Showing 1–50 of 1,346 results for author: Xu, S

Estimating Rate-Distortion Functions Using the Energy-Based Model

Authors: Shitong Wu, Sicheng Xu, Lingyi Chen, Huihui Wu, Wenyi Zhang

Abstract: The rate-distortion (RD) theory is one of the key concepts in information theory, providing theoretical limits for compression performance and guiding the source coding design, with both theoretical and practical significance. The Blahut-Arimoto (BA) algorithm, as a classical algorithm to compute RD functions, encounters computational challenges when applied to high-dimensional scenarios. In recen… ▽ More The rate-distortion (RD) theory is one of the key concepts in information theory, providing theoretical limits for compression performance and guiding the source coding design, with both theoretical and practical significance. The Blahut-Arimoto (BA) algorithm, as a classical algorithm to compute RD functions, encounters computational challenges when applied to high-dimensional scenarios. In recent years, many neural methods have attempted to compute high-dimensional RD problems from the perspective of implicit generative models. Nevertheless, these approaches often neglect the reconstruction of the optimal conditional distribution or rely on unreasonable prior assumptions. In face of these issues, we propose an innovative energy-based modeling framework that leverages the connection between the RD dual form and the free energy in statistical physics, achieving effective reconstruction of the optimal conditional distribution.The proposed algorithm requires training only a single neural network and circumvents the challenge of computing the normalization factor in energy-based models using the Markov chain Monte Carlo (MCMC) sampling. Experimental results demonstrate the significant effectiveness of the proposed algorithm in estimating high-dimensional RD functions and reconstructing the optimal conditional distribution. △ Less

Submitted 21 July, 2025; originally announced July 2025.

Comments: 6 pages, 6 figures

One Step Beyond: Feedthrough & Placement-Aware Rectilinear Floorplanner

Authors: Zhexuan Xu, Jie Wang, Siyuan Xu, Zijie Geng, Mingxuan Yuan, Feng Wu

Abstract: Floorplanning determines the shapes and locations of modules on a chip canvas and plays a critical role in optimizing the chip's Power, Performance, and Area (PPA) metrics. However, existing floorplanning approaches often fail to integrate with subsequent physical design stages, leading to suboptimal in-module component placement and excessive inter-module feedthrough. To tackle this challenge, we… ▽ More Floorplanning determines the shapes and locations of modules on a chip canvas and plays a critical role in optimizing the chip's Power, Performance, and Area (PPA) metrics. However, existing floorplanning approaches often fail to integrate with subsequent physical design stages, leading to suboptimal in-module component placement and excessive inter-module feedthrough. To tackle this challenge, we propose Flora, a three-stage feedthrough and placement aware rectilinear floorplanner. In the first stage, Flora employs wiremask and position mask techniques to achieve coarse-grained optimization of HPWL and feedthrough. In the second stage, under the constraint of a fixed outline, Flora achieves a zero-whitespace layout by locally resizing module shapes, thereby performing fine-grained optimization of feedthrough and improving component placement. In the third stage, Flora utilizes a fast tree search-based method to efficiently place components-including macros and standard cells-within each module, subsequently adjusting module boundaries based on the placement results to enable cross-stage optimization. Experimental results show that Flora outperforms recent state-of-the-art floorplanning approaches, achieving an average reduction of 6% in HPWL, 5.16% in FTpin, 29.15% in FTmod, and a 14% improvement in component placement performance. △ Less

Submitted 20 July, 2025; originally announced July 2025.

MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization

Authors: Xingxuan Li, Yao Xiao, Dianwen Ng, Hai Ye, Yue Deng, Xiang Lin, Bin Wang, Zhanfeng Mo, Chong Zhang, Yueyi Zhang, Zonglin Yang, Ruilin Li, Lei Lei, Shihao Xu, Han Zhao, Weiling Chen, Feng Ji, Lidong Bing

Abstract: Large language models have recently evolved from fluent text generation to advanced reasoning across diverse domains, giving rise to reasoning language models. Among these domains, mathematical reasoning serves as a representative benchmark as it requires precise multi-step logic and abstract reasoning, which can be generalized to other tasks. While closed-source RLMs such as GPT-o3 demonstrate im… ▽ More Large language models have recently evolved from fluent text generation to advanced reasoning across diverse domains, giving rise to reasoning language models. Among these domains, mathematical reasoning serves as a representative benchmark as it requires precise multi-step logic and abstract reasoning, which can be generalized to other tasks. While closed-source RLMs such as GPT-o3 demonstrate impressive reasoning capabilities, their proprietary nature limits transparency and reproducibility. Although many open-source projects aim to close this gap, most of them lack sufficient openness by omitting critical resources such as datasets and detailed training configurations, which hinders reproducibility. To contribute toward greater transparency in RLM development, we introduce the MiroMind-M1 series, a set of fully open-source RLMs built on the Qwen-2.5 backbone that match or exceed the performance of existing open-source RLMs. Specifically, our models are trained in two stages: SFT on a carefully curated corpus of 719K math-reasoning problems with verified CoT trajectories, followed by RLVR on 62K challenging and verifiable problems. To enhance the robustness and efficiency of the RLVR process, we introduce Context-Aware Multi-Stage Policy Optimization, an algorithm that integrates length-progressive training with an adaptive repetition penalty to encourage context-aware RL training. Our model achieves state-of-the-art or competitive performance and superior token efficiency among Qwen-2.5-based open-source 7B and 32B models on the AIME24, AIME25, and MATH benchmarks. To facilitate reproducibility, we release the complete stack: models (MiroMind-M1-SFT-7B, MiroMind-M1-RL-7B, MiroMind-M1-RL-32B); datasets (MiroMind-M1-SFT-719K, MiroMind-M1-RL-62K); and all training and evaluation configurations. We hope these resources will support further research and foster community advancement. △ Less

Submitted 19 July, 2025; originally announced July 2025.

Comments: Technical report

Traffic Signal Phase and Timing Estimation with Large-Scale Floating Car Data

Authors: Mingcheng Liao, Zebang Feng, Miao Fan, Shengtong Xu, Haoyi Xiong

Abstract: Effective modern transportation systems depend critically on accurate Signal Phase and Timing (SPaT) estimation. However, acquiring ground-truth SPaT information faces significant hurdles due to communication challenges with transportation departments and signal installers. As a result, Floating Car Data (FCD) has become the primary source for large-scale SPaT analyses. Current FCD approaches ofte… ▽ More Effective modern transportation systems depend critically on accurate Signal Phase and Timing (SPaT) estimation. However, acquiring ground-truth SPaT information faces significant hurdles due to communication challenges with transportation departments and signal installers. As a result, Floating Car Data (FCD) has become the primary source for large-scale SPaT analyses. Current FCD approaches often simplify the problem by assuming fixed schedules and basic intersection designs for specific times and locations. These methods fail to account for periodic signal changes, diverse intersection structures, and the inherent limitations of real-world data, thus lacking a comprehensive framework that is universally applicable. Addressing this limitation, we propose an industrial-grade FCD analysis suite that manages the entire process, from initial data preprocessing to final SPaT estimation. Our approach estimates signal phases, identifies time-of-day (TOD) periods, and determines the durations of red and green lights. The framework's notable stability and robustness across diverse conditions, regardless of road geometry, is a key feature. Furthermore, we provide a cleaned, de-identified FCD dataset and supporting parameters to facilitate future research. Currently operational within our navigation platform, the system analyses over 15 million FCD records daily, supporting over two million traffic signals in mainland China, with more than 75\% of estimations demonstrating less than five seconds of error. △ Less

Submitted 13 July, 2025; originally announced July 2025.

Comments: Accepted by ITSC'25

DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration

Authors: Xiyun Li, Yining Ding, Yuhua Jiang, Yunlong Zhao, Runpeng Xie, Shuang Xu, Yuanhua Ni, Yiqin Yang, Bo Xu

Abstract: Real-time human-artificial intelligence (AI) collaboration is crucial yet challenging, especially when AI agents must adapt to diverse and unseen human behaviors in dynamic scenarios. Existing large language model (LLM) agents often fail to accurately model the complex human mental characteristics such as domain intentions, especially in the absence of direct communication. To address this limitat… ▽ More Real-time human-artificial intelligence (AI) collaboration is crucial yet challenging, especially when AI agents must adapt to diverse and unseen human behaviors in dynamic scenarios. Existing large language model (LLM) agents often fail to accurately model the complex human mental characteristics such as domain intentions, especially in the absence of direct communication. To address this limitation, we propose a novel dual process multi-scale theory of mind (DPMT) framework, drawing inspiration from cognitive science dual process theory. Our DPMT framework incorporates a multi-scale theory of mind (ToM) module to facilitate robust human partner modeling through mental characteristic reasoning. Experimental results demonstrate that DPMT significantly enhances human-AI collaboration, and ablation studies further validate the contributions of our multi-scale ToM in the slow system. △ Less

Submitted 18 July, 2025; originally announced July 2025.

Journal ref: cogsci-2025

Apple Intelligence Foundation Language Models: Tech Report 2025

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

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

Submitted 17 July, 2025; originally announced July 2025.

Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion

Authors: Caixia Dong, Duwei Dai, Xinyi Han, Fan Liu, Xu Yang, Zongfang Li, Songhua Xu

Abstract: Accurate coronary artery segmentation is critical for computeraided diagnosis of coronary artery disease (CAD), yet it remains challenging due to the small size, complex morphology, and low contrast with surrounding tissues. To address these challenges, we propose a novel segmentation framework that leverages the power of vision foundation models (VFMs) through a parallel encoding architecture. Sp… ▽ More Accurate coronary artery segmentation is critical for computeraided diagnosis of coronary artery disease (CAD), yet it remains challenging due to the small size, complex morphology, and low contrast with surrounding tissues. To address these challenges, we propose a novel segmentation framework that leverages the power of vision foundation models (VFMs) through a parallel encoding architecture. Specifically, a vision transformer (ViT) encoder within the VFM captures global structural features, enhanced by the activation of the final two ViT blocks and the integration of an attention-guided enhancement (AGE) module, while a convolutional neural network (CNN) encoder extracts local details. These complementary features are adaptively fused using a cross-branch variational fusion (CVF) module, which models latent distributions and applies variational attention to assign modality-specific weights. Additionally, we introduce an evidential-learning uncertainty refinement (EUR) module, which quantifies uncertainty using evidence theory and refines uncertain regions by incorporating multi-scale feature aggregation and attention mechanisms, further enhancing segmentation accuracy. Extensive evaluations on one in-house and two public datasets demonstrate that the proposed framework significantly outperforms state-of-the-art methods, achieving superior performance in accurate coronary artery segmentation and showcasing strong generalization across multiple datasets. The code is available at https://github.com/d1c2x3/CAseg. △ Less

Submitted 17 July, 2025; originally announced July 2025.

