Showing 1–50 of 153 results for author: Xie, K

FireRedTTS3: Unified Speech Generation and Editing with Semantically Enriched Speech Representations

Authors: Feiyu Shen, Kun Xie, Yichen Wu, Ziqi Dai, Yichen Han, Junjie Li, Xuelong Geng, Fenglong Xie, Lei Xie, Xu Tang, Yao Hu

Abstract: Recent continuous autoregressive TTS models operate directly on continuous speech representations, preserving rich acoustic details while leveraging the instruction-following capabilities of text LLMs. This paradigm opens new possibilities for voice cloning, instruction-controlled voice design, and speech editing, but remains susceptible to error accumulation during autoregressive generation. Exis… ▽ More Recent continuous autoregressive TTS models operate directly on continuous speech representations, preserving rich acoustic details while leveraging the instruction-following capabilities of text LLMs. This paradigm opens new possibilities for voice cloning, instruction-controlled voice design, and speech editing, but remains susceptible to error accumulation during autoregressive generation. Existing solutions often require additional semantic modules, multi-stage tokenizer training pipelines, or complex autoregressive architectures. In this work, we propose FireRedTTS3, a simple yet effective speech generation and editing framework that mitigates error accumulation at the representation level. Specifically, we leverage a frozen Audio Encoder trained on diverse speech understanding tasks as a semantic teacher to regularize the audio feature space. This improves text-speech alignment and stabilizes autoregressive generation while keeping the overall system simple. FireRedTTS3 provides two variants: FireRedTTS3-Base for multilingual and multi-dialect zero-shot voice cloning, and FireRedTTS3-Instruct for unified voice cloning, instruction-controlled voice design, and speech editing. Experiments show that FireRedTTS3-Base achieves the best average speech intelligibility and speaker similarity among compared systems on Seed-TTS-Eval and MiniMax-MLS-Test, while FireRedTTS3-Instruct outperforms competing systems on InstructTTSEval and Ming-Freeform-Audio-Edit. These results demonstrate that semantically enriched continuous speech representations, combined with a simple architecture, enable stable, controllable, and high-fidelity speech generation and editing. Code and models are available at https://github.com/FireRedTeam/FireRedTTS3. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Incremental Directed Minimum Cut by Dynamizing Gabow's Algorithm

Authors: Thatchaphol Saranurak, Kaiyang Xie, Zhaienhe Zhou

Abstract: We give the first incremental algorithm for directed global minimum cut. Given a directed graph with $n$ vertices undergoing $m$ edge insertions, our deterministic algorithm explicitly maintains a global minimum cut or certifies that its value is at least $k$ in $O(km\log n)$ total update time. Prior work required either that $k\le2$ or that the graph is undirected. Our algorithm is a strict inc… ▽ More We give the first incremental algorithm for directed global minimum cut. Given a directed graph with $n$ vertices undergoing $m$ edge insertions, our deterministic algorithm explicitly maintains a global minimum cut or certifies that its value is at least $k$ in $O(km\log n)$ total update time. Prior work required either that $k\le2$ or that the graph is undirected. Our algorithm is a strict incremental extension of Gabow's state-of-the-art static algorithm (JCSS 1995), with no asymptotic loss in running time over the entire insertion sequence. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility

Authors: Yansen Zhang, Yilu Liu, Tianyu Liu, Jiamin Chen, Xiaokun Zhang, Kai Xie, Xue Liu, Yiyan Qi, Chen Ma

Abstract: Large language models increasingly support scientific and algorithmic discovery through inference-time search over evaluated candidates. Existing adaptive discovery controllers assign credit based only on score progress, even though prompt length, retries, and guidance calls cause search actions to incur different token costs. We prove that cost-blind credit can forfeit all but a vanishing fractio… ▽ More Large language models increasingly support scientific and algorithmic discovery through inference-time search over evaluated candidates. Existing adaptive discovery controllers assign credit based only on score progress, even though prompt length, retries, and guidance calls cause search actions to incur different token costs. We prove that cost-blind credit can forfeit all but a vanishing fraction of attainable quality as frontiers multiply and costs diverge. Under a fixed search-side token budget, the controller must decide which frontier is improving and whether its gain justifies the realized cost before the budget is exhausted. We introduce \textbf{CostAda}, a cost-calibrated adaptive controller built around \emph{cost-calibrated frontier utility}. The utility values frontier progress relative to realized action cost and conditions that credit on the remaining budget. CostAda uses this signal to control local exploration intensity, frontier allocation, and budgeted tactic intervention. Cost and remaining budget therefore shape the search rather than serving only as accounting variables or a stopping rule. CostAda reaches the strongest baseline's full-budget quality with at most half the budget on twelve of sixteen benchmark--backbone pairs while achieving the strongest mean final quality on all eight benchmarks under GLM-5 and GPT-5.4. △ Less

Submitted 5 August, 2026; v1 submitted 29 July, 2026; originally announced July 2026.

DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation

Authors: Jian Zhu, Jianjun Zhang, Taiyi Su, Tianbin Liu, Zhangyuan Wang, Kai Xie, Zitai Huang, Chong Ma, Youzhang He, Tianjian Wang, Hanyang Wang, Weihao Ding, Yi Xu

Abstract: World Action Models (WAMs) provide a promising alternative to Vision-Language-Action (VLA) policies by using video-based world modeling as dense supervision for robot action learning. Existing WAMs excel at physically grounded execution, but typically lack the explicit language-level planning interface in VLM-based VLAs for decomposing coarse instructions. Such decomposition becomes important when… ▽ More World Action Models (WAMs) provide a promising alternative to Vision-Language-Action (VLA) policies by using video-based world modeling as dense supervision for robot action learning. Existing WAMs excel at physically grounded execution, but typically lack the explicit language-level planning interface in VLM-based VLAs for decomposing coarse instructions. Such decomposition becomes important when household tasks involve complex multi-step goals, where coarse user commands need to be converted into sequences of fine-grained executable subtasks. Meanwhile, the field still lacks a fair real-robot comparison between VLA and WAM execution capabilities, since existing systems often differ in data, robot embodiments, and task protocols. To address both the decomposition gap and the need for a controlled WAM-VLA comparison, we introduce DSWAM, a Dual-System World Action Foundation Model for fine-grained robot manipulation. DSWAM keeps a System 1 WAM executor as the default control path and optionally activates a System 2 vision-language subtask planner only when task decomposition is useful. The planner predicts executable subtasks from short-term visual history and a global task prompt, while the WAM executor performs world-aware action generation for each instruction or subtask. The executor is trained with action prediction and video co-training, but inference directly predicts action chunks without explicit future video generation. To make this execution path practical on real robots, we further integrate TensorRT acceleration, asynchronous execution, and real-time chunking (RTC) so that policy queries do not block robot control. To provide a fair real-robot comparison with VLA policies, we build and evaluate DSWAM under the DeMaVLA real-world deformable manipulation setting with matched robot platform, pretraining data, post-training data, and evaluation criteria. △ Less

Submitted 6 July, 2026; originally announced July 2026.

Comments: 13 pages, 1 figures

ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing

Authors: Wei Sun, Weixia Zhang, Linhan Cao, Mingkai Lu, Xiongkuo Min, Xiaoping Zhang, Patrick Le Callet, Guangtao Zhai, Hongxing Chen, Wenqi Wu, Zhenhao Hu, Shanshan Lin, Guanjie Huang, Kai Xie, Rui Xin, Zilong Zhao, Runmin Cong, Ningjing Li, Siqi Ma, Yi Jin Ong, Tianfei Zhou, Shunzhou Wang, Zhiyang Chen, Hao Fang, Chen Zhang , et al. (8 additional authors not shown)

Abstract: This paper presents the IEEE International Conference on Multimedia and Expo (ICME) 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing. The challenge is motivated by two key limitations of existing industrial defect inspection systems: (1) current deep learning-based methods often suffer significant performance degradation whe… ▽ More This paper presents the IEEE International Conference on Multimedia and Expo (ICME) 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing. The challenge is motivated by two key limitations of existing industrial defect inspection systems: (1) current deep learning-based methods often suffer significant performance degradation when deployed in unseen production scenarios, and (2) most benchmarks neglect severity-aware assessment, which is critical for risk control and yield optimization. To address these limitations, we design two complementary tracks: Track 1 (Cross-Scenario Defect Detection) targets accurate defect detection, localization, and classification across diverse unseen production environments; Track 2 (Fine-Grained Severity Grading) requires assigning each detected defect an industry-standard severity level, including Acceptable, Marginal NG, NG, and Gross NG. We construct a large-scale industrial dataset of high-resolution microscopic images spanning seven representative defect categories, comprising over 3,800 images with pixel-level instance annotations for Track 1 and over 2,600 images with severity-grade labels for Track 2. The challenge attracted 86 registered participants with 130 submissions; during the final testing phase, 21 teams submitted results and 12 teams provided models with technical reports. The resulting benchmark, together with the diverse and effective solutions contributed by participating teams, sets a new standard for industrial defect analysis research. △ Less

Submitted 6 July, 2026; originally announced July 2026.

