Showing 1–50 of 2,329 results for author: Xu, X

Mindfulness Meditation and Respiration: Accelerometer-Based Respiration Rate and Mindfulness Progress Estimation to Enhance App Engagement and Mindfulness Skills

Authors: Mohammad Nur Hossain Khan, David creswell, Jordan Albert, Patrick O'Connell, Shawn Fallon, Mathew Polowitz, Xuhai "orson" Xu, Bashima islam

Abstract: Mindfulness training is widely recognized for its benefits in reducing depression, anxiety, and loneliness. With the rise of smartphone-based mindfulness apps, digital meditation has become more accessible, but sustaining long-term user engagement remains a challenge. This paper explores whether respiration biosignal feedback and mindfulness skill estimation enhance system usability and skill deve… ▽ More Mindfulness training is widely recognized for its benefits in reducing depression, anxiety, and loneliness. With the rise of smartphone-based mindfulness apps, digital meditation has become more accessible, but sustaining long-term user engagement remains a challenge. This paper explores whether respiration biosignal feedback and mindfulness skill estimation enhance system usability and skill development. We develop a smartphone's accelerometer-based respiration tracking algorithm, eliminating the need for additional wearables. Unlike existing methods, our approach accurately captures slow breathing patterns typical of mindfulness meditation. Additionally, we introduce the first quantitative framework to estimate mindfulness skills-concentration, sensory clarity, and equanimity-based on accelerometer-derived respiration data. We develop and test our algorithms on 261 mindfulness sessions in both controlled and real-world settings. A user study comparing an experimental group receiving biosignal feedback with a control group using a standard app shows that respiration feedback enhances system usability. Our respiration tracking model achieves a mean absolute error (MAE) of 1.6 breaths per minute, closely aligning with ground truth data, while our mindfulness skill estimation attains F1 scores of 80-84% in tracking skill progression. By integrating respiration tracking and mindfulness estimation into a commercial app, we demonstrate the potential of smartphone sensors to enhance digital mindfulness training. △ Less

Submitted 23 July, 2025; originally announced July 2025.

Comments: Accepted in Proc. ACM Interact. Mob. Wearable Ubiquitous Technology (IMWUT)

Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors

Authors: Chen Ma, Xinjie Xu, Shuyu Cheng, Qi Xuan

Abstract: One of the most practical and challenging types of black-box adversarial attacks is the hard-label attack, where only the top-1 predicted label is available. One effective approach is to search for the optimal ray direction from the benign image that minimizes the $\ell_p$-norm distance to the adversarial region. The unique advantage of this approach is that it transforms the hard-label attack int… ▽ More One of the most practical and challenging types of black-box adversarial attacks is the hard-label attack, where only the top-1 predicted label is available. One effective approach is to search for the optimal ray direction from the benign image that minimizes the $\ell_p$-norm distance to the adversarial region. The unique advantage of this approach is that it transforms the hard-label attack into a continuous optimization problem. The objective function value is the ray's radius, which can be obtained via binary search at a high query cost. Existing methods use a "sign trick" in gradient estimation to reduce the number of queries. In this paper, we theoretically analyze the quality of this gradient estimation and propose a novel prior-guided approach to improve ray search efficiency both theoretically and empirically. Specifically, we utilize the transfer-based priors from surrogate models, and our gradient estimators appropriately integrate them by approximating the projection of the true gradient onto the subspace spanned by these priors and random directions, in a query-efficient manner. We theoretically derive the expected cosine similarities between the obtained gradient estimators and the true gradient, and demonstrate the improvement achieved by incorporating priors. Extensive experiments on the ImageNet and CIFAR-10 datasets show that our approach significantly outperforms 11 state-of-the-art methods in terms of query efficiency. △ Less

Submitted 23 July, 2025; originally announced July 2025.

Comments: Published at ICLR 2025 (Spotlight paper)

ACM Class: I.2.6; I.5.1; G.1.6

An h-space Based Adversarial Attack for Protection Against Few-shot Personalization

Authors: Xide Xu, Sandesh Kamath, Muhammad Atif Butt, Bogdan Raducanu

Abstract: The versatility of diffusion models in generating customized images from few samples raises significant privacy concerns, particularly regarding unauthorized modifications of private content. This concerning issue has renewed the efforts in developing protection mechanisms based on adversarial attacks, which generate effective perturbations to poison diffusion models. Our work is motivated by the… ▽ More The versatility of diffusion models in generating customized images from few samples raises significant privacy concerns, particularly regarding unauthorized modifications of private content. This concerning issue has renewed the efforts in developing protection mechanisms based on adversarial attacks, which generate effective perturbations to poison diffusion models. Our work is motivated by the observation that these models exhibit a high degree of abstraction within their semantic latent space (`h-space'), which encodes critical high-level features for generating coherent and meaningful content. In this paper, we propose a novel anti-customization approach, called HAAD (h-space based Adversarial Attack for Diffusion models), that leverages adversarial attacks to craft perturbations based on the h-space that can efficiently degrade the image generation process. Building upon HAAD, we further introduce a more efficient variant, HAAD-KV, that constructs perturbations solely based on the KV parameters of the h-space. This strategy offers a stronger protection, that is computationally less expensive. Despite their simplicity, our methods outperform state-of-the-art adversarial attacks, highlighting their effectiveness. △ Less

Submitted 23 July, 2025; originally announced July 2025.

Comments: 32 pages, 15 figures. Accepted by ACM Multimedia 2025

Exploring Spatial Diversity for Region-based Active Learning

Authors: Lile Cai, Xun Xu, Lining Zhang, Chuan-Sheng Foo

Abstract: State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation costs, especially for dense pixel-level prediction tasks like semantic segmentation. We consider region-based active learning as a strategy to reduce annotation costs while maintaining high performance. In this setting, b… ▽ More State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation costs, especially for dense pixel-level prediction tasks like semantic segmentation. We consider region-based active learning as a strategy to reduce annotation costs while maintaining high performance. In this setting, batches of informative image regions instead of entire images are selected for labeling. Importantly, we propose that enforcing local spatial diversity is beneficial for active learning in this case, and to incorporate spatial diversity along with the traditional active selection criterion, e.g., data sample uncertainty, in a unified optimization framework for region-based active learning. We apply this framework to the Cityscapes and PASCAL VOC datasets and demonstrate that the inclusion of spatial diversity effectively improves the performance of uncertainty-based and feature diversity-based active learning methods. Our framework achieves $95\%$ performance of fully supervised methods with only $5-9\%$ of the labeled pixels, outperforming all state-of-the-art region-based active learning methods for semantic segmentation. △ Less

Submitted 23 July, 2025; originally announced July 2025.

Comments: published in IEEE Transactions on Image Processing, 2021

Exploring Active Learning for Semiconductor Defect Segmentation

Authors: Lile Cai, Ramanpreet Singh Pahwa, Xun Xu, Jie Wang, Richard Chang, Lining Zhang, Chuan-Sheng Foo

Abstract: The development of X-Ray microscopy (XRM) technology has enabled non-destructive inspection of semiconductor structures for defect identification. Deep learning is widely used as the state-of-the-art approach to perform visual analysis tasks. However, deep learning based models require large amount of annotated data to train. This can be time-consuming and expensive to obtain especially for dense… ▽ More The development of X-Ray microscopy (XRM) technology has enabled non-destructive inspection of semiconductor structures for defect identification. Deep learning is widely used as the state-of-the-art approach to perform visual analysis tasks. However, deep learning based models require large amount of annotated data to train. This can be time-consuming and expensive to obtain especially for dense prediction tasks like semantic segmentation. In this work, we explore active learning (AL) as a potential solution to alleviate the annotation burden. We identify two unique challenges when applying AL on semiconductor XRM scans: large domain shift and severe class-imbalance. To address these challenges, we propose to perform contrastive pretraining on the unlabelled data to obtain the initialization weights for each AL cycle, and a rareness-aware acquisition function that favors the selection of samples containing rare classes. We evaluate our method on a semiconductor dataset that is compiled from XRM scans of high bandwidth memory structures composed of logic and memory dies, and demonstrate that our method achieves state-of-the-art performance. △ Less

Submitted 23 July, 2025; originally announced July 2025.

Comments: accepted to ICIP 2022

Quantitative Quantum Soundness for Bipartite Compiled Bell Games via the Sequential NPA Hierarchy

Authors: Igor Klep, Connor Paddock, Marc-Olivier Renou, Simon Schmidt, Lucas Tendick, Xiangling Xu, Yuming Zhao

Abstract: Compiling Bell games under cryptographic assumptions replaces the need for physical separation, allowing nonlocality to be probed with a single untrusted device. While Kalai et al. (STOC'23) showed that this compilation preserves quantum advantages, its quantitative quantum soundness has remained an open problem. We address this gap with two primary contributions. First, we establish the first qua… ▽ More Compiling Bell games under cryptographic assumptions replaces the need for physical separation, allowing nonlocality to be probed with a single untrusted device. While Kalai et al. (STOC'23) showed that this compilation preserves quantum advantages, its quantitative quantum soundness has remained an open problem. We address this gap with two primary contributions. First, we establish the first quantitative quantum soundness bounds for every bipartite compiled Bell game whose optimal quantum strategy is finite-dimensional: any polynomial-time prover's score in the compiled game is negligibly close to the game's ideal quantum value. More generally, for all bipartite games we show that the compiled score cannot significantly exceed the bounds given by a newly formalized sequential Navascués-Pironio-Acín (NPA) hierarchy. Second, we provide a full characterization of this sequential NPA hierarchy, establishing it as a robust numerical tool that is of independent interest. Finally, for games without finite-dimensional optimal strategies, we explore the necessity of NPA approximation error for quantitatively bounding their compiled scores, linking these considerations to the complexity conjecture $\mathrm{MIP}^{\mathrm{co}}=\mathrm{coRE}$ and open challenges such as quantum homomorphic encryption correctness for "weakly commuting" quantum registers. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Comments: 41 pages, 1 figure; comments welcome. We refer to Cui, Falor, Natarajan, and Zhang for an independent parallel work on the same topic

Improving U-Net Confidence on TEM Image Data with L2-Regularization, Transfer Learning, and Deep Fine-Tuning

