation for future advances in MLLMs for music sheet understanding. Code, data, and model will be released upon acceptance. △ Less

Submitted 28 June, 2025; originally announced June 2025.