Journal ref: MICCAI2025

Making Language Model a Hierarchical Classifier and Generator

Authors: Yihong Wang, Zhonglin Jiang, Ningyuan Xi, Yue Zhao, Qingqing Gu, Xiyuan Chen, Hao Wu, Sheng Xu, Hange Zhou, Yong Chen, Luo Ji

Abstract: Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers decoding texts simultaneously. Due to limited time and computationally resources, we choose to adapt a pretrained language model into this form of hierarchical decoder… ▽ More Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers decoding texts simultaneously. Due to limited time and computationally resources, we choose to adapt a pretrained language model into this form of hierarchical decoder. Language heads of the last layer are copied to different selected intermediate layers, and fine-tuned with different task inputs. By thorough experiments, we validate that these selective intermediate layers could be adapted to speak meaningful and reasonable contents, and this paradigm of hierarchical decoder can obtain state-of-the-art performances on multiple tasks such as hierarchical text classification, classification-guided generation, and hierarchical text generation. This study suggests the possibility of a generalized hierarchical reasoner, pretraining from scratch. △ Less

Submitted 17 July, 2025; originally announced July 2025.

3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering

Authors: Rongtao Xu, Han Gao, Mingming Yu, Dong An, Shunpeng Chen, Changwei Wang, Li Guo, Xiaodan Liang, Shibiao Xu

Abstract: With the growing need for diverse and scalable data in indoor scene tasks, such as question answering and dense captioning, we propose 3D-MoRe, a novel paradigm designed to generate large-scale 3D-language datasets by leveraging the strengths of foundational models. The framework integrates key components, including multi-modal embedding, cross-modal interaction, and a language model decoder, to p… ▽ More With the growing need for diverse and scalable data in indoor scene tasks, such as question answering and dense captioning, we propose 3D-MoRe, a novel paradigm designed to generate large-scale 3D-language datasets by leveraging the strengths of foundational models. The framework integrates key components, including multi-modal embedding, cross-modal interaction, and a language model decoder, to process natural language instructions and 3D scene data. This approach facilitates enhanced reasoning and response generation in complex 3D environments. Using the ScanNet 3D scene dataset, along with text annotations from ScanQA and ScanRefer, 3D-MoRe generates 62,000 question-answer (QA) pairs and 73,000 object descriptions across 1,513 scenes. We also employ various data augmentation techniques and implement semantic filtering to ensure high-quality data. Experiments on ScanQA demonstrate that 3D-MoRe significantly outperforms state-of-the-art baselines, with the CIDEr score improving by 2.15\%. Similarly, on ScanRefer, our approach achieves a notable increase in CIDEr@0.5 by 1.84\%, highlighting its effectiveness in both tasks. Our code and generated datasets will be publicly released to benefit the community, and both can be accessed on the https://3D-MoRe.github.io. △ Less

Submitted 16 July, 2025; originally announced July 2025.

Comments: Accepted by IROS 2025

MOSPA: Human Motion Generation Driven by Spatial Audio

Authors: Shuyang Xu, Zhiyang Dou, Mingyi Shi, Liang Pan, Leo Ho, Jingbo Wang, Yuan Liu, Cheng Lin, Yuexin Ma, Wenping Wang, Taku Komura

Abstract: Enabling virtual humans to dynamically and realistically respond to diverse auditory stimuli remains a key challenge in character animation, demanding the integration of perceptual modeling and motion synthesis. Despite its significance, this task remains largely unexplored. Most previous works have primarily focused on mapping modalities like speech, audio, and music to generate human motion. As… ▽ More Enabling virtual humans to dynamically and realistically respond to diverse auditory stimuli remains a key challenge in character animation, demanding the integration of perceptual modeling and motion synthesis. Despite its significance, this task remains largely unexplored. Most previous works have primarily focused on mapping modalities like speech, audio, and music to generate human motion. As of yet, these models typically overlook the impact of spatial features encoded in spatial audio signals on human motion. To bridge this gap and enable high-quality modeling of human movements in response to spatial audio, we introduce the first comprehensive Spatial Audio-Driven Human Motion (SAM) dataset, which contains diverse and high-quality spatial audio and motion data. For benchmarking, we develop a simple yet effective diffusion-based generative framework for human MOtion generation driven by SPatial Audio, termed MOSPA, which faithfully captures the relationship between body motion and spatial audio through an effective fusion mechanism. Once trained, MOSPA could generate diverse realistic human motions conditioned on varying spatial audio inputs. We perform a thorough investigation of the proposed dataset and conduct extensive experiments for benchmarking, where our method achieves state-of-the-art performance on this task. Our model and dataset will be open-sourced upon acceptance. Please refer to our supplementary video for more details. △ Less

Submitted 16 July, 2025; originally announced July 2025.

Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update

Authors: Yu-Jie Zhang, Sheng-An Xu, Peng Zhao, Masashi Sugiyama

Abstract: We study the generalized linear bandit (GLB) problem, a contextual multi-armed bandit framework that extends the classical linear model by incorporating a non-linear link function, thereby modeling a broad class of reward distributions such as Bernoulli and Poisson. While GLBs are widely applicable to real-world scenarios, their non-linear nature introduces significant challenges in achieving both… ▽ More We study the generalized linear bandit (GLB) problem, a contextual multi-armed bandit framework that extends the classical linear model by incorporating a non-linear link function, thereby modeling a broad class of reward distributions such as Bernoulli and Poisson. While GLBs are widely applicable to real-world scenarios, their non-linear nature introduces significant challenges in achieving both computational and statistical efficiency. Existing methods typically trade off between two objectives, either incurring high per-round costs for optimal regret guarantees or compromising statistical efficiency to enable constant-time updates. In this paper, we propose a jointly efficient algorithm that attains a nearly optimal regret bound with $\mathcal{O}(1)$ time and space complexities per round. The core of our method is a tight confidence set for the online mirror descent (OMD) estimator, which is derived through a novel analysis that leverages the notion of mix loss from online prediction. The analysis shows that our OMD estimator, even with its one-pass updates, achieves statistical efficiency comparable to maximum likelihood estimation, thereby leading to a jointly efficient optimistic method. △ Less

Submitted 15 July, 2025; originally announced July 2025.

Space Cybersecurity Testbed: Fidelity Framework, Example Implementation, and Characterization

Authors: Jose Luis Castanon Remy, Caleb Chang, Ekzhin Ear, Shouhuai Xu

Abstract: Cyber threats against space infrastructures, including satellites and systems on the ground, have not been adequately understood. Testbeds are important to deepen our understanding and validate space cybersecurity studies. The state of the art is that there are very few studies on building testbeds, and there are few characterizations of testbeds. In this paper, we propose a framework for characte… ▽ More Cyber threats against space infrastructures, including satellites and systems on the ground, have not been adequately understood. Testbeds are important to deepen our understanding and validate space cybersecurity studies. The state of the art is that there are very few studies on building testbeds, and there are few characterizations of testbeds. In this paper, we propose a framework for characterizing the fidelity of space cybersecurity testbeds. The framework includes 7 attributes for characterizing the system models, threat models, and defenses that can be accommodated by a testbed. We use the framework to guide us in building and characterizing a concrete testbed we have implemented, which includes space, ground, user, and link segments. In particular, we show how the testbed can accommodate some space cyber attack scenarios that have occurred in the real world, and discuss future research directions. △ Less

Submitted 15 July, 2025; originally announced July 2025.

Journal ref: Workshop on Security of Space and Satellite Systems (SpaceSec) 2025, 24 February 2025, San Diego, CA, USA

Player-Team Heterogeneous Interaction Graph Transformer for Soccer Outcome Prediction

Authors: Lintao Wang, Shiwen Xu, Michael Horton, Joachim Gudmundsson, Zhiyong Wang

Abstract: Predicting soccer match outcomes is a challenging task due to the inherently unpredictable nature of the game and the numerous dynamic factors influencing results. While it conventionally relies on meticulous feature engineering, deep learning techniques have recently shown a great promise in learning effective player and team representations directly for soccer outcome prediction. However, existi… ▽ More Predicting soccer match outcomes is a challenging task due to the inherently unpredictable nature of the game and the numerous dynamic factors influencing results. While it conventionally relies on meticulous feature engineering, deep learning techniques have recently shown a great promise in learning effective player and team representations directly for soccer outcome prediction. However, existing methods often overlook the heterogeneous nature of interactions among players and teams, which is crucial for accurately modeling match dynamics. To address this gap, we propose HIGFormer (Heterogeneous Interaction Graph Transformer), a novel graph-augmented transformer-based deep learning model for soccer outcome prediction. HIGFormer introduces a multi-level interaction framework that captures both fine-grained player dynamics and high-level team interactions. Specifically, it comprises (1) a Player Interaction Network, which encodes player performance through heterogeneous interaction graphs, combining local graph convolutions with a global graph-augmented transformer; (2) a Team Interaction Network, which constructs interaction graphs from a team-to-team perspective to model historical match relationships; and (3) a Match Comparison Transformer, which jointly analyzes both team and player-level information to predict match outcomes. Extensive experiments on the WyScout Open Access Dataset, a large-scale real-world soccer dataset, demonstrate that HIGFormer significantly outperforms existing methods in prediction accuracy. Furthermore, we provide valuable insights into leveraging our model for player performance evaluation, offering a new perspective on talent scouting and team strategy analysis. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Branch Explorer: Leveraging Branching Narratives to Support Interactive 360° Video Viewing for Blind and Low Vision Users