DPIFrame: A Dual-Level Parallelism Acceleration Framework for CTR Model Inference

Authors: Dezhi Yi, Huifeng Guo, Kunpeng Xie, Zhaolong Jian, Haochi Yu, Wenxuan He, Zhenhua Dong, Ruiming Tang, Ye Lu

Abstract: Deep learning technology has enhanced the ability of Click-through rate (CTR) prediction models to learn features and improve prediction accuracy. However, it is challenging to deploy CTR models on GPU smoothly and perform inference efficiently, because there is a huge mismatch between the serial computational pattern and the parallel model structure. In this paper, we propose DPIFrame, the first… ▽ More Deep learning technology has enhanced the ability of Click-through rate (CTR) prediction models to learn features and improve prediction accuracy. However, it is challenging to deploy CTR models on GPU smoothly and perform inference efficiently, because there is a huge mismatch between the serial computational pattern and the parallel model structure. In this paper, we propose DPIFrame, the first dual parallelizable framework to accelerate CTR model inference. In DPIFrame, a) a dual parallelizable architecture is proposed to perform parallel CTR model inference in both intra-module and inter-module; b) an efficient multi-table lookup algorithm is presented for embedding operations through anticipating the whole workload in advance; c) a breadth-first stream scheduling strategy is designed for fine-grained management of parallel computation on GPU to further supporting the dual parallel execution. Extensive experiments are conducted on two real-world datasets, and the results highlight that DPIFrame can reduce the embedding latency efficiently by \textbf{23.0$\times$} compared to PyTorch. Compared with PyTorch, TorchRec, HugeCTR, and OneFlow, DPIFrame can achieve state-of-the-art inference performance on GPU with speedups of \textbf{5.83$\times$}, \textbf{4.29$\times$}, \textbf{2.15$\times$}, and \textbf{2.0$\times$}, respectively. △ Less

Submitted 19 June, 2026; originally announced June 2026.

DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models

Authors: Xinglong Sun, Kevin Xie, Jenny Schmalfuss, Despoina Paschalidou, Xiuming Zhang, Sanja Fidler, Kashyap Chitta, Jose M. Alvarez

Abstract: Autonomous driving has shifted towards end-to-end policy learning, where reliable, interpretable policy evaluation is a fundamental challenge as driving quality is highly context-dependent. Commonly used rule-based driving metrics like EPDMS are interpretable but lack context-awareness, while recent VLMbased evaluations are context-aware but limited by ambiguous VLM outputs and weak physical groun… ▽ More Autonomous driving has shifted towards end-to-end policy learning, where reliable, interpretable policy evaluation is a fundamental challenge as driving quality is highly context-dependent. Commonly used rule-based driving metrics like EPDMS are interpretable but lack context-awareness, while recent VLMbased evaluations are context-aware but limited by ambiguous VLM outputs and weak physical grounding. To evaluate driving in a manner that is both interpretable and context-aware, we introduce DriveJudge. DriveJudge is a driving evaluation agent that combines rule-grounded evaluation with Vision-Language Model (VLM) reasoning and selectively invokes physically-grounded deterministic rule functions after interpreting the environmental context. To train and evaluate DriveJudge, we curate a large-scale dataset of 33,577 challenging driving samples with human annotations on whether the driving behavior is reasonable in the given scenario. With this dataset, we address the underexplored problem of driving metric evaluation, and introduce two human-aligned benchmark tasks: Driving Quality Classification and Trajectory Preference Selection. DriveJudge outperforms EPDMS for driving quality classification by 21.23 AUC, and the recent VLM-based DriveCritic for trajectory preference selection by 6.5%, setting a new standard for interpretable and precise driving evaluation. △ Less

Submitted 15 June, 2026; originally announced June 2026.