Authors: Aiden Ochoa, Xinyuan Xu, Xing Wang

Abstract: With ever-increasing data volumes, it is essential to develop automated approaches for identifying nanoscale defects in transmission electron microscopy (TEM) images. However, compared to features in conventional photographs, nanoscale defects in TEM images exhibit far greater variation due to the complex contrast mechanisms and intricate defect structures. These challenges often result in much le… ▽ More With ever-increasing data volumes, it is essential to develop automated approaches for identifying nanoscale defects in transmission electron microscopy (TEM) images. However, compared to features in conventional photographs, nanoscale defects in TEM images exhibit far greater variation due to the complex contrast mechanisms and intricate defect structures. These challenges often result in much less labeled data and higher rates of annotation errors, posing significant obstacles to improving machine learning model performance for TEM image analysis. To address these limitations, we examined transfer learning by leveraging large, pre-trained models used for natural images. We demonstrated that by using the pre-trained encoder and L2-regularization, semantically complex features are ignored in favor of simpler, more reliable cues, substantially improving the model performance. However, this improvement cannot be captured by conventional evaluation metrics such as F1-score, which can be skewed by human annotation errors treated as ground truth. Instead, we introduced novel evaluation metrics that are independent of the annotation accuracy. Using grain boundary detection in UO2 TEM images as a case study, we found that our approach led to a 57% improvement in defect detection rate, which is a robust and holistic measure of model performance on the TEM dataset used in this work. Finally, we showed that model self-confidence is only achieved through transfer learning and fine-tuning of very deep layers. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Comments: Accepted into the ICCV 2025 CV4MS Workshop

From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure

Authors: Sijin Yu, Zijiao Chen, Wenxuan Wu, Shengxian Chen, Zhongliang Liu, Jingxin Nie, Xiaofen Xing, Xiangmin Xu, Xin Zhang

Abstract: Reconstructing visual stimuli from human brain activity (e.g., fMRI) bridges neuroscience and computer vision by decoding neural representations. However, existing methods often overlook critical brain structure-function relationships, flattening spatial information and neglecting individual anatomical variations. To address these issues, we propose (1) a novel sphere tokenizer that explicitly mod… ▽ More Reconstructing visual stimuli from human brain activity (e.g., fMRI) bridges neuroscience and computer vision by decoding neural representations. However, existing methods often overlook critical brain structure-function relationships, flattening spatial information and neglecting individual anatomical variations. To address these issues, we propose (1) a novel sphere tokenizer that explicitly models fMRI signals as spatially coherent 2D spherical data on the cortical surface; (2) integration of structural MRI (sMRI) data, enabling personalized encoding of individual anatomical variations; and (3) a positive-sample mixup strategy for efficiently leveraging multiple fMRI scans associated with the same visual stimulus. Collectively, these innovations enhance reconstruction accuracy, biological interpretability, and generalizability across individuals. Experiments demonstrate superior reconstruction performance compared to SOTA methods, highlighting the effectiveness and interpretability of our biologically informed approach. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Comments: 18 pages, 14 figures, ICCV Findings 2025

Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny

Authors: Chuanhao Yan, Fengdi Che, Xuhan Huang, Xu Xu, Xin Li, Yizhi Li, Xingwei Qu, Jingzhe Shi, Zhuangzhuang He, Chenghua Lin, Yaodong Yang, Binhang Yuan, Hang Zhao, Yu Qiao, Bowen Zhou, Jie Fu

Abstract: Existing informal language-based (e.g., human language) Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant challenge: their verification processes, which provide crucial training signals, are neither reliable nor scalable. In fact, the prevalent large proprietary models could hardly generate verifiable programs. A promising yet largely uncharted alternative is… ▽ More Existing informal language-based (e.g., human language) Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant challenge: their verification processes, which provide crucial training signals, are neither reliable nor scalable. In fact, the prevalent large proprietary models could hardly generate verifiable programs. A promising yet largely uncharted alternative is formal language-based reasoning. Grounding LLMs in rigorous formal systems where generative models operate in formal language spaces (e.g., Dafny) enables the automatic and mathematically provable verification of their reasoning processes and outcomes. This capability is pivotal for achieving large-scale, reliable formal software verification. It is a common practice to employ human-annotated chain-of-thought and other human priors to induce the reasoning and coding capabilities of LLMs. Unfortunately, it becomes unacceptably all-consuming to provide such priors for supervising complex programming tasks. In this work, we systematically explore ways to reduce human priors with the formal language, Dafny, as the main environment for our pilot study. Our pipeline mainly relies on introducing an automatic and scalable data curation pipeline, and careful RL designs integrated with feedback from the formal language verifier. We introduce DafnyComp, a benchmark of compositional formal programs with auto-formalized specifications for specification reasoning. Our supervised fine-tuning (SFT) stage enables even small models (e.g., 0.5B) to generate syntactically valid and verifiable Dafny code, surpassing proprietary models. RL with regularization further improves performance, achieving stronger generalization to out-of-domain tasks and outperforming all strong baselines on the challenging DafnyComp benchmark. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Positive Style Accumulation: A Style Screening and Continuous Utilization Framework for Federated DG-ReID

Authors: Xin Xu, Chaoyue Ren, Wei Liu, Wenke Huang, Bin Yang, Zhixi Yu, Kui Jiang

Abstract: The Federated Domain Generalization for Person re-identification (FedDG-ReID) aims to learn a global server model that can be effectively generalized to source and target domains through distributed source domain data. Existing methods mainly improve the diversity of samples through style transformation, which to some extent enhances the generalization performance of the model. However, we discove… ▽ More The Federated Domain Generalization for Person re-identification (FedDG-ReID) aims to learn a global server model that can be effectively generalized to source and target domains through distributed source domain data. Existing methods mainly improve the diversity of samples through style transformation, which to some extent enhances the generalization performance of the model. However, we discover that not all styles contribute to the generalization performance. Therefore, we define styles that are beneficial or harmful to the model's generalization performance as positive or negative styles. Based on this, new issues arise: How to effectively screen and continuously utilize the positive styles. To solve these problems, we propose a Style Screening and Continuous Utilization (SSCU) framework. Firstly, we design a Generalization Gain-guided Dynamic Style Memory (GGDSM) for each client model to screen and accumulate generated positive styles. Meanwhile, we propose a style memory recognition loss to fully leverage the positive styles memorized by Memory. Furthermore, we propose a Collaborative Style Training (CST) strategy to make full use of positive styles. Unlike traditional learning strategies, our approach leverages both newly generated styles and the accumulated positive styles stored in memory to train client models on two distinct branches. This training strategy is designed to effectively promote the rapid acquisition of new styles by the client models, and guarantees the continuous and thorough utilization of positive styles, which is highly beneficial for the model's generalization performance. Extensive experimental results demonstrate that our method outperforms existing methods in both the source domain and the target domain. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Comments: 10 pages, 3 figures, accepted at ACM MM 2025, Submission ID: 4394

ACM Class: I.4.9; I.2.10

A Framework for Analyzing Abnormal Emergence in Service Ecosystems Through LLM-based Agent Intention Mining

Authors: Yifan Shen, Zihan Zhao, Xiao Xue, Yuwei Guo, Qun Ma, Deyu Zhou, Ming Zhang

Abstract: With the rise of service computing, cloud computing, and IoT, service ecosystems are becoming increasingly complex. The intricate interactions among intelligent agents make abnormal emergence analysis challenging, as traditional causal methods focus on individual trajectories. Large language models offer new possibilities for Agent-Based Modeling (ABM) through Chain-of-Thought (CoT) reasoning to r… ▽ More With the rise of service computing, cloud computing, and IoT, service ecosystems are becoming increasingly complex. The intricate interactions among intelligent agents make abnormal emergence analysis challenging, as traditional causal methods focus on individual trajectories. Large language models offer new possibilities for Agent-Based Modeling (ABM) through Chain-of-Thought (CoT) reasoning to reveal agent intentions. However, existing approaches remain limited to microscopic and static analysis. This paper introduces a framework: Emergence Analysis based on Multi-Agent Intention (EAMI), which enables dynamic and interpretable emergence analysis. EAMI first employs a dual-perspective thought track mechanism, where an Inspector Agent and an Analysis Agent extract agent intentions under bounded and perfect rationality. Then, k-means clustering identifies phase transition points in group intentions, followed by a Intention Temporal Emergence diagram for dynamic analysis. The experiments validate EAMI in complex online-to-offline (O2O) service system and the Stanford AI Town experiment, with ablation studies confirming its effectiveness, generalizability, and efficiency. This framework provides a novel paradigm for abnormal emergence and causal analysis in service ecosystems. The code is available at https://anonymous.4open.science/r/EAMI-B085. △ Less

Submitted 21 July, 2025; originally announced July 2025.

Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation

Authors: Xinran Li, Xiujuan Xu, Jiaqi Qiao

Abstract: Emotion Recognition in Conversation (ERC) is a practical and challenging task. This paper proposes a novel multimodal approach, the Long-Short Distance Graph Neural Network (LSDGNN). Based on the Directed Acyclic Graph (DAG), it constructs a long-distance graph neural network and a short-distance graph neural network to obtain multimodal features of distant and nearby utterances, respectively. To… ▽ More Emotion Recognition in Conversation (ERC) is a practical and challenging task. This paper proposes a novel multimodal approach, the Long-Short Distance Graph Neural Network (LSDGNN). Based on the Directed Acyclic Graph (DAG), it constructs a long-distance graph neural network and a short-distance graph neural network to obtain multimodal features of distant and nearby utterances, respectively. To ensure that long- and short-distance features are as distinct as possible in representation while enabling mutual influence between the two modules, we employ a Differential Regularizer and incorporate a BiAffine Module to facilitate feature interaction. In addition, we propose an Improved Curriculum Learning (ICL) to address the challenge of data imbalance. By computing the similarity between different emotions to emphasize the shifts in similar emotions, we design a "weighted emotional shift" metric and develop a difficulty measurer, enabling a training process that prioritizes learning easy samples before harder ones. Experimental results on the IEMOCAP and MELD datasets demonstrate that our model outperforms existing benchmarks. △ Less

Submitted 20 July, 2025; originally announced July 2025.

Comments: Accepted by the 28th European Conference on Artificial Intelligence (ECAI 2025)

From Kicking to Causality: Simulating Infant Agency Detection with a Robust Intrinsic Reward

Authors: Xia Xu, Jochen Triesch

Abstract: While human infants robustly discover their own causal efficacy, standard reinforcement learning agents remain brittle, as their reliance on correlation-based rewards fails in noisy, ecologically valid scenarios. To address this, we introduce the Causal Action Influence Score (CAIS), a novel intrinsic reward rooted in causal inference. CAIS quantifies an action's influence by measuring the 1-Wasse… ▽ More While human infants robustly discover their own causal efficacy, standard reinforcement learning agents remain brittle, as their reliance on correlation-based rewards fails in noisy, ecologically valid scenarios. To address this, we introduce the Causal Action Influence Score (CAIS), a novel intrinsic reward rooted in causal inference. CAIS quantifies an action's influence by measuring the 1-Wasserstein distance between the learned distribution of sensory outcomes conditional on that action, $p(h|a)$, and the baseline outcome distribution, $p(h)$. This divergence provides a robust reward that isolates the agent's causal impact from confounding environmental noise. We test our approach in a simulated infant-mobile environment where correlation-based perceptual rewards fail completely when the mobile is subjected to external forces. In stark contrast, CAIS enables the agent to filter this noise, identify its influence, and learn the correct policy. Furthermore, the high-quality predictive model learned for CAIS allows our agent, when augmented with a surprise signal, to successfully reproduce the "extinction burst" phenomenon. We conclude that explicitly inferring causality is a crucial mechanism for developing a robust sense of agency, offering a psychologically plausible framework for more adaptive autonomous systems. △ Less

Submitted 20 July, 2025; originally announced July 2025.