Authors: Shuchang Xu, Xiaofu Jin, Wenshuo Zhang, Huamin Qu, Yukang Yan

Abstract: 360° videos enable users to freely choose their viewing paths, but blind and low vision (BLV) users are often excluded from this interactive experience. To bridge this gap, we present Branch Explorer, a system that transforms 360° videos into branching narratives -- stories that dynamically unfold based on viewer choices -- to support interactive viewing for BLV audiences. Our formative study iden… ▽ More 360° videos enable users to freely choose their viewing paths, but blind and low vision (BLV) users are often excluded from this interactive experience. To bridge this gap, we present Branch Explorer, a system that transforms 360° videos into branching narratives -- stories that dynamically unfold based on viewer choices -- to support interactive viewing for BLV audiences. Our formative study identified three key considerations for accessible branching narratives: providing diverse branch options, ensuring coherent story progression, and enabling immersive navigation among branches. To address these needs, Branch Explorer employs a multi-modal machine learning pipeline to generate diverse narrative paths, allowing users to flexibly make choices at detected branching points and seamlessly engage with each storyline through immersive audio guidance. Evaluation with 12 BLV viewers showed that Branch Explorer significantly enhanced user agency and engagement in 360° video viewing. Users also developed personalized strategies for exploring 360° content. We further highlight implications for supporting accessible exploration of videos and virtual environments. △ Less

Submitted 14 July, 2025; originally announced July 2025.

Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline

Authors: Shiyi Mu, Zichong Gu, Hanqi Lyu, Yilin Gao, Shugong Xu

Abstract: 3D detection technology is widely used in the field of autonomous driving, with its application scenarios gradually expanding from enclosed highways to open conventional roads. For rare anomaly categories that appear on the road, 3D detection models trained on closed sets often misdetect or fail to detect anomaly objects. To address this risk, it is necessary to enhance the generalization ability… ▽ More 3D detection technology is widely used in the field of autonomous driving, with its application scenarios gradually expanding from enclosed highways to open conventional roads. For rare anomaly categories that appear on the road, 3D detection models trained on closed sets often misdetect or fail to detect anomaly objects. To address this risk, it is necessary to enhance the generalization ability of 3D detection models for targets of arbitrary shapes and to possess the capability to filter out anomalies. The generalization of 3D detection is limited by two factors: the coupled training of 2D and 3D, and the insufficient diversity in the scale distribution of training samples. This paper proposes a Stereo-based 3D Anomaly object Detection (S3AD) algorithm, which decouples the training strategy of 3D and 2D to release the generalization ability for arbitrary 3D foreground detection, and proposes an anomaly scoring algorithm based on foreground confidence prediction, achieving target-level anomaly scoring. In order to further verify and enhance the generalization of anomaly detection, we use a 3D rendering method to synthesize two augmented reality binocular stereo 3D detection datasets which named KITTI-AR. KITTI-AR extends upon KITTI by adding 97 new categories, totaling 6k pairs of stereo images. The KITTI-AR-ExD subset includes 39 common categories as extra training data to address the sparse sample distribution issue. Additionally, 58 rare categories form the KITTI-AR-OoD subset, which are not used in training to simulate zero-shot scenarios in real-world settings, solely for evaluating 3D anomaly detection. Finally, the performance of the algorithm and the dataset is verified in the experiments. (Code and dataset can be obtained at https://github.com/xxxx/xxx). △ Less

Submitted 12 July, 2025; originally announced July 2025.

Comments: under review

Multimodal HD Mapping for Intersections by Intelligent Roadside Units

Authors: Zhongzhang Chen, Miao Fan, Shengtong Xu, Mengmeng Yang, Kun Jiang, Xiangzeng Liu, Haoyi Xiong

Abstract: High-definition (HD) semantic mapping of complex intersections poses significant challenges for traditional vehicle-based approaches due to occlusions and limited perspectives. This paper introduces a novel camera-LiDAR fusion framework that leverages elevated intelligent roadside units (IRUs). Additionally, we present RS-seq, a comprehensive dataset developed through the systematic enhancement an… ▽ More High-definition (HD) semantic mapping of complex intersections poses significant challenges for traditional vehicle-based approaches due to occlusions and limited perspectives. This paper introduces a novel camera-LiDAR fusion framework that leverages elevated intelligent roadside units (IRUs). Additionally, we present RS-seq, a comprehensive dataset developed through the systematic enhancement and annotation of the V2X-Seq dataset. RS-seq includes precisely labelled camera imagery and LiDAR point clouds collected from roadside installations, along with vectorized maps for seven intersections annotated with detailed features such as lane dividers, pedestrian crossings, and stop lines. This dataset facilitates the systematic investigation of cross-modal complementarity for HD map generation using IRU data. The proposed fusion framework employs a two-stage process that integrates modality-specific feature extraction and cross-modal semantic integration, capitalizing on camera high-resolution texture and precise geometric data from LiDAR. Quantitative evaluations using the RS-seq dataset demonstrate that our multimodal approach consistently surpasses unimodal methods. Specifically, compared to unimodal baselines evaluated on the RS-seq dataset, the multimodal approach improves the mean Intersection-over-Union (mIoU) for semantic segmentation by 4\% over the image-only results and 18\% over the point cloud-only results. This study establishes a baseline methodology for IRU-based HD semantic mapping and provides a valuable dataset for future research in infrastructure-assisted autonomous driving systems. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Comments: Accepted by ITSC'25

End-to-End Generation of City-Scale Vectorized Maps by Crowdsourced Vehicles

Authors: Zebang Feng, Miao Fan, Bao Liu, Shengtong Xu, Haoyi Xiong

Abstract: High-precision vectorized maps are indispensable for autonomous driving, yet traditional LiDAR-based creation is costly and slow, while single-vehicle perception methods lack accuracy and robustness, particularly in adverse conditions. This paper introduces EGC-VMAP, an end-to-end framework that overcomes these limitations by generating accurate, city-scale vectorized maps through the aggregation… ▽ More High-precision vectorized maps are indispensable for autonomous driving, yet traditional LiDAR-based creation is costly and slow, while single-vehicle perception methods lack accuracy and robustness, particularly in adverse conditions. This paper introduces EGC-VMAP, an end-to-end framework that overcomes these limitations by generating accurate, city-scale vectorized maps through the aggregation of data from crowdsourced vehicles. Unlike prior approaches, EGC-VMAP directly fuses multi-vehicle, multi-temporal map elements perceived onboard vehicles using a novel Trip-Aware Transformer architecture within a unified learning process. Combined with hierarchical matching for efficient training and a multi-objective loss, our method significantly enhances map accuracy and structural robustness compared to single-vehicle baselines. Validated on a large-scale, multi-city real-world dataset, EGC-VMAP demonstrates superior performance, enabling a scalable, cost-effective solution for city-wide mapping with a reported 90\% reduction in manual annotation costs. △ Less

Submitted 11 July, 2025; originally announced July 2025.

Comments: Accepted by ITSC'25

Unreal is all you need: Multimodal ISAC Data Simulation with Only One Engine

Authors: Kongwu Huang, Shiyi Mu, Jun Jiang, Yuan Gao, Shugong Xu

Abstract: Scaling laws have achieved success in LLM and foundation models. To explore their potential in ISAC research, we propose Great-X. This single-engine multimodal data twin platform reconstructs the ray-tracing computation of Sionna within Unreal Engine and is deeply integrated with autonomous driving tools. This enables efficient and synchronized simulation of multimodal data, including CSI, RGB, Ra… ▽ More Scaling laws have achieved success in LLM and foundation models. To explore their potential in ISAC research, we propose Great-X. This single-engine multimodal data twin platform reconstructs the ray-tracing computation of Sionna within Unreal Engine and is deeply integrated with autonomous driving tools. This enables efficient and synchronized simulation of multimodal data, including CSI, RGB, Radar, and LiDAR. Based on this platform, we construct an open-source, large-scale, low-altitude UAV multimodal synaesthesia dataset named Great-MSD, and propose a baseline CSI-based UAV 3D localization algorithm, demonstrating its feasibility and generalizability across different CSI simulation engines. The related code and dataset will be made available at: https://github.com/hkw-xg/Great-MCD. △ Less

Submitted 22 July, 2025; v1 submitted 11 July, 2025; originally announced July 2025.

Temporal Motif Participation Profiles for Analyzing Node Similarity in Temporal Networks

Authors: Maxwell C. Lee, Kevin S. Xu

Abstract: Temporal networks consisting of timestamped interactions between a set of nodes provide a useful representation for analyzing complex networked systems that evolve over time. Beyond pairwise interactions between nodes, temporal motifs capture patterns of higher-order interactions such as directed triangles over short time periods. We propose temporal motif participation profiles (TMPPs) to capture… ▽ More Temporal networks consisting of timestamped interactions between a set of nodes provide a useful representation for analyzing complex networked systems that evolve over time. Beyond pairwise interactions between nodes, temporal motifs capture patterns of higher-order interactions such as directed triangles over short time periods. We propose temporal motif participation profiles (TMPPs) to capture the behavior of nodes in temporal motifs. Two nodes with similar TMPPs take similar positions within temporal motifs, possibly with different nodes. TMPPs serve as unsupervised embeddings for nodes in temporal networks that are directly interpretable, as each entry denotes the frequency at which a node participates in a particular position in a specific temporal motif. We demonstrate that clustering TMPPs reveals groups of nodes with similar roles in a temporal network through simulation experiments and a case study on a network of militarized interstate disputes. △ Less

Submitted 8 July, 2025; originally announced July 2025.

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

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

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

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

Comments: 72 pages, 17 figures

MedGemma Technical Report

Authors: Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri, Atilla Kiraly, Madeleine Traverse, Timo Kohlberger, Shawn Xu, Fayaz Jamil, Cían Hughes, Charles Lau, Justin Chen, Fereshteh Mahvar, Liron Yatziv, Tiffany Chen, Bram Sterling, Stefanie Anna Baby, Susanna Maria Baby, Jeremy Lai, Samuel Schmidgall, Lu Yang, Kejia Chen, Per Bjornsson, Shashir Reddy, Ryan Brush, Kenneth Philbrick , et al. (56 additional authors not shown)

Abstract: Artificial intelligence (AI) has significant potential in healthcare applications, but its training and deployment faces challenges due to healthcare's diverse data, complex tasks, and the need to preserve privacy. Foundation models that perform well on medical tasks and require less task-specific tuning data are critical to accelerate the development of healthcare AI applications. We introduce Me… ▽ More Artificial intelligence (AI) has significant potential in healthcare applications, but its training and deployment faces challenges due to healthcare's diverse data, complex tasks, and the need to preserve privacy. Foundation models that perform well on medical tasks and require less task-specific tuning data are critical to accelerate the development of healthcare AI applications. We introduce MedGemma, a collection of medical vision-language foundation models based on Gemma 3 4B and 27B. MedGemma demonstrates advanced medical understanding and reasoning on images and text, significantly exceeding the performance of similar-sized generative models and approaching the performance of task-specific models, while maintaining the general capabilities of the Gemma 3 base models. For out-of-distribution tasks, MedGemma achieves 2.6-10% improvement on medical multimodal question answering, 15.5-18.1% improvement on chest X-ray finding classification, and 10.8% improvement on agentic evaluations compared to the base models. Fine-tuning MedGemma further improves performance in subdomains, reducing errors in electronic health record information retrieval by 50% and reaching comparable performance to existing specialized state-of-the-art methods for pneumothorax classification and histopathology patch classification. We additionally introduce MedSigLIP, a medically-tuned vision encoder derived from SigLIP. MedSigLIP powers the visual understanding capabilities of MedGemma and as an encoder achieves comparable or better performance than specialized medical image encoders. Taken together, the MedGemma collection provides a strong foundation of medical image and text capabilities, with potential to significantly accelerate medical research and development of downstream applications. The MedGemma collection, including tutorials and model weights, can be found at https://goo.gle/medgemma. △ Less

Submitted 12 July, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Colorectal Cancer Tumor Grade Segmentation in Digital Histopathology Images: From Giga to Mini Challenge

Authors: Alper Bahcekapili, Duygu Arslan, Umut Ozdemir, Berkay Ozkirli, Emre Akbas, Ahmet Acar, Gozde B. Akar, Bingdou He, Shuoyu Xu, Umit Mert Caglar, Alptekin Temizel, Guillaume Picaud, Marc Chaumont, Gérard Subsol, Luc Téot, Fahad Alsharekh, Shahad Alghannam, Hexiang Mao, Wenhua Zhang

Abstract: Colorectal cancer (CRC) is the third most diagnosed cancer and the second leading cause of cancer-related death worldwide. Accurate histopathological grading of CRC is essential for prognosis and treatment planning but remains a subjective process prone to observer variability and limited by global shortages of trained pathologists. To promote automated and standardized solutions, we organized the… ▽ More Colorectal cancer (CRC) is the third most diagnosed cancer and the second leading cause of cancer-related death worldwide. Accurate histopathological grading of CRC is essential for prognosis and treatment planning but remains a subjective process prone to observer variability and limited by global shortages of trained pathologists. To promote automated and standardized solutions, we organized the ICIP Grand Challenge on Colorectal Cancer Tumor Grading and Segmentation using the publicly available METU CCTGS dataset. The dataset comprises 103 whole-slide images with expert pixel-level annotations for five tissue classes. Participants submitted segmentation masks via Codalab, evaluated using metrics such as macro F-score and mIoU. Among 39 participating teams, six outperformed the Swin Transformer baseline (62.92 F-score). This paper presents an overview of the challenge, dataset, and the top-performing methods △ Less

Submitted 12 July, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: Accepted Grand Challenge Paper ICIP 2025

Breaking Imitation Bottlenecks: Reinforced Diffusion Powers Diverse Trajectory Generation

Authors: Ziying Song, Lin Liu, Hongyu Pan, Bencheng Liao, Mingzhe Guo, Lei Yang, Yongchang Zhang, Shaoqing Xu, Caiyan Jia, Yadan Luo

Abstract: Most end-to-end autonomous driving methods rely on imitation learning from single expert demonstrations, often leading to conservative and homogeneous behaviors that limit generalization in complex real-world scenarios. In this work, we propose DIVER, an end-to-end driving framework that integrates reinforcement learning with diffusion-based generation to produce diverse and feasible trajectories.… ▽ More Most end-to-end autonomous driving methods rely on imitation learning from single expert demonstrations, often leading to conservative and homogeneous behaviors that limit generalization in complex real-world scenarios. In this work, we propose DIVER, an end-to-end driving framework that integrates reinforcement learning with diffusion-based generation to produce diverse and feasible trajectories. At the core of DIVER lies a reinforced diffusion-based generation mechanism. First, the model conditions on map elements and surrounding agents to generate multiple reference trajectories from a single ground-truth trajectory, alleviating the limitations of imitation learning that arise from relying solely on single expert demonstrations. Second, reinforcement learning is employed to guide the diffusion process, where reward-based supervision enforces safety and diversity constraints on the generated trajectories, thereby enhancing their practicality and generalization capability. Furthermore, to address the limitations of L2-based open-loop metrics in capturing trajectory diversity, we propose a novel Diversity metric to evaluate the diversity of multi-mode predictions.Extensive experiments on the closed-loop NAVSIM and Bench2Drive benchmarks, as well as the open-loop nuScenes dataset, demonstrate that DIVER significantly improves trajectory diversity, effectively addressing the mode collapse problem inherent in imitation learning. △ Less

Submitted 5 July, 2025; originally announced July 2025.

Comments: 16 pages, 6 figures

Bridging Vision and Language: Optimal Transport-Driven Radiology Report Generation via LLMs

Authors: Haifeng Zhao, Yufei Zhang, Leilei Ma, Shuo Xu, Dengdi Sun

Abstract: Radiology report generation represents a significant application within medical AI, and has achieved impressive results. Concurrently, large language models (LLMs) have demonstrated remarkable performance across various domains. However, empirical validation indicates that general LLMs tend to focus more on linguistic fluency rather than clinical effectiveness, and lack the ability to effectively… ▽ More Radiology report generation represents a significant application within medical AI, and has achieved impressive results. Concurrently, large language models (LLMs) have demonstrated remarkable performance across various domains. However, empirical validation indicates that general LLMs tend to focus more on linguistic fluency rather than clinical effectiveness, and lack the ability to effectively capture the relationship between X-ray images and their corresponding texts, thus resulting in poor clinical practicability. To address these challenges, we propose Optimal Transport-Driven Radiology Report Generation (OTDRG), a novel framework that leverages Optimal Transport (OT) to align image features with disease labels extracted from reports, effectively bridging the cross-modal gap. The core component of OTDRG is Alignment \& Fine-Tuning, where OT utilizes results from the encoding of label features and image visual features to minimize cross-modal distances, then integrating image and text features for LLMs fine-tuning. Additionally, we design a novel disease prediction module to predict disease labels contained in X-ray images during validation and testing. Evaluated on the MIMIC-CXR and IU X-Ray datasets, OTDRG achieves state-of-the-art performance in both natural language generation (NLG) and clinical efficacy (CE) metrics, delivering reports that are not only linguistically coherent but also clinically accurate. △ Less

Submitted 5 July, 2025; originally announced July 2025.

Causal-SAM-LLM: Large Language Models as Causal Reasoners for Robust Medical Segmentation

Authors: Tao Tang, Shijie Xu, Yiting Wu, Zhixiang Lu

Abstract: The clinical utility of deep learning models for medical image segmentation is severely constrained by their inability to generalize to unseen domains. This failure is often rooted in the models learning spurious correlations between anatomical content and domain-specific imaging styles. To overcome this fundamental challenge, we introduce Causal-SAM-LLM, a novel framework that elevates Large Lang… ▽ More The clinical utility of deep learning models for medical image segmentation is severely constrained by their inability to generalize to unseen domains. This failure is often rooted in the models learning spurious correlations between anatomical content and domain-specific imaging styles. To overcome this fundamental challenge, we introduce Causal-SAM-LLM, a novel framework that elevates Large Language Models (LLMs) to the role of causal reasoners. Our framework, built upon a frozen Segment Anything Model (SAM) encoder, incorporates two synergistic innovations. First, Linguistic Adversarial Disentanglement (LAD) employs a Vision-Language Model to generate rich, textual descriptions of confounding image styles. By training the segmentation model's features to be contrastively dissimilar to these style descriptions, it learns a representation robustly purged of non-causal information. Second, Test-Time Causal Intervention (TCI) provides an interactive mechanism where an LLM interprets a clinician's natural language command to modulate the segmentation decoder's features in real-time, enabling targeted error correction. We conduct an extensive empirical evaluation on a composite benchmark from four public datasets (BTCV, CHAOS, AMOS, BraTS), assessing generalization under cross-scanner, cross-modality, and cross-anatomy settings. Causal-SAM-LLM establishes a new state of the art in out-of-distribution (OOD) robustness, improving the average Dice score by up to 6.2 points and reducing the Hausdorff Distance by 15.8 mm over the strongest baseline, all while using less than 9% of the full model's trainable parameters. Our work charts a new course for building robust, efficient, and interactively controllable medical AI systems. △ Less

Submitted 4 July, 2025; originally announced July 2025.