Comments: 13 pages, 5 figures

MSC Class: F.2.2

PaperBridge: Crafting Research Narratives through Human-AI Co-Exploration

Authors: Runhua Zhang, Yang Ouyang, Leixian Shen, Yuying Tang, Xiaojuan Ma, Huamin Qu, Xian Xu

Abstract: Researchers frequently need to synthesize their own publications into coherent narratives that demonstrate their scholarly contributions. To suit diverse communication contexts, exploring alternative ways to organize one's work while maintaining coherence is particularly challenging, especially in interdisciplinary fields like HCI where individual researchers' publications may span diverse domains… ▽ More Researchers frequently need to synthesize their own publications into coherent narratives that demonstrate their scholarly contributions. To suit diverse communication contexts, exploring alternative ways to organize one's work while maintaining coherence is particularly challenging, especially in interdisciplinary fields like HCI where individual researchers' publications may span diverse domains and methodologies. In this paper, we present PaperBridge, a human-AI co-exploration system informed by a formative study and content analysis. PaperBridge assists researchers in exploring diverse perspectives for organizing their publications into coherent narratives. At its core is a bi-directional analysis engine powered by large language models, supporting iterative exploration through both top-down user intent (e.g., determining organization structure) and bottom-up refinement on narrative components (e.g., thematic paper groupings). Our user study (N=12) demonstrated PaperBridge's usability and effectiveness in facilitating the exploration of alternative research narratives. Our findings also provided empirical insights into how interactive systems can scaffold academic communication tasks. △ Less

Submitted 19 July, 2025; originally announced July 2025.

Comments: Conditionally accepted by UIST'25

Generative Distribution Distillation

Authors: Jiequan Cui, Beier Zhu, Qingshan Xu, Xiaogang Xu, Pengguang Chen, Xiaojuan Qi, Bei Yu, Hanwang Zhang, Richang Hong

Abstract: In this paper, we formulate the knowledge distillation (KD) as a conditional generative problem and propose the \textit{Generative Distribution Distillation (GenDD)} framework. A naive \textit{GenDD} baseline encounters two major challenges: the curse of high-dimensional optimization and the lack of semantic supervision from labels. To address these issues, we introduce a \textit{Split Tokenizatio… ▽ More In this paper, we formulate the knowledge distillation (KD) as a conditional generative problem and propose the \textit{Generative Distribution Distillation (GenDD)} framework. A naive \textit{GenDD} baseline encounters two major challenges: the curse of high-dimensional optimization and the lack of semantic supervision from labels. To address these issues, we introduce a \textit{Split Tokenization} strategy, achieving stable and effective unsupervised KD. Additionally, we develop the \textit{Distribution Contraction} technique to integrate label supervision into the reconstruction objective. Our theoretical proof demonstrates that \textit{GenDD} with \textit{Distribution Contraction} serves as a gradient-level surrogate for multi-task learning, realizing efficient supervised training without explicit classification loss on multi-step sampling image representations. To evaluate the effectiveness of our method, we conduct experiments on balanced, imbalanced, and unlabeled data. Experimental results show that \textit{GenDD} performs competitively in the unsupervised setting, significantly surpassing KL baseline by \textbf{16.29\%} on ImageNet validation set. With label supervision, our ResNet-50 achieves \textbf{82.28\%} top-1 accuracy on ImageNet in 600 epochs training, establishing a new state-of-the-art. △ Less

Submitted 19 July, 2025; originally announced July 2025.

Comments: Technique report

Open-Vocabulary Object Detection in UAV Imagery: A Review and Future Perspectives

Authors: Yang Zhou, Junjie Li, CongYang Ou, Dawei Yan, Haokui Zhang, Xizhe Xue

Abstract: Due to its extensive applications, aerial image object detection has long been a hot topic in computer vision. In recent years, advancements in Unmanned Aerial Vehicles (UAV) technology have further propelled this field to new heights, giving rise to a broader range of application requirements. However, traditional UAV aerial object detection methods primarily focus on detecting predefined categor… ▽ More Due to its extensive applications, aerial image object detection has long been a hot topic in computer vision. In recent years, advancements in Unmanned Aerial Vehicles (UAV) technology have further propelled this field to new heights, giving rise to a broader range of application requirements. However, traditional UAV aerial object detection methods primarily focus on detecting predefined categories, which significantly limits their applicability. The advent of cross-modal text-image alignment (e.g., CLIP) has overcome this limitation, enabling open-vocabulary object detection (OVOD), which can identify previously unseen objects through natural language descriptions. This breakthrough significantly enhances the intelligence and autonomy of UAVs in aerial scene understanding. This paper presents a comprehensive survey of OVOD in the context of UAV aerial scenes. We begin by aligning the core principles of OVOD with the unique characteristics of UAV vision, setting the stage for a specialized discussion. Building on this foundation, we construct a systematic taxonomy that categorizes existing OVOD methods for aerial imagery and provides a comprehensive overview of the relevant datasets. This structured review enables us to critically dissect the key challenges and open problems at the intersection of these fields. Finally, based on this analysis, we outline promising future research directions and application prospects. This survey aims to provide a clear road map and a valuable reference for both newcomers and seasoned researchers, fostering innovation in this rapidly evolving domain. We keep tracing related works at https://github.com/zhouyang2002/OVOD-in-UVA-imagery △ Less

Submitted 4 July, 2025; originally announced July 2025.

Comments: 27 pages, 5 figures

Detecting LLM-generated Code with Subtle Modification by Adversarial Training

Authors: Xin Yin, Xinrui Li, Chao Ni, Xiaodan Xu, Xiaohu Yang

Abstract: With the rapid development of Large Language Models (LLMs), their powerful code-generation capabilities have been widely applied in tasks like code completion and automated development, demonstrating the value of improving coding efficiency. However, the extensive use of LLM-generated code also raises several new challenges. On the one hand, issues such as the regulation of code provenance, copyri… ▽ More With the rapid development of Large Language Models (LLMs), their powerful code-generation capabilities have been widely applied in tasks like code completion and automated development, demonstrating the value of improving coding efficiency. However, the extensive use of LLM-generated code also raises several new challenges. On the one hand, issues such as the regulation of code provenance, copyright disputes, and code quality have become increasingly concerning. How to effectively detect LLM-generated code and ensure its compliant and responsible use has become a critical and urgent issue. On the other hand, in practical applications, LLM-generated code is often subject to manual modifications, such as variable renaming or structural adjustments. Although some recent studies have proposed training-based and zero-shot methods for detecting LLM-generated code, these approaches show insufficient robustness when facing modified LLM-generated code, and there is a lack of an effective solution. To address the real-world scenario where LLM-generated code may undergo minor modifications, we propose CodeGPTSensor+, an enhanced version of CodeGPTSensor, which employs adversarial training to improve robustness against input perturbations. CodeGPTSensor+ integrates an adversarial sample generation module, Multi-objective Identifier and Structure Transformation (MIST), which systematically generates both high-quality and representative adversarial samples. This module effectively enhances the model's resistance against diverse adversarial attacks. Experimental results on the HMCorp dataset demonstrate that CodeGPTSensor+ significantly improves detection accuracy on the adversarial test set while maintaining high accuracy on the original test set, showcasing superior robustness compared to CodeGPTSensor. △ Less

Submitted 17 July, 2025; originally announced July 2025.

LoViC: Efficient Long Video Generation with Context Compression

Authors: Jiaxiu Jiang, Wenbo Li, Jingjing Ren, Yuping Qiu, Yong Guo, Xiaogang Xu, Han Wu, Wangmeng Zuo

Abstract: Despite recent advances in diffusion transformers (DiTs) for text-to-video generation, scaling to long-duration content remains challenging due to the quadratic complexity of self-attention. While prior efforts -- such as sparse attention and temporally autoregressive models -- offer partial relief, they often compromise temporal coherence or scalability. We introduce LoViC, a DiT-based framework… ▽ More Despite recent advances in diffusion transformers (DiTs) for text-to-video generation, scaling to long-duration content remains challenging due to the quadratic complexity of self-attention. While prior efforts -- such as sparse attention and temporally autoregressive models -- offer partial relief, they often compromise temporal coherence or scalability. We introduce LoViC, a DiT-based framework trained on million-scale open-domain videos, designed to produce long, coherent videos through a segment-wise generation process. At the core of our approach is FlexFormer, an expressive autoencoder that jointly compresses video and text into unified latent representations. It supports variable-length inputs with linearly adjustable compression rates, enabled by a single query token design based on the Q-Former architecture. Additionally, by encoding temporal context through position-aware mechanisms, our model seamlessly supports prediction, retradiction, interpolation, and multi-shot generation within a unified paradigm. Extensive experiments across diverse tasks validate the effectiveness and versatility of our approach. △ Less

Submitted 17 July, 2025; originally announced July 2025.

Comments: Project page: https://jiangjiaxiu.github.io/lovic/

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning

Authors: Fan Shi, Bin Li, Xiangyang Xue

Abstract: Abstract visual reasoning (AVR) enables humans to quickly discover and generalize abstract rules to new scenarios. Designing intelligent systems with human-like AVR abilities has been a long-standing topic in the artificial intelligence community. Deep AVR solvers have recently achieved remarkable success in various AVR tasks. However, they usually use task-specific designs or parameters in differ… ▽ More Abstract visual reasoning (AVR) enables humans to quickly discover and generalize abstract rules to new scenarios. Designing intelligent systems with human-like AVR abilities has been a long-standing topic in the artificial intelligence community. Deep AVR solvers have recently achieved remarkable success in various AVR tasks. However, they usually use task-specific designs or parameters in different tasks. In such a paradigm, solving new tasks often means retraining the model, and sometimes retuning the model architectures, which increases the cost of solving AVR problems. In contrast to task-specific approaches, this paper proposes a novel Unified Conditional Generative Solver (UCGS), aiming to address multiple AVR tasks in a unified framework. First, we prove that some well-known AVR tasks can be reformulated as the problem of estimating the predictability of target images in problem panels. Then, we illustrate that, under the proposed framework, training one conditional generative model can solve various AVR tasks. The experiments show that with a single round of multi-task training, UCGS demonstrates abstract reasoning ability across various AVR tasks. Especially, UCGS exhibits the ability of zero-shot reasoning, enabling it to perform abstract reasoning on problems from unseen AVR tasks in the testing phase. △ Less

Submitted 15 July, 2025; originally announced July 2025.

ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition

Authors: Ronggang Huang, Haoxin Yang, Yan Cai, Xuemiao Xu, Huaidong Zhang, Shengfeng He

Abstract: 3D visual grounding aims to identify and localize objects in a 3D space based on textual descriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolving inconsistencies in spatial descriptions caused by perspective variations. To tackle these challenges, we propose ViewSRD, a framework that formulates 3D visual grounding as a s… ▽ More 3D visual grounding aims to identify and localize objects in a 3D space based on textual descriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolving inconsistencies in spatial descriptions caused by perspective variations. To tackle these challenges, we propose ViewSRD, a framework that formulates 3D visual grounding as a structured multi-view decomposition process. First, the Simple Relation Decoupling (SRD) module restructures complex multi-anchor queries into a set of targeted single-anchor statements, generating a structured set of perspective-aware descriptions that clarify positional relationships. These decomposed representations serve as the foundation for the Multi-view Textual-Scene Interaction (Multi-TSI) module, which integrates textual and scene features across multiple viewpoints using shared, Cross-modal Consistent View Tokens (CCVTs) to preserve spatial correlations. Finally, a Textual-Scene Reasoning module synthesizes multi-view predictions into a unified and robust 3D visual grounding. Experiments on 3D visual grounding datasets show that ViewSRD significantly outperforms state-of-the-art methods, particularly in complex queries requiring precise spatial differentiation. △ Less

Submitted 15 July, 2025; originally announced July 2025.

Comments: Accepted by ICCV 2025

Transformer based Collaborative Reinforcement Learning for Fluid Antenna System (FAS)-enabled 3D UAV Positioning

Authors: Xiaoren Xu, Hao Xu, Dongyu Wei, Walid Saad, Mehdi Bennis, Mingzhe Chen

Abstract: In this paper, a novel Three dimensional (3D) positioning framework of fluid antenna system (FAS)-enabled unmanned aerial vehicles (UAVs) is developed. In the proposed framework, a set of controlled UAVs cooperatively estimate the real-time 3D position of a target UAV. Here, the active UAV transmits a measurement signal to the passive UAVs via the reflection from the target UAV. Each passive UAV e… ▽ More In this paper, a novel Three dimensional (3D) positioning framework of fluid antenna system (FAS)-enabled unmanned aerial vehicles (UAVs) is developed. In the proposed framework, a set of controlled UAVs cooperatively estimate the real-time 3D position of a target UAV. Here, the active UAV transmits a measurement signal to the passive UAVs via the reflection from the target UAV. Each passive UAV estimates the distance of the active-target-passive UAV link and selects an antenna port to share the distance information with the base station (BS) that calculates the real-time position of the target UAV. As the target UAV is moving due to its task operation, the controlled UAVs must optimize their trajectories and select optimal antenna port, aiming to estimate the real-time position of the target UAV. We formulate this problem as an optimization problem to minimize the target UAV positioning error via optimizing the trajectories of all controlled UAVs and antenna port selection of passive UAVs. Here, an attention-based recurrent multi-agent reinforcement learning (AR-MARL) scheme is proposed, which enables each controlled UAV to use the local Q function to determine its trajectory and antenna port while optimizing the target UAV positioning performance without knowing the trajectories and antenna port selections of other controlled UAVs. Different from current MARL methods, the proposed method uses a recurrent neural network (RNN) that incorporates historical state-action pairs of each controlled UAV, and an attention mechanism to analyze the importance of these historical state-action pairs, thus improving the global Q function approximation accuracy and the target UAV positioning accuracy. Simulation results show that the proposed AR-MARL scheme can reduce the average positioning error by up to 17.5% and 58.5% compared to the VD-MARL scheme and the proposed method without FAS. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation

Authors: Jialong Mai, Xiaofen Xing, Yawei Li, Zhipeng Li, Jingyuan Xing, Xiangmin Xu

Abstract: Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality severely limits the signal processing and understanding capabilities of SLLM. For example, a SLLM with a 4K context window can only process 80 seconds of audio at 50Hz feature sampling rate before reaching its capacity li… ▽ More Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality severely limits the signal processing and understanding capabilities of SLLM. For example, a SLLM with a 4K context window can only process 80 seconds of audio at 50Hz feature sampling rate before reaching its capacity limit. Input token compression methods used in SLLM overlook the continuity and inertia of emotions across multiple conversation turns. This paper proposes a Dynamic Parameter Memory (DPM) mechanism with contextual semantics and sentence-level emotion encoding, enabling processing of unlimited-length audio with limited context windows in SLLM. Specifically, DPM progressively encodes sentence-level information and emotions into a temporary LoRA module during inference to effectively "memorize" the contextual information. We trained an emotion SLLM as a backbone and incorporated our DPM into inference for emotion recognition in conversation (ERC). Experimental results on the IEMOCAP dataset show that DPM significantly improves the emotion recognition capabilities of SLLM when processing long audio sequences, achieving state-of-the-art performance. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Comments: submitted to EMNLP 2025

MSC Class: 68T50 ACM Class: I.2.7; H.5.2

DatasetAgent: A Novel Multi-Agent System for Auto-Constructing Datasets from Real-World Images

Authors: Haoran Sun, Haoyu Bian, Shaoning Zeng, Yunbo Rao, Xu Xu, Lin Mei, Jianping Gou

Abstract: Common knowledge indicates that the process of constructing image datasets usually depends on the time-intensive and inefficient method of manual collection and annotation. Large models offer a solution via data generation. Nonetheless, real-world data are obviously more valuable comparing to artificially intelligence generated data, particularly in constructing image datasets. For this reason, we… ▽ More Common knowledge indicates that the process of constructing image datasets usually depends on the time-intensive and inefficient method of manual collection and annotation. Large models offer a solution via data generation. Nonetheless, real-world data are obviously more valuable comparing to artificially intelligence generated data, particularly in constructing image datasets. For this reason, we propose a novel method for auto-constructing datasets from real-world images by a multiagent collaborative system, named as DatasetAgent. By coordinating four different agents equipped with Multi-modal Large Language Models (MLLMs), as well as a tool package for image optimization, DatasetAgent is able to construct high-quality image datasets according to user-specified requirements. In particular, two types of experiments are conducted, including expanding existing datasets and creating new ones from scratch, on a variety of open-source datasets. In both cases, multiple image datasets constructed by DatasetAgent are used to train various vision models for image classification, object detection, and image segmentation. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Towards AI-Native RAN: An Operator's Perspective of 6G Day 1 Standardization

Authors: Nan Li, Qi Sun, Lehan Wang, Xiaofei Xu, Jinri Huang, Chunhui Liu, Jing Gao, Yuhong Huang, Chih-Lin I

Abstract: Artificial Intelligence/Machine Learning (AI/ML) has become the most certain and prominent feature of 6G mobile networks. Unlike 5G, where AI/ML was not natively integrated but rather an add-on feature over existing architecture, 6G shall incorporate AI from the onset to address its complexity and support ubiquitous AI applications. Based on our extensive mobile network operation and standardizati… ▽ More Artificial Intelligence/Machine Learning (AI/ML) has become the most certain and prominent feature of 6G mobile networks. Unlike 5G, where AI/ML was not natively integrated but rather an add-on feature over existing architecture, 6G shall incorporate AI from the onset to address its complexity and support ubiquitous AI applications. Based on our extensive mobile network operation and standardization experience from 2G to 5G, this paper explores the design and standardization principles of AI-Native radio access networks (RAN) for 6G, with a particular focus on its critical Day 1 architecture, functionalities and capabilities. We investigate the framework of AI-Native RAN and present its three essential capabilities to shed some light on the standardization direction; namely, AI-driven RAN processing/optimization/automation, reliable AI lifecycle management (LCM), and AI-as-a-Service (AIaaS) provisioning. The standardization of AI-Native RAN, in particular the Day 1 features, including an AI-Native 6G RAN architecture, were proposed. For validation, a large-scale field trial with over 5000 5G-A base stations have been built and delivered significant improvements in average air interface latency, root cause identification, and network energy consumption with the proposed architecture and the supporting AI functions. This paper aims to provide a Day 1 framework for 6G AI-Native RAN standardization design, balancing technical innovation with practical deployment. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Optimizing Model Splitting and Device Task Assignment for Deceptive Signal Assisted Private Multi-hop Split Learning

Authors: Dongyu Wei, Xiaoren Xu, Yuchen Liu, H. Vincent Poor, Mingzhe Chen

Abstract: In this paper, deceptive signal-assisted private split learning is investigated. In our model, several edge devices jointly perform collaborative training, and some eavesdroppers aim to collect the model and data information from devices. To prevent the eavesdroppers from collecting model and data information, a subset of devices can transmit deceptive signals. Therefore, it is necessary to determ… ▽ More In this paper, deceptive signal-assisted private split learning is investigated. In our model, several edge devices jointly perform collaborative training, and some eavesdroppers aim to collect the model and data information from devices. To prevent the eavesdroppers from collecting model and data information, a subset of devices can transmit deceptive signals. Therefore, it is necessary to determine the subset of devices used for deceptive signal transmission, the subset of model training devices, and the models assigned to each model training device. This problem is formulated as an optimization problem whose goal is to minimize the information leaked to eavesdroppers while meeting the model training energy consumption and delay constraints. To solve this problem, we propose a soft actor-critic deep reinforcement learning framework with intrinsic curiosity module and cross-attention (ICM-CA) that enables a centralized agent to determine the model training devices, the deceptive signal transmission devices, the transmit power, and sub-models assigned to each model training device without knowing the position and monitoring probability of eavesdroppers. The proposed method uses an ICM module to encourage the server to explore novel actions and states and a CA module to determine the importance of each historical state-action pair thus improving training efficiency. Simulation results demonstrate that the proposed method improves the convergence rate by up to 3x and reduces the information leaked to eavesdroppers by up to 13% compared to the traditional SAC algorithm. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Optimizing Communication and Device Clustering for Clustered Federated Learning with Differential Privacy