Learning to Generate Vectorized Maps at Intersections with Multiple Roadside Cameras

Authors: Quanxin Zheng, Miao Fan, Shengtong Xu, Linghe Kong, Haoyi Xiong

Abstract: Vectorized maps are indispensable for precise navigation and the safe operation of autonomous vehicles. Traditional methods for constructing these maps fall into two categories: offline techniques, which rely on expensive, labor-intensive LiDAR data collection and manual annotation, and online approaches that use onboard cameras to reduce costs but suffer from limited performance, especially at co… ▽ More Vectorized maps are indispensable for precise navigation and the safe operation of autonomous vehicles. Traditional methods for constructing these maps fall into two categories: offline techniques, which rely on expensive, labor-intensive LiDAR data collection and manual annotation, and online approaches that use onboard cameras to reduce costs but suffer from limited performance, especially at complex intersections. To bridge this gap, we introduce MRC-VMap, a cost-effective, vision-centric, end-to-end neural network designed to generate high-definition vectorized maps directly at intersections. Leveraging existing roadside surveillance cameras, MRC-VMap directly converts time-aligned, multi-directional images into vectorized map representations. This integrated solution lowers the need for additional intermediate modules--such as separate feature extraction and Bird's-Eye View (BEV) conversion steps--thus reducing both computational overhead and error propagation. Moreover, the use of multiple camera views enhances mapping completeness, mitigates occlusions, and provides robust performance under practical deployment constraints. Extensive experiments conducted on 4,000 intersections across 4 major metropolitan areas in China demonstrate that MRC-VMap not only outperforms state-of-the-art online methods but also achieves accuracy comparable to high-cost LiDAR-based approaches, thereby offering a scalable and efficient solution for modern autonomous navigation systems. △ Less

Submitted 11 July, 2025; v1 submitted 23 June, 2025; originally announced July 2025.

Comments: Accepted by IROS'25

MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details

Authors: Ruicheng Wang, Sicheng Xu, Yue Dong, Yu Deng, Jianfeng Xiang, Zelong Lv, Guangzhong Sun, Xin Tong, Jiaolong Yang

Abstract: We propose MoGe-2, an advanced open-domain geometry estimation model that recovers a metric scale 3D point map of a scene from a single image. Our method builds upon the recent monocular geometry estimation approach, MoGe, which predicts affine-invariant point maps with unknown scales. We explore effective strategies to extend MoGe for metric geometry prediction without compromising the relative g… ▽ More We propose MoGe-2, an advanced open-domain geometry estimation model that recovers a metric scale 3D point map of a scene from a single image. Our method builds upon the recent monocular geometry estimation approach, MoGe, which predicts affine-invariant point maps with unknown scales. We explore effective strategies to extend MoGe for metric geometry prediction without compromising the relative geometry accuracy provided by the affine-invariant point representation. Additionally, we discover that noise and errors in real data diminish fine-grained detail in the predicted geometry. We address this by developing a unified data refinement approach that filters and completes real data from different sources using sharp synthetic labels, significantly enhancing the granularity of the reconstructed geometry while maintaining the overall accuracy. We train our model on a large corpus of mixed datasets and conducted comprehensive evaluations, demonstrating its superior performance in achieving accurate relative geometry, precise metric scale, and fine-grained detail recovery -- capabilities that no previous methods have simultaneously achieved. △ Less

Submitted 3 July, 2025; originally announced July 2025.

Comments: Project page: https://wangrc.site/MoGe2Page/

ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving

Authors: Kai Chen, Ruiyuan Gao, Lanqing Hong, Hang Xu, Xu Jia, Holger Caesar, Dengxin Dai, Bingbing Liu, Dzmitry Tsishkou, Songcen Xu, Chunjing Xu, Qiang Xu, Huchuan Lu, Dit-Yan Yeung

Abstract: In this paper, we present details of the 1st W-CODA workshop, held in conjunction with the ECCV 2024. W-CODA aims to explore next-generation solutions for autonomous driving corner cases, empowered by state-of-the-art multimodal perception and comprehension techniques. 5 Speakers from both academia and industry are invited to share their latest progress and opinions. We collect research papers and… ▽ More In this paper, we present details of the 1st W-CODA workshop, held in conjunction with the ECCV 2024. W-CODA aims to explore next-generation solutions for autonomous driving corner cases, empowered by state-of-the-art multimodal perception and comprehension techniques. 5 Speakers from both academia and industry are invited to share their latest progress and opinions. We collect research papers and hold a dual-track challenge, including both corner case scene understanding and generation. As the pioneering effort, we will continuously bridge the gap between frontier autonomous driving techniques and fully intelligent, reliable self-driving agents robust towards corner cases. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Comments: ECCV 2024. Workshop page: https://coda-dataset.github.io/w-coda2024/

When Less Is More: Binary Feedback Can Outperform Ordinal Comparisons in Ranking Recovery

Authors: Shirong Xu, Jingnan Zhang, Junhui Wang

Abstract: Paired comparison data, where users evaluate items in pairs, play a central role in ranking and preference learning tasks. While ordinal comparison data intuitively offer richer information than binary comparisons, this paper challenges that conventional wisdom. We propose a general parametric framework for modeling ordinal paired comparisons without ties. The model adopts a generalized additive s… ▽ More Paired comparison data, where users evaluate items in pairs, play a central role in ranking and preference learning tasks. While ordinal comparison data intuitively offer richer information than binary comparisons, this paper challenges that conventional wisdom. We propose a general parametric framework for modeling ordinal paired comparisons without ties. The model adopts a generalized additive structure, featuring a link function that quantifies the preference difference between two items and a pattern function that governs the distribution over ordinal response levels. This framework encompasses classical binary comparison models as special cases, by treating binary responses as binarized versions of ordinal data. Within this framework, we show that binarizing ordinal data can significantly improve the accuracy of ranking recovery. Specifically, we prove that under the counting algorithm, the ranking error associated with binary comparisons exhibits a faster exponential convergence rate than that of ordinal data. Furthermore, we characterize a substantial performance gap between binary and ordinal data in terms of a signal-to-noise ratio (SNR) determined by the pattern function. We identify the pattern function that minimizes the SNR and maximizes the benefit of binarization. Extensive simulations and a real application on the MovieLens dataset further corroborate our theoretical findings. △ Less

Submitted 2 July, 2025; originally announced July 2025.

GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Authors: GLM-V Team, :, Wenyi Hong, Wenmeng Yu, Xiaotao Gu, Guo Wang, Guobing Gan, Haomiao Tang, Jiale Cheng, Ji Qi, Junhui Ji, Lihang Pan, Shuaiqi Duan, Weihan Wang, Yan Wang, Yean Cheng, Zehai He, Zhe Su, Zhen Yang, Ziyang Pan, Aohan Zeng, Baoxu Wang, Boyan Shi, Changyu Pang, Chenhui Zhang , et al. (54 additional authors not shown)

Abstract: We present GLM-4.1V-Thinking, a vision-language model (VLM) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the fi… ▽ More We present GLM-4.1V-Thinking, a vision-language model (VLM) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document understanding. We open-source GLM-4.1V-9B-Thinking, which achieves state-of-the-art performance among models of comparable size. In a comprehensive evaluation across 28 public benchmarks, our model outperforms Qwen2.5-VL-7B on nearly all tasks and achieves comparable or even superior performance on 18 benchmarks relative to the significantly larger Qwen2.5-VL-72B. Notably, GLM-4.1V-9B-Thinking also demonstrates competitive or superior performance compared to closed-source models such as GPT-4o on challenging tasks including long document understanding and STEM reasoning, further underscoring its strong capabilities. Code, models and more information are released at https://github.com/THUDM/GLM-4.1V-Thinking. △ Less

Submitted 2 July, 2025; v1 submitted 1 July, 2025; originally announced July 2025.

DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World

Authors: Xiangtai Li, Tao Zhang, Yanwei Li, Haobo Yuan, Shihao Chen, Yikang Zhou, Jiahao Meng, Yueyi Sun, Shilin Xu, Lu Qi, Tianheng Cheng, Yi Lin, Zilong Huang, Wenhao Huang, Jiashi Feng, Guang Shi

Abstract: Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack the ground locations and relations for visual entities. Several grounded caption datasets face the problems of missing detailed descriptions, relations, and massive object descriptions on high-resolution images. To fill t… ▽ More Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack the ground locations and relations for visual entities. Several grounded caption datasets face the problems of missing detailed descriptions, relations, and massive object descriptions on high-resolution images. To fill this gap for the community, we present DenseWorld-1M, the first massive, detailed, dense grounded caption dataset in the real world. We design a three-stage labeling pipeline, containing open-world perception, detailed object caption generation, and dense caption merging. The first stage obtains entity-level masks and labels. The second stage generates the object-level, detailed captions with the guidance of masks and labels from the first stage. The final stage merges object captions and masks into spatial and relational dense captions. To accelerate the labeling process and improve caption quality, we present two VLM models: the Detailed Region Caption model and the Spatial Caption Merging model. Extensive experiments on various settings, including vision-language understanding, visual grounding, and region caption generation, demonstrate the effectiveness of our DenseWorld-1M dataset and labeling models. △ Less

Submitted 30 June, 2025; originally announced June 2025.

Comments: Datasets and Models: https://github.com/lxtGH/DenseWorld-1M

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

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

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

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

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

SDRNET: Stacked Deep Residual Network for Accurate Semantic Segmentation of Fine-Resolution Remotely Sensed Images

Authors: Naftaly Wambugu, Ruisheng Wang, Bo Guo, Tianshu Yu, Sheng Xu, Mohammed Elhassan

Abstract: Land cover maps generated from semantic segmentation of high-resolution remotely sensed images have drawn mucon in the photogrammetry and remote sensing research community. Currently, massive fine-resolution remotely sensed (FRRS) images acquired by improving sensing and imaging technologies become available. However, accurate semantic segmentation of such FRRS images is greatly affected by substa… ▽ More Land cover maps generated from semantic segmentation of high-resolution remotely sensed images have drawn mucon in the photogrammetry and remote sensing research community. Currently, massive fine-resolution remotely sensed (FRRS) images acquired by improving sensing and imaging technologies become available. However, accurate semantic segmentation of such FRRS images is greatly affected by substantial class disparities, the invisibility of key ground objects due to occlusion, and object size variation. Despite the extraordinary potential in deep convolutional neural networks (DCNNs) in image feature learning and representation, extracting sufficient features from FRRS images for accurate semantic segmentation is still challenging. These challenges demand the deep learning models to learn robust features and generate sufficient feature descriptors. Specifically, learning multi-contextual features to guarantee adequate coverage of varied object sizes from the ground scene and harnessing global-local contexts to overcome class disparities challenge even profound networks. Deeper networks significantly lose spatial details due to gradual downsampling processes resulting in poor segmentation results and coarse boundaries. This article presents a stacked deep residual network (SDRNet) for semantic segmentation from FRRS images. The proposed framework utilizes two stacked encoder-decoder networks to harness long-range semantics yet preserve spatial information and dilated residual blocks (DRB) between each encoder and decoder network to capture sufficient global dependencies thus improving segmentation performance. Our experimental results obtained using the ISPRS Vaihingen and Potsdam datasets demonstrate that the SDRNet performs effectively and competitively against current DCNNs in semantic segmentation. △ Less

Submitted 27 June, 2025; originally announced June 2025.

CURL-SLAM: Continuous and Compact LiDAR Mapping

Authors: Kaicheng Zhang, Shida Xu, Yining Ding, Xianwen Kong, Sen Wang

Abstract: This paper studies 3D LiDAR mapping with a focus on developing an updatable and localizable map representation that enables continuity, compactness and consistency in 3D maps. Traditional LiDAR Simultaneous Localization and Mapping (SLAM) systems often rely on 3D point cloud maps, which typically require extensive storage to preserve structural details in large-scale environments. In this paper, w… ▽ More This paper studies 3D LiDAR mapping with a focus on developing an updatable and localizable map representation that enables continuity, compactness and consistency in 3D maps. Traditional LiDAR Simultaneous Localization and Mapping (SLAM) systems often rely on 3D point cloud maps, which typically require extensive storage to preserve structural details in large-scale environments. In this paper, we propose a novel paradigm for LiDAR SLAM by leveraging the Continuous and Ultra-compact Representation of LiDAR (CURL) introduced in [1]. Our proposed LiDAR mapping approach, CURL-SLAM, produces compact 3D maps capable of continuous reconstruction at variable densities using CURL's spherical harmonics implicit encoding, and achieves global map consistency after loop closure. Unlike popular Iterative Closest Point (ICP)-based LiDAR odometry techniques, CURL-SLAM formulates LiDAR pose estimation as a unique optimization problem tailored for CURL and extends it to local Bundle Adjustment (BA), enabling simultaneous pose refinement and map correction. Experimental results demonstrate that CURL-SLAM achieves state-of-the-art 3D mapping quality and competitive LiDAR trajectory accuracy, delivering sensor-rate real-time performance (10 Hz) on a CPU. We will release the CURL-SLAM implementation to the community. △ Less

Submitted 26 June, 2025; originally announced June 2025.

Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search

Authors: Zhigong Zhou, Ning Ding, Xiaochuan Fan, Yue Shang, Yiming Qiu, Jingwei Zhuo, Zhiwei Ge, Songlin Wang, Lin Liu, Sulong Xu, Han Zhang

Abstract: Semantic retrieval, which retrieves semantically matched items given a textual query, has been an essential component to enhance system effectiveness in e-commerce search. In this paper, we study the multimodal retrieval problem, where the visual information (e.g, image) of item is leveraged as supplementary of textual information to enrich item representation and further improve retrieval perform… ▽ More Semantic retrieval, which retrieves semantically matched items given a textual query, has been an essential component to enhance system effectiveness in e-commerce search. In this paper, we study the multimodal retrieval problem, where the visual information (e.g, image) of item is leveraged as supplementary of textual information to enrich item representation and further improve retrieval performance. Though learning from cross-modality data has been studied extensively in tasks such as visual question answering or media summarization, multimodal retrieval remains a non-trivial and unsolved problem especially in the asymmetric scenario where the query is unimodal while the item is multimodal. In this paper, we propose a novel model named SMAR, which stands for Semantic-enhanced Modality-Asymmetric Retrieval, to tackle the problem of modality fusion and alignment in this kind of asymmetric scenario. Extensive experimental results on an industrial dataset show that the proposed model outperforms baseline models significantly in retrieval accuracy. We have open sourced our industrial dataset for the sake of reproducibility and future research works. △ Less

Submitted 25 June, 2025; originally announced June 2025.

Comments: published in sigir2023

Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture

Authors: Shuchen Xue, Tianyu Xie, Tianyang Hu, Zijin Feng, Jiacheng Sun, Kenji Kawaguchi, Zhenguo Li, Zhi-Ming Ma

Abstract: Large language models (LLMs) predominantly use autoregressive (AR) approaches, but masked diffusion models (MDMs) are emerging as viable alternatives. A key challenge in comparing AR and MDM paradigms is their typical architectural difference: AR models are often decoder-only, while MDMs have largely been encoder-only. This practice of changing both the modeling paradigm and architecture simultane… ▽ More Large language models (LLMs) predominantly use autoregressive (AR) approaches, but masked diffusion models (MDMs) are emerging as viable alternatives. A key challenge in comparing AR and MDM paradigms is their typical architectural difference: AR models are often decoder-only, while MDMs have largely been encoder-only. This practice of changing both the modeling paradigm and architecture simultaneously makes direct comparisons unfair, as it's hard to distinguish whether observed differences stem from the paradigm itself or the architectural shift. This research evaluates MDMs within a decoder-only framework to: (1) equitably compare MDM (as Any-Order AR, or AO-AR) and standard AR paradigms. Our investigation suggests that the standard AO-AR objective, which averages over all token permutations, may benefit from refinement, as many permutations appear less informative compared to the language's inherent left-to-right structure. (2) Investigate architectural influences (decoder-only vs. encoder-only) within MDMs. We demonstrate that while encoder-only MDMs model a simpler conditional probability space, decoder-only MDMs can achieve dramatic generation speedups ($\sim25\times$) and comparable perplexity with temperature annealing despite modeling a vastly larger space, highlighting key trade-offs. This work thus decouples core paradigm differences from architectural influences, offering insights for future model design. Code is available at https://github.com/scxue/AO-GPT-MDM. △ Less

Submitted 24 June, 2025; originally announced June 2025.

STIMULUS: Achieving Fast Convergence and Low Sample Complexity in Stochastic Multi-Objective Learning

Authors: Zhuqing Liu, Chaosheng Dong, Michinari Momma, Simone Shao, Shaoyuan Xu, Yan Gao, Haibo Yang, Jia Liu

Abstract: Recently, multi-objective optimization (MOO) has gained attention for its broad applications in ML, operations research, and engineering. However, MOO algorithm design remains in its infancy and many existing MOO methods suffer from unsatisfactory convergence rate and sample complexity performance. To address this challenge, in this paper, we propose an algorithm called STIMULUS( stochastic path-i… ▽ More Recently, multi-objective optimization (MOO) has gained attention for its broad applications in ML, operations research, and engineering. However, MOO algorithm design remains in its infancy and many existing MOO methods suffer from unsatisfactory convergence rate and sample complexity performance. To address this challenge, in this paper, we propose an algorithm called STIMULUS( stochastic path-integrated multi-gradient recursive e\ulstimator), a new and robust approach for solving MOO problems. Different from the traditional methods, STIMULUS introduces a simple yet powerful recursive framework for updating stochastic gradient estimates to improve convergence performance with low sample complexity. In addition, we introduce an enhanced version of STIMULUS, termed STIMULUS-M, which incorporates a momentum term to further expedite convergence. We establish $O(1/T)$ convergence rates of the proposed methods for non-convex settings and $O (\exp{-μT})$ for strongly convex settings, where $T$ is the total number of iteration rounds. Additionally, we achieve the state-of-the-art $O \left(n+\sqrt{n}ε^{-1}\right)$ sample complexities for non-convex settings and $O\left(n+ \sqrt{n} \ln ({μ/ε})\right)$ for strongly convex settings, where $ε>0$ is a desired stationarity error. Moreover, to alleviate the periodic full gradient evaluation requirement in STIMULUS and STIMULUS-M, we further propose enhanced versions with adaptive batching called STIMULUS+/ STIMULUS-M+ and provide their theoretical analysis. △ Less

Submitted 23 June, 2025; originally announced June 2025.

Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional Controls

Authors: Yihong Luo, Shuchen Xue, Tianyang Hu, Jing Tang

Abstract: The pursuit of efficient and controllable high-quality content generation remains a central challenge in artificial intelligence-generated content (AIGC). While one-step generators, enabled by diffusion distillation techniques, offer excellent generation quality and computational efficiency, adapting them to new control conditions--such as structural constraints, semantic guidelines, or external i… ▽ More The pursuit of efficient and controllable high-quality content generation remains a central challenge in artificial intelligence-generated content (AIGC). While one-step generators, enabled by diffusion distillation techniques, offer excellent generation quality and computational efficiency, adapting them to new control conditions--such as structural constraints, semantic guidelines, or external inputs--poses a significant challenge. Conventional approaches often necessitate computationally expensive modifications to the base model and subsequent diffusion distillation. This paper introduces Noise Consistency Training (NCT), a novel and lightweight approach to directly integrate new control signals into pre-trained one-step generators without requiring access to original training images or retraining the base diffusion model. NCT operates by introducing an adapter module and employs a noise consistency loss in the noise space of the generator. This loss aligns the adapted model's generation behavior across noises that are conditionally dependent to varying degrees, implicitly guiding it to adhere to the new control. Theoretically, this training objective can be understood as minimizing the distributional distance between the adapted generator and the conditional distribution induced by the new conditions. NCT is modular, data-efficient, and easily deployable, relying only on the pre-trained one-step generator and a control signal model. Extensive experiments demonstrate that NCT achieves state-of-the-art controllable generation in a single forward pass, surpassing existing multi-step and distillation-based methods in both generation quality and computational efficiency. Code is available at https://github.com/Luo-Yihong/NCT △ Less

Submitted 24 June, 2025; originally announced June 2025.