Authors: Dongyu Wei, Xiaoren Xu, Shiwen Mao, Mingzhe Chen

Abstract: In this paper, a secure and communication-efficient clustered federated learning (CFL) design is proposed. In our model, several base stations (BSs) with heterogeneous task-handling capabilities and multiple users with non-independent and identically distributed (non-IID) data jointly perform CFL training incorporating differential privacy (DP) techniques. Since each BS can process only a subset o… ▽ More In this paper, a secure and communication-efficient clustered federated learning (CFL) design is proposed. In our model, several base stations (BSs) with heterogeneous task-handling capabilities and multiple users with non-independent and identically distributed (non-IID) data jointly perform CFL training incorporating differential privacy (DP) techniques. Since each BS can process only a subset of the learning tasks and has limited wireless resource blocks (RBs) to allocate to users for federated learning (FL) model parameter transmission, it is necessary to jointly optimize RB allocation and user scheduling for CFL performance optimization. Meanwhile, our considered CFL method requires devices to use their limited data and FL model information to determine their task identities, which may introduce additional communication overhead. We formulate an optimization problem whose goal is to minimize the training loss of all learning tasks while considering device clustering, RB allocation, DP noise, and FL model transmission delay. To solve the problem, we propose a novel dynamic penalty function assisted value decomposed multi-agent reinforcement learning (DPVD-MARL) algorithm that enables distributed BSs to independently determine their connected users, RBs, and DP noise of the connected users but jointly minimize the training loss of all learning tasks across all BSs. Different from the existing MARL methods that assign a large penalty for invalid actions, we propose a novel penalty assignment scheme that assigns penalty depending on the number of devices that cannot meet communication constraints (e.g., delay), which can guide the MARL scheme to quickly find valid actions, thus improving the convergence speed. Simulation results show that the DPVD-MARL can improve the convergence rate by up to 20% and the ultimate accumulated rewards by 15% compared to independent Q-learning. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery

Authors: Licong Xu, Milind Sarkar, Anto I. Lonappan, Íñigo Zubeldia, Pablo Villanueva-Domingo, Santiago Casas, Christian Fidler, Chetana Amancharla, Ujjwal Tiwari, Adrian Bayer, Chadi Ait Ekioui, Miles Cranmer, Adrian Dimitrov, James Fergusson, Kahaan Gandhi, Sven Krippendorf, Andrew Laverick, Julien Lesgourgues, Antony Lewis, Thomas Meier, Blake Sherwin, Kristen Surrao, Francisco Villaescusa-Navarro, Chi Wang, Xueqing Xu , et al. (1 additional authors not shown)

Abstract: We present a multi-agent system for automation of scientific research tasks, cmbagent (https://github.com/CMBAgents/cmbagent). The system is formed by about 30 Large Language Model (LLM) agents and implements a Planning & Control strategy to orchestrate the agentic workflow, with no human-in-the-loop at any point. Each agent specializes in a different task (performing retrieval on scientific paper… ▽ More We present a multi-agent system for automation of scientific research tasks, cmbagent (https://github.com/CMBAgents/cmbagent). The system is formed by about 30 Large Language Model (LLM) agents and implements a Planning & Control strategy to orchestrate the agentic workflow, with no human-in-the-loop at any point. Each agent specializes in a different task (performing retrieval on scientific papers and codebases, writing code, interpreting results, critiquing the output of other agents) and the system is able to execute code locally. We successfully apply cmbagent to carry out a PhD level cosmology task (the measurement of cosmological parameters using supernova data) and evaluate its performance on two benchmark sets, finding superior performance over state-of-the-art LLMs. The source code is available on GitHub, demonstration videos are also available, and the system is deployed on HuggingFace and will be available on the cloud. △ Less

Submitted 11 July, 2025; v1 submitted 9 July, 2025; originally announced July 2025.

Comments: Accepted contribution to the ICML 2025 Workshop on Machine Learning for Astrophysics. Code: https://github.com/CMBAgents/cmbagent Videos: https://www.youtube.com/@cmbagent HuggingFace: https://huggingface.co/spaces/astropilot-ai/cmbagent Cloud: https://cmbagent.cloud

Evaluating Retrieval-Augmented Generation Agents for Autonomous Scientific Discovery in Astrophysics

Authors: Xueqing Xu, Boris Bolliet, Adrian Dimitrov, Andrew Laverick, Francisco Villaescusa-Navarro, Licong Xu, Íñigo Zubeldia

Abstract: We evaluate 9 Retrieval Augmented Generation (RAG) agent configurations on 105 Cosmology Question-Answer (QA) pairs that we built specifically for this purpose.The RAG configurations are manually evaluated by a human expert, that is, a total of 945 generated answers were assessed. We find that currently the best RAG agent configuration is with OpenAI embedding and generative model, yielding 91.4\%… ▽ More We evaluate 9 Retrieval Augmented Generation (RAG) agent configurations on 105 Cosmology Question-Answer (QA) pairs that we built specifically for this purpose.The RAG configurations are manually evaluated by a human expert, that is, a total of 945 generated answers were assessed. We find that currently the best RAG agent configuration is with OpenAI embedding and generative model, yielding 91.4\% accuracy. Using our human evaluation results we calibrate LLM-as-a-Judge (LLMaaJ) system which can be used as a robust proxy for human evaluation. These results allow us to systematically select the best RAG agent configuration for multi-agent system for autonomous scientific discovery in astrophysics (e.g., cmbagent presented in a companion paper) and provide us with an LLMaaJ system that can be scaled to thousands of cosmology QA pairs. We make our QA dataset, human evaluation results, RAG pipelines, and LLMaaJ system publicly available for further use by the astrophysics community. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Comments: Accepted contribution (spotlight) to the ICML 2025 Workshop on Machine Learning for Astrophysics; codes: https://huggingface.co/datasets/ASTROANTS/CosmoPaperQA, https://github.com/CMBAgents/cmbagent, https://github.com/CMBAgents/scirag

A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding

Authors: Zhenyang Liu, Sixiao Zheng, Siyu Chen, Cairong Zhao, Longfei Liang, Xiangyang Xue, Yanwei Fu

Abstract: Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries, which is crucial for embodied AI applications such as autonomous navigation, robotics, and augmented reality. Learning 3D language fields through neural representations enables accurate understanding of 3D scenes from limited viewpoints and facilitates the localization of target objects in comp… ▽ More Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries, which is crucial for embodied AI applications such as autonomous navigation, robotics, and augmented reality. Learning 3D language fields through neural representations enables accurate understanding of 3D scenes from limited viewpoints and facilitates the localization of target objects in complex environments. However, existing language field methods struggle to accurately localize instances using spatial relations in language queries, such as ``the book on the chair.'' This limitation mainly arises from inadequate reasoning about spatial relations in both language queries and 3D scenes. In this work, we propose SpatialReasoner, a novel neural representation-based framework with large language model (LLM)-driven spatial reasoning that constructs a visual properties-enhanced hierarchical feature field for open-vocabulary 3D visual grounding. To enable spatial reasoning in language queries, SpatialReasoner fine-tunes an LLM to capture spatial relations and explicitly infer instructions for the target, anchor, and spatial relation. To enable spatial reasoning in 3D scenes, SpatialReasoner incorporates visual properties (opacity and color) to construct a hierarchical feature field. This field represents language and instance features using distilled CLIP features and masks extracted via the Segment Anything Model (SAM). The field is then queried using the inferred instructions in a hierarchical manner to localize the target 3D instance based on the spatial relation in the language query. Extensive experiments show that our framework can be seamlessly integrated into different neural representations, outperforming baseline models in 3D visual grounding while empowering their spatial reasoning capability. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Spatial-Temporal Aware Visuomotor Diffusion Policy Learning

Authors: Zhenyang Liu, Yikai Wang, Kuanning Wang, Longfei Liang, Xiangyang Xue, Yanwei Fu

Abstract: Visual imitation learning is effective for robots to learn versatile tasks. However, many existing methods rely on behavior cloning with supervised historical trajectories, limiting their 3D spatial and 4D spatiotemporal awareness. Consequently, these methods struggle to capture the 3D structures and 4D spatiotemporal relationships necessary for real-world deployment. In this work, we propose 4D D… ▽ More Visual imitation learning is effective for robots to learn versatile tasks. However, many existing methods rely on behavior cloning with supervised historical trajectories, limiting their 3D spatial and 4D spatiotemporal awareness. Consequently, these methods struggle to capture the 3D structures and 4D spatiotemporal relationships necessary for real-world deployment. In this work, we propose 4D Diffusion Policy (DP4), a novel visual imitation learning method that incorporates spatiotemporal awareness into diffusion-based policies. Unlike traditional approaches that rely on trajectory cloning, DP4 leverages a dynamic Gaussian world model to guide the learning of 3D spatial and 4D spatiotemporal perceptions from interactive environments. Our method constructs the current 3D scene from a single-view RGB-D observation and predicts the future 3D scene, optimizing trajectory generation by explicitly modeling both spatial and temporal dependencies. Extensive experiments across 17 simulation tasks with 173 variants and 3 real-world robotic tasks demonstrate that the 4D Diffusion Policy (DP4) outperforms baseline methods, improving the average simulation task success rate by 16.4% (Adroit), 14% (DexArt), and 6.45% (RLBench), and the average real-world robotic task success rate by 8.6%. △ Less

Submitted 13 July, 2025; v1 submitted 9 July, 2025; originally announced July 2025.

Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection

Authors: Yupeng Hu, Changxing Ding, Chang Sun, Shaoli Huang, Xiangmin Xu

Abstract: Open vocabulary Human-Object Interaction (HOI) detection is a challenging task that detects all <human, verb, object> triplets of interest in an image, even those that are not pre-defined in the training set. Existing approaches typically rely on output features generated by large Vision-Language Models (VLMs) to enhance the generalization ability of interaction representations. However, the visua… ▽ More Open vocabulary Human-Object Interaction (HOI) detection is a challenging task that detects all <human, verb, object> triplets of interest in an image, even those that are not pre-defined in the training set. Existing approaches typically rely on output features generated by large Vision-Language Models (VLMs) to enhance the generalization ability of interaction representations. However, the visual features produced by VLMs are holistic and coarse-grained, which contradicts the nature of detection tasks. To address this issue, we propose a novel Bilateral Collaboration framework for open vocabulary HOI detection (BC-HOI). This framework includes an Attention Bias Guidance (ABG) component, which guides the VLM to produce fine-grained instance-level interaction features according to the attention bias provided by the HOI detector. It also includes a Large Language Model (LLM)-based Supervision Guidance (LSG) component, which provides fine-grained token-level supervision for the HOI detector by the LLM component of the VLM. LSG enhances the ability of ABG to generate high-quality attention bias. We conduct extensive experiments on two popular benchmarks: HICO-DET and V-COCO, consistently achieving superior performance in the open vocabulary and closed settings. The code will be released in Github. △ Less

Submitted 8 July, 2025; originally announced July 2025.

Comments: ICCV 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

Beyond Retrieval: Ensembling Cross-Encoders and GPT Rerankers with LLMs for Biomedical QA

Authors: Shashank Verma, Fengyi Jiang, Xiangning Xue

Abstract: Biomedical semantic question answering rooted in information retrieval can play a crucial role in keeping up to date with vast, rapidly evolving and ever-growing biomedical literature. A robust system can help researchers, healthcare professionals and even layman users access relevant knowledge grounded in evidence. The BioASQ 2025 Task13b Challenge serves as an important benchmark, offering a com… ▽ More Biomedical semantic question answering rooted in information retrieval can play a crucial role in keeping up to date with vast, rapidly evolving and ever-growing biomedical literature. A robust system can help researchers, healthcare professionals and even layman users access relevant knowledge grounded in evidence. The BioASQ 2025 Task13b Challenge serves as an important benchmark, offering a competitive platform for advancement of this space. This paper presents the methodologies and results from our participation in this challenge where we built a Retrieval-Augmented Generation (RAG) system that can answer biomedical questions by retrieving relevant PubMed documents and snippets to generate answers. For the retrieval task, we generated dense embeddings from biomedical articles for initial retrieval, and applied an ensemble of finetuned cross-encoders and large language models (LLMs) for re-ranking to identify top relevant documents. Our solution achieved an MAP@10 of 0.1581, placing 10th on the leaderboard for the retrieval task. For answer generation, we employed few-shot prompting of instruction-tuned LLMs. Our system achieved macro-F1 score of 0.95 for yes/no questions (rank 12), Mean Reciprocal Rank (MRR) of 0.64 for factoid questions (rank 1), mean-F1 score of 0.63 for list questions (rank 5), and ROUGE-SU4 F1 score of 0.29 for ideal answers (rank 11). △ Less

Submitted 7 July, 2025; originally announced July 2025.

Comments: Paper submitted to CLEF 2025 CEUR-WS

Cross-Subject DD: A Cross-Subject Brain-Computer Interface Algorithm

Authors: Xiaoyuan Li, Xinru Xue, Bohan Zhang, Ye Sun, Shoushuo Xi, Gang Liu

Abstract: Brain-computer interface (BCI) based on motor imagery (MI) enables direct control of external devices by decoding the electroencephalogram (EEG) generated in the brain during imagined movements. However, due to inter-individual variability in brain activity, existing BCI models exhibit poor adaptability across subjects, thereby limiting their generalizability and widespread application. To address… ▽ More Brain-computer interface (BCI) based on motor imagery (MI) enables direct control of external devices by decoding the electroencephalogram (EEG) generated in the brain during imagined movements. However, due to inter-individual variability in brain activity, existing BCI models exhibit poor adaptability across subjects, thereby limiting their generalizability and widespread application. To address this issue, this paper proposes a cross-subject BCI algorithm named Cross-Subject DD (CSDD), which constructs a universal BCI model by extracting common features across subjects. The specific methods include: 1) training personalized models for each subject; 2) transforming personalized models into relation spectrums; 3) identifying common features through statistical analysis; and 4) constructing a cross-subject universal model based on common features. The experiments utilized the BCIC IV 2a dataset, involving nine subjects. Eight of these subjects were selected for training and extracing the common features, and the cross-subject decoding performance of the model was validated on the remaining subject. The results demonstrate that, compared with existing similar methods, our approach achieves a 3.28% improvement in performance. This paper introduces for the first time a novel method for extracting pure common features and constructing a universal cross-subject BCI model, thereby facilitating broader applications of BCI technology. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Comments: 20 pages, 9 figures

Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations

Authors: Xiang Xu, Lingdong Kong, Song Wang, Chuanwei Zhou, Qingshan Liu

Abstract: LiDAR representation learning aims to extract rich structural and semantic information from large-scale, readily available datasets, reducing reliance on costly human annotations. However, existing LiDAR representation strategies often overlook the inherent spatiotemporal cues in LiDAR sequences, limiting their effectiveness. In this work, we propose LiMA, a novel long-term image-to-LiDAR Memory A… ▽ More LiDAR representation learning aims to extract rich structural and semantic information from large-scale, readily available datasets, reducing reliance on costly human annotations. However, existing LiDAR representation strategies often overlook the inherent spatiotemporal cues in LiDAR sequences, limiting their effectiveness. In this work, we propose LiMA, a novel long-term image-to-LiDAR Memory Aggregation framework that explicitly captures longer range temporal correlations to enhance LiDAR representation learning. LiMA comprises three key components: 1) a Cross-View Aggregation module that aligns and fuses overlapping regions across neighboring camera views, constructing a more unified and redundancy-free memory bank; 2) a Long-Term Feature Propagation mechanism that efficiently aligns and integrates multi-frame image features, reinforcing temporal coherence during LiDAR representation learning; and 3) a Cross-Sequence Memory Alignment strategy that enforces consistency across driving sequences, improving generalization to unseen environments. LiMA maintains high pretraining efficiency and incurs no additional computational overhead during downstream tasks. Extensive experiments on mainstream LiDAR-based perception benchmarks demonstrate that LiMA significantly improves both LiDAR semantic segmentation and 3D object detection. We hope this work inspires more effective pretraining paradigms for autonomous driving. The code has be made publicly accessible for future research. △ Less

Submitted 7 July, 2025; originally announced July 2025.

Comments: ICCV 2025; 26 pages, 12 figures, 10 tables; Code at http://github.com/Xiangxu-0103/LiMA

CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step

Authors: Zheyuan Liu, Munan Ning, Qihui Zhang, Shuo Yang, Zhongrui Wang, Yiwei Yang, Xianzhe Xu, Yibing Song, Weihua Chen, Fan Wang, Li Yuan

Abstract: Current text-to-image (T2I) generation models struggle to align spatial composition with the input text, especially in complex scenes. Even layout-based approaches yield suboptimal spatial control, as their generation process is decoupled from layout planning, making it difficult to refine the layout during synthesis. We present CoT-Diff, a framework that brings step-by-step CoT-style reasoning in… ▽ More Current text-to-image (T2I) generation models struggle to align spatial composition with the input text, especially in complex scenes. Even layout-based approaches yield suboptimal spatial control, as their generation process is decoupled from layout planning, making it difficult to refine the layout during synthesis. We present CoT-Diff, a framework that brings step-by-step CoT-style reasoning into T2I generation by tightly integrating Multimodal Large Language Model (MLLM)-driven 3D layout planning with the diffusion process. CoT-Diff enables layout-aware reasoning inline within a single diffusion round: at each denoising step, the MLLM evaluates intermediate predictions, dynamically updates the 3D scene layout, and continuously guides the generation process. The updated layout is converted into semantic conditions and depth maps, which are fused into the diffusion model via a condition-aware attention mechanism, enabling precise spatial control and semantic injection. Experiments on 3D Scene benchmarks show that CoT-Diff significantly improves spatial alignment and compositional fidelity, and outperforms the state-of-the-art method by 34.7% in complex scene spatial accuracy, thereby validating the effectiveness of this entangled generation paradigm. △ Less

Submitted 6 July, 2025; originally announced July 2025.

Artificial intelligence in drug discovery: A comprehensive review with a case study on hyperuricemia, gout arthritis, and hyperuricemic nephropathy

Authors: Junwei Su, Cheng Xin, Ao Shang, Shan Wu, Zhenzhen Xie, Ruogu Xiong, Xiaoyu Xu, Cheng Zhang, Guang Chen, Yau-Tuen Chan, Guoyi Tang, Ning Wang, Yong Xu, Yibin Feng

Abstract: This paper systematically reviews recent advances in artificial intelligence (AI), with a particular focus on machine learning (ML), across the entire drug discovery pipeline. Due to the inherent complexity, escalating costs, prolonged timelines, and high failure rates of traditional drug discovery methods, there is a critical need to comprehensively understand how AI/ML can be effectively integra… ▽ More This paper systematically reviews recent advances in artificial intelligence (AI), with a particular focus on machine learning (ML), across the entire drug discovery pipeline. Due to the inherent complexity, escalating costs, prolonged timelines, and high failure rates of traditional drug discovery methods, there is a critical need to comprehensively understand how AI/ML can be effectively integrated throughout the full process. Currently available literature reviews often narrowly focus on specific phases or methodologies, neglecting the dependence between key stages such as target identification, hit screening, and lead optimization. To bridge this gap, our review provides a detailed and holistic analysis of AI/ML applications across these core phases, highlighting significant methodological advances and their impacts at each stage. We further illustrate the practical impact of these techniques through an in-depth case study focused on hyperuricemia, gout arthritis, and hyperuricemic nephropathy, highlighting real-world successes in molecular target identification and therapeutic candidate discovery. Additionally, we discuss significant challenges facing AI/ML in drug discovery and outline promising future research directions. Ultimately, this review serves as an essential orientation for researchers aiming to leverage AI/ML to overcome existing bottlenecks and accelerate drug discovery. △ Less

Submitted 4 July, 2025; originally announced July 2025.

CrowdTrack: A Benchmark for Difficult Multiple Pedestrian Tracking in Real Scenarios

Authors: Teng Fu, Yuwen Chen, Zhuofan Chen, Mengyang Zhao, Bin Li, Xiangyang Xue

Abstract: Multi-object tracking is a classic field in computer vision. Among them, pedestrian tracking has extremely high application value and has become the most popular research category. Existing methods mainly use motion or appearance information for tracking, which is often difficult in complex scenarios. For the motion information, mutual occlusions between objects often prevent updating of the motio… ▽ More Multi-object tracking is a classic field in computer vision. Among them, pedestrian tracking has extremely high application value and has become the most popular research category. Existing methods mainly use motion or appearance information for tracking, which is often difficult in complex scenarios. For the motion information, mutual occlusions between objects often prevent updating of the motion state; for the appearance information, non-robust results are often obtained due to reasons such as only partial visibility of the object or blurred images. Although learning how to perform tracking in these situations from the annotated data is the simplest solution, the existing MOT dataset fails to satisfy this solution. Existing methods mainly have two drawbacks: relatively simple scene composition and non-realistic scenarios. Although some of the video sequences in existing dataset do not have the above-mentioned drawbacks, the number is far from adequate for research purposes. To this end, we propose a difficult large-scale dataset for multi-pedestrian tracking, shot mainly from the first-person view and all from real-life complex scenarios. We name it ``CrowdTrack'' because there are numerous objects in most of the sequences. Our dataset consists of 33 videos, containing a total of 5,185 trajectories. Each object is annotated with a complete bounding box and a unique object ID. The dataset will provide a platform to facilitate the development of algorithms that remain effective in complex situations. We analyzed the dataset comprehensively and tested multiple SOTA models on our dataset. Besides, we analyzed the performance of the foundation models on our dataset. The dataset and project code is released at: https://github.com/loseevaya/CrowdTrack . △ Less

Submitted 3 July, 2025; originally announced July 2025.