PS-WL: A Probability-Sensitive Wear Leveling scheme for SSD array scaling

Authors: Shuhang Xu, Yunfei Gu, Linhui Liu, Chentao Wu

Abstract: As flash-based Solid State Drive (SSD) arrays become essential to modern data centers, scaling these arrays to meet explosive data growth is a frequent and critical operation. However, the conventional wear-leveling (WL) paradigm applied during scaling suffers from a fundamental flaw: it ignores the non-linear relationship between wear and failure probability, potentially pushing the most vulnerab… ▽ More As flash-based Solid State Drive (SSD) arrays become essential to modern data centers, scaling these arrays to meet explosive data growth is a frequent and critical operation. However, the conventional wear-leveling (WL) paradigm applied during scaling suffers from a fundamental flaw: it ignores the non-linear relationship between wear and failure probability, potentially pushing the most vulnerable, aged disks towards premature failure. To address this critical issue at its root, we propose the Probability-Sensitive Wear Leveling (PS-WL) scheme, which shifts the optimization goal from balancing wear to directly balancing failure risk. At its core, PS-WL introduces an "effective lifetime" model derived from a realistic failure probability to more accurately assess disk lifetime. This model guides a PID controller for wear leveling operation, with a conservative zone minimizes performance overhead by restricting warm data migration. Comprehensive simulations validate the superiority of PS-WL over state-of-the-art methods. The results demonstrate that our approach significantly reduces performance overhead while, most critically, consistently and effectively lowering the aggregated array failure risk across diverse system configurations and workloads. This proves that by directly optimizing for reliability, PS-WL builds a scalable storage system that is, by design, fundamentally safer, more efficient, and more stable. △ Less

Submitted 3 July, 2025; v1 submitted 24 June, 2025; originally announced June 2025.

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

Authors: Ziqiao Ma, Xuweiyi Chen, Shoubin Yu, Sai Bi, Kai Zhang, Chen Ziwen, Sihan Xu, Jianing Yang, Zexiang Xu, Kalyan Sunkavalli, Mohit Bansal, Joyce Chai, Hao Tan

Abstract: Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative answer with 4D-LRM, the first large-scale 4D reconstruction model that takes input from unconstrained views and timestamps and renders arbitrary novel view-time combinations. Unlike prior 4D approaches, e.g., optimizati… ▽ More Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative answer with 4D-LRM, the first large-scale 4D reconstruction model that takes input from unconstrained views and timestamps and renders arbitrary novel view-time combinations. Unlike prior 4D approaches, e.g., optimization-based, geometry-based, or generative, that struggle with efficiency, generalization, or faithfulness, 4D-LRM learns a unified space-time representation and directly predicts per-pixel 4D Gaussian primitives from posed image tokens across time, enabling fast, high-quality rendering at, in principle, infinite frame rate. Our results demonstrate that scaling spatiotemporal pretraining enables accurate and efficient 4D reconstruction. We show that 4D-LRM generalizes to novel objects, interpolates across time, and handles diverse camera setups. It reconstructs 24-frame sequences in one forward pass with less than 1.5 seconds on a single A100 GPU. △ Less

Submitted 23 June, 2025; originally announced June 2025.

Comments: Project page: https://4dlrm.github.io/

Light of Normals: Unified Feature Representation for Universal Photometric Stereo

Authors: Hong Li, Houyuan Chen, Chongjie Ye, Zhaoxi Chen, Bohan Li, Shaocong Xu, Xianda Guo, Xuhui Liu, Yikai Wang, Baochang Zhang, Satoshi Ikehata, Boxin Shi, Anyi Rao, Hao Zhao

Abstract: Universal photometric stereo (PS) aims to recover high-quality surface normals from objects under arbitrary lighting conditions without relying on specific illumination models. Despite recent advances such as SDM-UniPS and Uni MS-PS, two fundamental challenges persist: 1) the deep coupling between varying illumination and surface normal features, where ambiguity in observed intensity makes it diff… ▽ More Universal photometric stereo (PS) aims to recover high-quality surface normals from objects under arbitrary lighting conditions without relying on specific illumination models. Despite recent advances such as SDM-UniPS and Uni MS-PS, two fundamental challenges persist: 1) the deep coupling between varying illumination and surface normal features, where ambiguity in observed intensity makes it difficult to determine whether brightness variations stem from lighting changes or surface orientation; and 2) the preservation of high-frequency geometric details in complex surfaces, where intricate geometries create self-shadowing, inter-reflections, and subtle normal variations that conventional feature processing operations struggle to capture accurately. △ Less

Submitted 24 June, 2025; v1 submitted 23 June, 2025; originally announced June 2025.

Comments: Home: https://houyuanchen111.github.io/lino.github.io Github: https://github.com/houyuanchen111/LINO_UniPS HuggingFace Demo: https://huggingface.co/spaces/houyuanchen/lino

OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation

Authors: Qijun Gan, Ruizi Yang, Jianke Zhu, Shaofei Xue, Steven Hoi

Abstract: Significant progress has been made in audio-driven human animation, while most existing methods focus mainly on facial movements, limiting their ability to create full-body animations with natural synchronization and fluidity. They also struggle with precise prompt control for fine-grained generation. To tackle these challenges, we introduce OmniAvatar, an innovative audio-driven full-body video g… ▽ More Significant progress has been made in audio-driven human animation, while most existing methods focus mainly on facial movements, limiting their ability to create full-body animations with natural synchronization and fluidity. They also struggle with precise prompt control for fine-grained generation. To tackle these challenges, we introduce OmniAvatar, an innovative audio-driven full-body video generation model that enhances human animation with improved lip-sync accuracy and natural movements. OmniAvatar introduces a pixel-wise multi-hierarchical audio embedding strategy to better capture audio features in the latent space, enhancing lip-syncing across diverse scenes. To preserve the capability for prompt-driven control of foundation models while effectively incorporating audio features, we employ a LoRA-based training approach. Extensive experiments show that OmniAvatar surpasses existing models in both facial and semi-body video generation, offering precise text-based control for creating videos in various domains, such as podcasts, human interactions, dynamic scenes, and singing. Our project page is https://omni-avatar.github.io/. △ Less

Submitted 23 June, 2025; originally announced June 2025.

Comments: Project page: https://omni-avatar.github.io/

USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways

Authors: Shanliang Yao, Runwei Guan, Yi Ni, Sen Xu, Yong Yue, Xiaohui Zhu, Ryan Wen Liu

Abstract: Object tracking in inland waterways plays a crucial role in safe and cost-effective applications, including waterborne transportation, sightseeing tours, environmental monitoring and surface rescue. Our Unmanned Surface Vehicle (USV), equipped with a 4D radar, a monocular camera, a GPS, and an IMU, delivers robust tracking capabilities in complex waterborne environments. By leveraging these sensor… ▽ More Object tracking in inland waterways plays a crucial role in safe and cost-effective applications, including waterborne transportation, sightseeing tours, environmental monitoring and surface rescue. Our Unmanned Surface Vehicle (USV), equipped with a 4D radar, a monocular camera, a GPS, and an IMU, delivers robust tracking capabilities in complex waterborne environments. By leveraging these sensors, our USV collected comprehensive object tracking data, which we present as USVTrack, the first 4D radar-camera tracking dataset tailored for autonomous driving in new generation waterborne transportation systems. Our USVTrack dataset presents rich scenarios, featuring diverse various waterways, varying times of day, and multiple weather and lighting conditions. Moreover, we present a simple but effective radar-camera matching method, termed RCM, which can be plugged into popular two-stage association trackers. Experimental results utilizing RCM demonstrate the effectiveness of the radar-camera matching in improving object tracking accuracy and reliability for autonomous driving in waterborne environments. The USVTrack dataset is public on https://usvtrack.github.io. △ Less

Submitted 23 June, 2025; originally announced June 2025.

Comments: Accepted by IROS

Efficient Beam Selection for ISAC in Cell-Free Massive MIMO via Digital Twin-Assisted Deep Reinforcement Learning

Authors: Jiexin Zhang, Shu Xu, Chunguo Li, Yongming Huang, Luxi Yang

Abstract: Beamforming enhances signal strength and quality by focusing energy in specific directions. This capability is particularly crucial in cell-free integrated sensing and communication (ISAC) systems, where multiple distributed access points (APs) collaborate to provide both communication and sensing services. In this work, we first derive the distribution of joint target detection probabilities acro… ▽ More Beamforming enhances signal strength and quality by focusing energy in specific directions. This capability is particularly crucial in cell-free integrated sensing and communication (ISAC) systems, where multiple distributed access points (APs) collaborate to provide both communication and sensing services. In this work, we first derive the distribution of joint target detection probabilities across multiple receiving APs under false alarm rate constraints, and then formulate the beam selection procedure as a Markov decision process (MDP). We establish a deep reinforcement learning (DRL) framework, in which reward shaping and sinusoidal embedding are introduced to facilitate agent learning. To eliminate the high costs and associated risks of real-time agent-environment interactions, we further propose a novel digital twin (DT)-assisted offline DRL approach. Different from traditional online DRL, a conditional generative adversarial network (cGAN)-based DT module, operating as a replica of the real world, is meticulously designed to generate virtual state-action transition pairs and enrich data diversity, enabling offline adjustment of the agent's policy. Additionally, we address the out-of-distribution issue by incorporating an extra penalty term into the loss function design. The convergency of agent-DT interaction and the upper bound of the Q-error function are theoretically derived. Numerical results demonstrate the remarkable performance of our proposed approach, which significantly reduces online interaction overhead while maintaining effective beam selection across diverse conditions including strict false alarm control, low signal-to-noise ratios, and high target velocities. △ Less

Submitted 23 June, 2025; originally announced June 2025.

Comments: Submitted to IEEE Transactions on Wireless Communications

Deep Research Agents: A Systematic Examination And Roadmap

Authors: Yuxuan Huang, Yihang Chen, Haozheng Zhang, Kang Li, Meng Fang, Linyi Yang, Xiaoguang Li, Lifeng Shang, Songcen Xu, Jianye Hao, Kun Shao, Jun Wang

Abstract: The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to tackle complex, multi-turn informational research tasks by leveraging a combination of dynamic reasoning, adaptive long-horizon planning, multi-hop information retrieval, iterative tool use, and the generation of struct… ▽ More The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to tackle complex, multi-turn informational research tasks by leveraging a combination of dynamic reasoning, adaptive long-horizon planning, multi-hop information retrieval, iterative tool use, and the generation of structured analytical reports. In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute Deep Research agents. We begin by reviewing information acquisition strategies, contrasting API-based retrieval methods with browser-based exploration. We then examine modular tool-use frameworks, including code execution, multimodal input processing, and the integration of Model Context Protocols (MCPs) to support extensibility and ecosystem development. To systematize existing approaches, we propose a taxonomy that differentiates between static and dynamic workflows, and we classify agent architectures based on planning strategies and agent composition, including single-agent and multi-agent configurations. We also provide a critical evaluation of current benchmarks, highlighting key limitations such as restricted access to external knowledge, sequential execution inefficiencies, and misalignment between evaluation metrics and the practical objectives of DR agents. Finally, we outline open challenges and promising directions for future research. A curated and continuously updated repository of DR agent research is available at: {https://github.com/ai-agents-2030/awesome-deep-research-agent}. △ Less

Submitted 22 June, 2025; originally announced June 2025.

LIT-LVM: Structured Regularization for Interaction Terms in Linear Predictors using Latent Variable Models

Authors: Mohammadreza Nemati, Zhipeng Huang, Kevin S. Xu

Abstract: Some of the simplest, yet most frequently used predictors in statistics and machine learning use weighted linear combinations of features. Such linear predictors can model non-linear relationships between features by adding interaction terms corresponding to the products of all pairs of features. We consider the problem of accurately estimating coefficients for interaction terms in linear predicto… ▽ More Some of the simplest, yet most frequently used predictors in statistics and machine learning use weighted linear combinations of features. Such linear predictors can model non-linear relationships between features by adding interaction terms corresponding to the products of all pairs of features. We consider the problem of accurately estimating coefficients for interaction terms in linear predictors. We hypothesize that the coefficients for different interaction terms have an approximate low-dimensional structure and represent each feature by a latent vector in a low-dimensional space. This low-dimensional representation can be viewed as a structured regularization approach that further mitigates overfitting in high-dimensional settings beyond standard regularizers such as the lasso and elastic net. We demonstrate that our approach, called LIT-LVM, achieves superior prediction accuracy compared to elastic net and factorization machines on a wide variety of simulated and real data, particularly when the number of interaction terms is high compared to the number of samples. LIT-LVM also provides low-dimensional latent representations for features that are useful for visualizing and analyzing their relationships. △ Less

Submitted 18 June, 2025; originally announced June 2025.

FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution

Authors: Siyu Xu, Wenjie Li, Guangwei Gao, Jian Yang, Guo-Jun Qi, Chia-Wen Lin

Abstract: Face super-resolution (FSR) under limited computational costs remains an open problem. Existing approaches typically treat all facial pixels equally, resulting in suboptimal allocation of computational resources and degraded FSR performance. CNN is relatively sensitive to high-frequency facial features, such as component contours and facial outlines. Meanwhile, Mamba excels at capturing low-freque… ▽ More Face super-resolution (FSR) under limited computational costs remains an open problem. Existing approaches typically treat all facial pixels equally, resulting in suboptimal allocation of computational resources and degraded FSR performance. CNN is relatively sensitive to high-frequency facial features, such as component contours and facial outlines. Meanwhile, Mamba excels at capturing low-frequency features like facial color and fine-grained texture, and does so with lower complexity than Transformers. Motivated by these observations, we propose FADPNet, a Frequency-Aware Dual-Path Network that decomposes facial features into low- and high-frequency components and processes them via dedicated branches. For low-frequency regions, we introduce a Mamba-based Low-Frequency Enhancement Block (LFEB), which combines state-space attention with squeeze-and-excitation operations to extract low-frequency global interactions and emphasize informative channels. For high-frequency regions, we design a CNN-based Deep Position-Aware Attention (DPA) module to enhance spatially-dependent structural details, complemented by a lightweight High-Frequency Refinement (HFR) module that further refines frequency-specific representations. Through the above designs, our method achieves an excellent balance between FSR quality and model efficiency, outperforming existing approaches. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Comments: 12 pages, 11 figures, 6 tales

Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing

Authors: Xiang Zhang, Jiaqi Wei, Zijie Qiu, Sheng Xu, Nanqing Dong, Zhiqiang Gao, Siqi Sun

Abstract: Peptide sequencing-the process of identifying amino acid sequences from mass spectrometry data-is a fundamental task in proteomics. Non-Autoregressive Transformers (NATs) have proven highly effective for this task, outperforming traditional methods. Unlike autoregressive models, which generate tokens sequentially, NATs predict all positions simultaneously, leveraging bidirectional context through… ▽ More Peptide sequencing-the process of identifying amino acid sequences from mass spectrometry data-is a fundamental task in proteomics. Non-Autoregressive Transformers (NATs) have proven highly effective for this task, outperforming traditional methods. Unlike autoregressive models, which generate tokens sequentially, NATs predict all positions simultaneously, leveraging bidirectional context through unmasked self-attention. However, existing NAT approaches often rely on Connectionist Temporal Classification (CTC) loss, which presents significant optimization challenges due to CTC's complexity and increases the risk of training failures. To address these issues, we propose an improved non-autoregressive peptide sequencing model that incorporates a structured protein sequence curriculum learning strategy. This approach adjusts protein's learning difficulty based on the model's estimated protein generational capabilities through a sampling process, progressively learning peptide generation from simple to complex sequences. Additionally, we introduce a self-refining inference-time module that iteratively enhances predictions using learned NAT token embeddings, improving sequence accuracy at a fine-grained level. Our curriculum learning strategy reduces NAT training failures frequency by more than 90% based on sampled training over various data distributions. Evaluations on nine benchmark species demonstrate that our approach outperforms all previous methods across multiple metrics and species. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?

Authors: Xiangyang Li, Xiaopeng Li, Kuicai Dong, Quanhu Zhang, Rongju Ruan, Xinyi Dai, Xiaoshuang Liu, Shengchun Xu, Yasheng Wang, Ruiming Tang

Abstract: Code generation is a core capability of large language models (LLMs), yet mainstream benchmarks (e.g., APPs and LiveCodeBench) contain questions with medium-level difficulty and pose no challenge to advanced LLMs. To better reflected the advanced reasoning and code generation ability, We introduce Humanity's Last Code Exam (HLCE), comprising 235 most challenging problems from the International Col… ▽ More Code generation is a core capability of large language models (LLMs), yet mainstream benchmarks (e.g., APPs and LiveCodeBench) contain questions with medium-level difficulty and pose no challenge to advanced LLMs. To better reflected the advanced reasoning and code generation ability, We introduce Humanity's Last Code Exam (HLCE), comprising 235 most challenging problems from the International Collegiate Programming Contest (ICPC World Finals) and the International Olympiad in Informatics (IOI) spanning 2010 - 2024. As part of HLCE, we design a harmonized online-offline sandbox that guarantees fully reproducible evaluation. Through our comprehensive evaluation, we observe that even the strongest reasoning LLMs: o4-mini(high) and Gemini-2.5 Pro, achieve pass@1 rates of only 15.9% and 11.4%, respectively. Meanwhile, we propose a novel "self-recognition" task to measure LLMs' awareness of their own capabilities. Results indicate that LLMs' self-recognition abilities are not proportionally correlated with their code generation performance. Finally, our empirical validation of test-time scaling laws reveals that current advanced LLMs have substantial room for improvement on complex programming tasks. We expect HLCE to become a milestone challenge for code generation and to catalyze advances in high-performance reasoning and human-AI collaborative programming. Our code and dataset are also public available(https://github.com/Humanity-s-Last-Code-Exam/HLCE). △ Less

Submitted 15 June, 2025; originally announced June 2025.

SoK: Automated Vulnerability Repair: Methods, Tools, and Assessments

Authors: Yiwei Hu, Zhen Li, Kedie Shu, Shenghua Guan, Deqing Zou, Shouhuai Xu, Bin Yuan, Hai Jin

Abstract: The increasing complexity of software has led to the steady growth of vulnerabilities. Vulnerability repair investigates how to fix software vulnerabilities. Manual vulnerability repair is labor-intensive and time-consuming because it relies on human experts, highlighting the importance of Automated Vulnerability Repair (AVR). In this SoK, we present the systematization of AVR methods through the… ▽ More The increasing complexity of software has led to the steady growth of vulnerabilities. Vulnerability repair investigates how to fix software vulnerabilities. Manual vulnerability repair is labor-intensive and time-consuming because it relies on human experts, highlighting the importance of Automated Vulnerability Repair (AVR). In this SoK, we present the systematization of AVR methods through the three steps of AVR workflow: vulnerability analysis, patch generation, and patch validation. We assess AVR tools for C/C++ and Java programs as they have been widely studied by the community. Since existing AVR tools for C/C++ programs are evaluated with different datasets, which often consist of a few vulnerabilities, we construct the first C/C++ vulnerability repair benchmark dataset, dubbed Vul4C, which contains 144 vulnerabilities as well as their exploits and patches. We use Vul4C to evaluate seven AVR tools for C/C++ programs and use the third-party Vul4J dataset to evaluate two AVR tools for Java programs. We also discuss future research directions. △ Less

Submitted 13 June, 2025; originally announced June 2025.

Comments: The full version of "SoK: Automated Vulnerability Repair: Methods, Tools, and Assessments" accepted by the 34th USENIX Security Symposium (USENIX Security 2025)