UVLM: Benchmarking Video Language Model for Underwater World Understanding

Authors: Xizhe Xue, Yang Zhou, Dawei Yan, Ying Li, Haokui Zhang, Rong Xiao

Abstract: Recently, the remarkable success of large language models (LLMs) has achieved a profound impact on the field of artificial intelligence. Numerous advanced works based on LLMs have been proposed and applied in various scenarios. Among them, video language models (VidLMs) are particularly widely used. However, existing works primarily focus on terrestrial scenarios, overlooking the highly demanding… ▽ More Recently, the remarkable success of large language models (LLMs) has achieved a profound impact on the field of artificial intelligence. Numerous advanced works based on LLMs have been proposed and applied in various scenarios. Among them, video language models (VidLMs) are particularly widely used. However, existing works primarily focus on terrestrial scenarios, overlooking the highly demanding application needs of underwater observation. To overcome this gap, we introduce UVLM, an under water observation benchmark which is build through a collaborative approach combining human expertise and AI models. To ensure data quality, we have conducted in-depth considerations from multiple perspectives. First, to address the unique challenges of underwater environments, we selected videos that represent typical underwater challenges including light variations, water turbidity, and diverse viewing angles to construct the dataset. Second, to ensure data diversity, the dataset covers a wide range of frame rates, resolutions, 419 classes of marine animals, and various static plants and terrains. Next, for task diversity, we adopted a structured design where observation targets are categorized into two major classes: biological and environmental. Each category includes content observation and change/action observation, totaling 20 distinct task types. Finally, we designed several challenging evaluation metrics to enable quantitative comparison and analysis of different methods. Experiments on two representative VidLMs demonstrate that fine-tuning VidLMs on UVLM significantly improves underwater world understanding while also showing potential for slight improvements on existing in-air VidLM benchmarks, such as VideoMME and Perception text. The dataset and prompt engineering will be released publicly. △ Less

Submitted 3 July, 2025; originally announced July 2025.

Comments: 13 pages, 4 figures, 3 tables

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation

Authors: Lu Yan, Zhuo Zhang, Xiangzhe Xu, Shengwei An, Guangyu Shen, Zhou Xuan, Xuan Chen, Xiangyu Zhang

Abstract: Large language models (LLMs) have democratized software development, reducing the expertise barrier for programming complex applications. This accessibility extends to malicious software development, raising significant security concerns. While LLM providers have implemented alignment mechanisms to prevent direct generation of overtly malicious code, these safeguards predominantly evaluate individ… ▽ More Large language models (LLMs) have democratized software development, reducing the expertise barrier for programming complex applications. This accessibility extends to malicious software development, raising significant security concerns. While LLM providers have implemented alignment mechanisms to prevent direct generation of overtly malicious code, these safeguards predominantly evaluate individual prompts in isolation, overlooking a critical vulnerability: malicious operations can be systematically decomposed into benign-appearing sub-tasks. In this paper, we introduce the Malware Generation Compiler (MGC), a novel framework that leverages this vulnerability through modular decomposition and alignment-evasive generation. MGC employs a specialized Malware Description Intermediate Representation (MDIR) to bridge high-level malicious intents and benign-appearing code snippets. Extensive evaluation demonstrates that our attack reliably generates functional malware across diverse task specifications and categories, outperforming jailbreaking methods by +365.79% and underground services by +78.07% in correctness on three benchmark datasets. Case studies further show that MGC can reproduce and even enhance 16 real-world malware samples. This work provides critical insights for security researchers by exposing the risks of compositional attacks against aligned AI systems. Demonstrations are available at https://sites.google.com/view/malware-generation-compiler. △ Less

Submitted 2 July, 2025; originally announced July 2025.

RoboBrain 2.0 Technical Report

Authors: BAAI RoboBrain Team, Mingyu Cao, Huajie Tan, Yuheng Ji, Minglan Lin, Zhiyu Li, Zhou Cao, Pengwei Wang, Enshen Zhou, Yi Han, Yingbo Tang, Xiangqi Xu, Wei Guo, Yaoxu Lyu, Yijie Xu, Jiayu Shi, Mengfei Du, Cheng Chi, Mengdi Zhao, Xiaoshuai Hao, Junkai Zhao, Xiaojie Zhang, Shanyu Rong, Huaihai Lyu, Zhengliang Cai , et al. (27 additional authors not shown)

Abstract: We introduce RoboBrain 2.0, our latest generation of embodied vision-language foundation models, designed to unify perception, reasoning, and planning for complex embodied tasks in physical environments. It comes in two variants: a lightweight 7B model and a full-scale 32B model, featuring a heterogeneous architecture with a vision encoder and a language model. Despite its compact size, RoboBrain… ▽ More We introduce RoboBrain 2.0, our latest generation of embodied vision-language foundation models, designed to unify perception, reasoning, and planning for complex embodied tasks in physical environments. It comes in two variants: a lightweight 7B model and a full-scale 32B model, featuring a heterogeneous architecture with a vision encoder and a language model. Despite its compact size, RoboBrain 2.0 achieves strong performance across a wide spectrum of embodied reasoning tasks. On both spatial and temporal benchmarks, the 32B variant achieves leading results, surpassing prior open-source and proprietary models. In particular, it supports key real-world embodied AI capabilities, including spatial understanding (e.g., affordance prediction, spatial referring, trajectory forecasting) and temporal decision-making (e.g., closed-loop interaction, multi-agent long-horizon planning, and scene graph updating). This report details the model architecture, data construction, multi-stage training strategies, infrastructure and practical applications. We hope RoboBrain 2.0 advances embodied AI research and serves as a practical step toward building generalist embodied agents. The code, checkpoint and benchmark are available at https://superrobobrain.github.io. △ Less

Submitted 14 July, 2025; v1 submitted 2 July, 2025; originally announced July 2025.

BioMARS: A Multi-Agent Robotic System for Autonomous Biological Experiments

Authors: Yibo Qiu, Zan Huang, Zhiyu Wang, Handi Liu, Yiling Qiao, Yifeng Hu, Shu'ang Sun, Hangke Peng, Ronald X Xu, Mingzhai Sun

Abstract: Large language models (LLMs) and vision-language models (VLMs) have the potential to transform biological research by enabling autonomous experimentation. Yet, their application remains constrained by rigid protocol design, limited adaptability to dynamic lab conditions, inadequate error handling, and high operational complexity. Here we introduce BioMARS (Biological Multi-Agent Robotic System), a… ▽ More Large language models (LLMs) and vision-language models (VLMs) have the potential to transform biological research by enabling autonomous experimentation. Yet, their application remains constrained by rigid protocol design, limited adaptability to dynamic lab conditions, inadequate error handling, and high operational complexity. Here we introduce BioMARS (Biological Multi-Agent Robotic System), an intelligent platform that integrates LLMs, VLMs, and modular robotics to autonomously design, plan, and execute biological experiments. BioMARS uses a hierarchical architecture: the Biologist Agent synthesizes protocols via retrieval-augmented generation; the Technician Agent translates them into executable robotic pseudo-code; and the Inspector Agent ensures procedural integrity through multimodal perception and anomaly detection. The system autonomously conducts cell passaging and culture tasks, matching or exceeding manual performance in viability, consistency, and morphological integrity. It also supports context-aware optimization, outperforming conventional strategies in differentiating retinal pigment epithelial cells. A web interface enables real-time human-AI collaboration, while a modular backend allows scalable integration with laboratory hardware. These results highlight the feasibility of generalizable, AI-driven laboratory automation and the transformative role of language-based reasoning in biological research. △ Less

Submitted 2 July, 2025; originally announced July 2025.

TriVLA: A Triple-System-Based Unified Vision-Language-Action Model for General Robot Control

Authors: Zhenyang Liu, Yongchong Gu, Sixiao Zheng, Xiangyang Xue, Yanwei Fu

Abstract: Recent advancements in vision-language models (VLMs) for common-sense reasoning have led to the development of vision-language-action (VLA) models, enabling robots to perform generalized manipulation. Although existing autoregressive VLA methods design a specific architecture like dual-system to leverage large-scale pretrained knowledge, they tend to capture static information, often neglecting th… ▽ More Recent advancements in vision-language models (VLMs) for common-sense reasoning have led to the development of vision-language-action (VLA) models, enabling robots to perform generalized manipulation. Although existing autoregressive VLA methods design a specific architecture like dual-system to leverage large-scale pretrained knowledge, they tend to capture static information, often neglecting the dynamic aspects vital for embodied tasks. To this end, we propose TriVLA, a unified Vision-Language-Action model with a triple-system architecture for general robot control. The vision-language module (System 2) interprets the environment through vision and language instructions. The dynamics perception module (System 3) inherently produces visual representations that encompass both current static information and predicted future dynamics, thereby providing valuable guidance for policy learning. TriVLA utilizes pre-trained VLM model and fine-tunes pre-trained video foundation model on robot datasets along with internet human manipulation data. The subsequent policy learning module (System 1) generates fluid motor actions in real time. Experimental evaluation demonstrates that TriVLA operates at approximately 36 Hz and surpasses state-of-the-art imitation learning baselines on standard simulation benchmarks as well as challenging real-world manipulation tasks. △ Less

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

AI Agents and Agentic AI-Navigating a Plethora of Concepts for Future Manufacturing

Authors: Yinwang Ren, Yangyang Liu, Tang Ji, Xun Xu

Abstract: AI agents are autonomous systems designed to perceive, reason, and act within dynamic environments. With the rapid advancements in generative AI (GenAI), large language models (LLMs) and multimodal large language models (MLLMs) have significantly improved AI agents' capabilities in semantic comprehension, complex reasoning, and autonomous decision-making. At the same time, the rise of Agentic AI h… ▽ More AI agents are autonomous systems designed to perceive, reason, and act within dynamic environments. With the rapid advancements in generative AI (GenAI), large language models (LLMs) and multimodal large language models (MLLMs) have significantly improved AI agents' capabilities in semantic comprehension, complex reasoning, and autonomous decision-making. At the same time, the rise of Agentic AI highlights adaptability and goal-directed autonomy in dynamic and complex environments. LLMs-based AI Agents (LLM-Agents), MLLMs-based AI Agents (MLLM-Agents), and Agentic AI contribute to expanding AI's capabilities in information processing, environmental perception, and autonomous decision-making, opening new avenues for smart manufacturing. However, the definitions, capability boundaries, and practical applications of these emerging AI paradigms in smart manufacturing remain unclear. To address this gap, this study systematically reviews the evolution of AI and AI agent technologies, examines the core concepts and technological advancements of LLM-Agents, MLLM-Agents, and Agentic AI, and explores their potential applications in and integration into manufacturing, along with the potential challenges they may face. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Comments: Submitted to JMS(March 2025)

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

Authors: Maggie Huan, Yuetai Li, Tuney Zheng, Xiaoyu Xu, Seungone Kim, Minxin Du, Radha Poovendran, Graham Neubig, Xiang Yue

Abstract: Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting? To answer this question, we evaluate over 20 open-weight reasoning-tu… ▽ More Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting? To answer this question, we evaluate over 20 open-weight reasoning-tuned models across a broad suite of tasks, including math, scientific QA, agent planning, coding, and standard instruction-following. We surprisingly find that most models that succeed in math fail to transfer their gains to other domains. To rigorously study this phenomenon, we conduct controlled experiments on Qwen3-14B models using math-only data but different tuning methods. We find that reinforcement learning (RL)-tuned models generalize well across domains, while supervised fine-tuning (SFT)-tuned models often forget general capabilities. Latent-space representation and token-space distribution shift analyses reveal that SFT induces substantial representation and output drift, while RL preserves general-domain structure. Our results suggest a need to rethink standard post-training recipes, particularly the reliance on SFT-distilled data for advancing reasoning models. △ Less

Submitted 1 July, 2025; originally announced July 2025.

Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains

Authors: Xin Xu, Eibe Frank, Geoffrey Holmes

Abstract: We investigate cross-domain few-shot learning under the constraint that fine-tuning of backbones (i.e., feature extractors) is impossible or infeasible -- a scenario that is increasingly common in practical use cases. Handling the low-quality and static embeddings produced by frozen, "black-box" backbones leads to a problem representation of few-shot classification as a series of multiple instance… ▽ More We investigate cross-domain few-shot learning under the constraint that fine-tuning of backbones (i.e., feature extractors) is impossible or infeasible -- a scenario that is increasingly common in practical use cases. Handling the low-quality and static embeddings produced by frozen, "black-box" backbones leads to a problem representation of few-shot classification as a series of multiple instance verification (MIV) tasks. Inspired by this representation, we introduce a novel approach to few-shot domain adaptation, named the "MIV-head", akin to a classification head that is agnostic to any pretrained backbone and computationally efficient. The core components designed for the MIV-head, when trained on few-shot data from a target domain, collectively yield strong performance on test data from that domain. Importantly, it does so without fine-tuning the backbone, and within the "meta-testing" phase. Experimenting under various settings and on an extension of the Meta-dataset benchmark for cross-domain few-shot image classification, using representative off-the-shelf convolutional neural network and vision transformer backbones pretrained on ImageNet1K, we show that the MIV-head achieves highly competitive accuracy when compared to state-of-the-art "adapter" (or partially fine-tuning) methods applied to the same backbones, while incurring substantially lower adaptation cost. We also find well-known "classification head" approaches lag far behind in terms of accuracy. Ablation study empirically justifies the core components of our approach. We share our code at https://github.com/xxweka/MIV-head. △ Less

Submitted 30 June, 2025; originally announced July 2025.

Causal Prompting for Implicit Sentiment Analysis with Large Language Models

Authors: Jing Ren, Wenhao Zhou, Bowen Li, Mujie Liu, Nguyen Linh Dan Le, Jiade Cen, Liping Chen, Ziqi Xu, Xiwei Xu, Xiaodong Li

Abstract: Implicit Sentiment Analysis (ISA) aims to infer sentiment that is implied rather than explicitly stated, requiring models to perform deeper reasoning over subtle contextual cues. While recent prompting-based methods using Large Language Models (LLMs) have shown promise in ISA, they often rely on majority voting over chain-of-thought (CoT) reasoning paths without evaluating their causal validity, m… ▽ More Implicit Sentiment Analysis (ISA) aims to infer sentiment that is implied rather than explicitly stated, requiring models to perform deeper reasoning over subtle contextual cues. While recent prompting-based methods using Large Language Models (LLMs) have shown promise in ISA, they often rely on majority voting over chain-of-thought (CoT) reasoning paths without evaluating their causal validity, making them susceptible to internal biases and spurious correlations. To address this challenge, we propose CAPITAL, a causal prompting framework that incorporates front-door adjustment into CoT reasoning. CAPITAL decomposes the overall causal effect into two components: the influence of the input prompt on the reasoning chains, and the impact of those chains on the final output. These components are estimated using encoder-based clustering and the NWGM approximation, with a contrastive learning objective used to better align the encoder's representation with the LLM's reasoning space. Experiments on benchmark ISA datasets with three LLMs demonstrate that CAPITAL consistently outperforms strong prompting baselines in both accuracy and robustness, particularly under adversarial conditions. This work offers a principled approach to integrating causal inference into LLM prompting and highlights its benefits for bias-aware sentiment reasoning. The source code and case study are available at: https://github.com/whZ62/CAPITAL. △ Less

Submitted 30 June, 2025; originally announced July 2025.

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay

Authors: Xinrun Xu, Jianwen Yang, Qiuhong Zhang, Zhanbiao Lian, Zhiming Ding, Shan Jiang

Abstract: Continually adapting edge models in cloud-edge collaborative object detection for traffic monitoring suffers from catastrophic forgetting, where models lose previously learned knowledge when adapting to new data distributions. This is especially problematic in dynamic traffic environments characterised by periodic variations (e.g., day/night, peak hours), where past knowledge remains valuable. Exi… ▽ More Continually adapting edge models in cloud-edge collaborative object detection for traffic monitoring suffers from catastrophic forgetting, where models lose previously learned knowledge when adapting to new data distributions. This is especially problematic in dynamic traffic environments characterised by periodic variations (e.g., day/night, peak hours), where past knowledge remains valuable. Existing approaches like experience replay and visual prompts offer some mitigation, but struggle to effectively prioritize and leverage historical data for optimal knowledge retention and adaptation. Specifically, simply storing and replaying all historical data can be inefficient, while treating all historical experiences as equally important overlooks their varying relevance to the current domain. This paper proposes ER-EMU, an edge model update algorithm based on adaptive experience replay, to address these limitations. ER-EMU utilizes a limited-size experience buffer managed using a First-In-First-Out (FIFO) principle, and a novel Domain Distance Metric-based Experience Selection (DDM-ES) algorithm. DDM-ES employs the multi-kernel maximum mean discrepancy (MK-MMD) to quantify the dissimilarity between target domains, prioritizing the selection of historical data that is most dissimilar to the current target domain. This ensures training diversity and facilitates the retention of knowledge from a wider range of past experiences, while also preventing overfitting to the new domain. The experience buffer is also updated using a simple random sampling strategy to maintain a balanced representation of previous domains. Experiments on the Bellevue traffic video dataset, involving repeated day/night cycles, demonstrate that ER-EMU consistently improves the performance of several state-of-the-art cloud-edge collaborative object detection frameworks. △ Less

Submitted 23 June, 2025; originally announced July 2025.

Comments: ICANN 2025

Provably Efficient and Agile Randomized Q-Learning

Authors: He Wang, Xingyu Xu, Yuejie Chi

Abstract: While Bayesian-based exploration often demonstrates superior empirical performance compared to bonus-based methods in model-based reinforcement learning (RL), its theoretical understanding remains limited for model-free settings. Existing provable algorithms either suffer from computational intractability or rely on stage-wise policy updates which reduce responsiveness and slow down the learning p… ▽ More While Bayesian-based exploration often demonstrates superior empirical performance compared to bonus-based methods in model-based reinforcement learning (RL), its theoretical understanding remains limited for model-free settings. Existing provable algorithms either suffer from computational intractability or rely on stage-wise policy updates which reduce responsiveness and slow down the learning process. In this paper, we propose a novel variant of Q-learning algorithm, refereed to as RandomizedQ, which integrates sampling-based exploration with agile, step-wise, policy updates, for episodic tabular RL. We establish an $\widetilde{O}(\sqrt{H^5SAT})$ regret bound, where $S$ is the number of states, $A$ is the number of actions, $H$ is the episode length, and $T$ is the total number of episodes. In addition, we present a logarithmic regret bound under a mild positive sub-optimality condition on the optimal Q-function. Empirically, RandomizedQ exhibits outstanding performance compared to existing Q-learning variants with both bonus-based and Bayesian-based exploration on standard benchmarks. △ Less

Submitted 30 June, 2025; originally announced June 2025.

UltraTwin: Towards Cardiac Anatomical Twin Generation from Multi-view 2D Ultrasound

Authors: Junxuan Yu, Yaofei Duan, Yuhao Huang, Yu Wang, Rongbo Ling, Weihao Luo, Ang Zhang, Jingxian Xu, Qiongying Ni, Yongsong Zhou, Binghan Li, Haoran Dou, Liping Liu, Yanfen Chu, Feng Geng, Zhe Sheng, Zhifeng Ding, Dingxin Zhang, Rui Huang, Yuhang Zhang, Xiaowei Xu, Tao Tan, Dong Ni, Zhongshan Gou, Xin Yang

Abstract: Echocardiography is routine for cardiac examination. However, 2D ultrasound (US) struggles with accurate metric calculation and direct observation of 3D cardiac structures. Moreover, 3D US is limited by low resolution, small field of view and scarce availability in practice. Constructing the cardiac anatomical twin from 2D images is promising to provide precise treatment planning and clinical quan… ▽ More Echocardiography is routine for cardiac examination. However, 2D ultrasound (US) struggles with accurate metric calculation and direct observation of 3D cardiac structures. Moreover, 3D US is limited by low resolution, small field of view and scarce availability in practice. Constructing the cardiac anatomical twin from 2D images is promising to provide precise treatment planning and clinical quantification. However, it remains challenging due to the rare paired data, complex structures, and US noises. In this study, we introduce a novel generative framework UltraTwin, to obtain cardiac anatomical twin from sparse multi-view 2D US. Our contribution is three-fold. First, pioneered the construction of a real-world and high-quality dataset containing strictly paired multi-view 2D US and CT, and pseudo-paired data. Second, we propose a coarse-to-fine scheme to achieve hierarchical reconstruction optimization. Last, we introduce an implicit autoencoder for topology-aware constraints. Extensive experiments show that UltraTwin reconstructs high-quality anatomical twins versus strong competitors. We believe it advances anatomical twin modeling for potential applications in personalized cardiac care. △ Less

Submitted 29 June, 2025; originally announced June 2025.

Comments: accepted by miccai 2025