Comments: Under Review

NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

Authors: NVIDIA, :, Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, Francesco Ferroni, Guillermo Garcia Cobo, Haithem Turki, Huan Ling, Jaewoo Seo, James Lucas, Jay Zhangjie Wu, Jialiang Wang, Jonathan Lorraine, Jun Gao, Kai He, Katarina Tothova, Kevin Xie, Michał Tyszkiewicz, Qi Wu, Riccardo de Lutio, Ruilong Li, Sanja Fidler, Seung Wook Kim , et al. (10 additional authors not shown)

Abstract: As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations. While recent reconstruction-based neural s… ▽ More As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations. While recent reconstruction-based neural simulators offer photorealism, they are fundamentally constrained by their initial captured data and struggle to generalize to highly dynamic or novel scenes. To overcome these limitations, we introduce OmniDreams, a foundation generative world model mid- and post-trained from the Cosmos diffusion model to autoregressively generate action-conditioned videos in real time. By leveraging the rich visual priors of Cosmos and mid- and post-training on 21k hours of driving scenarios, OmniDreams synthesizes complex, unobserved phenomena that are hard for traditional simulators to capture, such as extreme weather and unpredictable dynamic agent behaviors. Crucially, it autoregressively conditions its photorealistic sensor generation on past frames, the current simulator state, and immediate driving actions. Deployed in a closed-loop system with the Alpamayo 1 policy model and AlpaSim orchestrator, OmniDreams acts as a highly responsive, reactive environment, providing a scalable and comprehensive solution for training and evaluating next-generation autonomous driving policies. We additionally show preliminary results indicating that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters. These results highlight the potential for a real-time world model like OmniDreams to also serve as a backbone for policy architectures. △ Less

Submitted 23 July, 2026; v1 submitted 2 June, 2026; originally announced June 2026.

Cosmos 3: Omnimodal World Models for Physical AI

Authors: NVIDIA, :, Aditi, Niket Agarwal, Arslan Ali, Jon Allen, Martin Antolini, Adeline Aubame, Alisson Azzolini, Junjie Bai, Maciej Bala, Yogesh Balaji, Josh Bapst, Aarti Basant, Mukesh Beladiya, Mohammad Qazim Bhat, Zaid Pervaiz Bhat, Dan Blick, Vanni Brighella, Han Cai, Tiffany Cai, Eric Cameracci, Jiaxin Cao, Yulong Cao, Mark Carlson , et al. (271 additional authors not shown)

Abstract: We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI -- effectively subsuming vision-language models, video generators, worl… ▽ More We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI -- effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3. △ Less

Submitted 23 June, 2026; v1 submitted 1 June, 2026; originally announced June 2026.

TransResAI: A Compound AI System for Coastal Transportation Resilience

Authors: Qingwen Pu, Kun Xie, Chenyu Yan

Abstract: Coastal flooding increasingly threatens transportation infrastructure, yet the analytical tools needed for resilience management remain difficult for many non-specialist practitioners to use. This study presents TransResAI, a compound AI system that supports analysis of flood-aware transportation resilience via natural-language interactions. The system integrates a locally deployable Large Languag… ▽ More Coastal flooding increasingly threatens transportation infrastructure, yet the analytical tools needed for resilience management remain difficult for many non-specialist practitioners to use. This study presents TransResAI, a compound AI system that supports analysis of flood-aware transportation resilience via natural-language interactions. The system integrates a locally deployable Large Language Model (LLM) with modules for task decomposition, secure code generation, geospatial analysis, retrieval-augmented generation, and interactive map rendering. TransResAI links MATSim flood-scenario simulation outputs, OpenStreetMap-derived flood-risk networks, equity-focused demographic indicators, and regional documents in Hampton Roads, Virginia. A structured user study with domain experts demonstrated that TransResAI reduced task completion time by 80-88% relative to conventional GIS workflows, compressing analytical tasks from a mean of 197.1 seconds to 29.7 seconds and visualization tasks from 364.0 seconds to 46.1 seconds, while maintaining mean accuracy of 4.60/5.00 and task completion rates exceeding 94%. These findings demonstrate that compound AI architectures bridge the gap between general-purpose language models and specialized domain knowledge, as well as the quantitative rigor required for infrastructure resilience, providing transportation agencies and communities with faster, more accessible analytical tools for decision-making under growing climate uncertainty. △ Less

Submitted 28 April, 2026; originally announced June 2026.

Comments: 36 pages, 13 figures, 3 table

ACM Class: I.2.7; H.3.3; I.2.1; J.2

Modeling Vehicle-Type-Specific Pedestrian Crash Avoidance Behavior in Safety-Critical Interactions Using Smooth-Mamba Deep Reinforcement Learning

Authors: Qingwen Pu, Kun Xie, Hong Yang, Di Yang, Junqing Wang

Abstract: As automated vehicles (AVs) increasingly share roadways with human-driven vehicles (HDVs), understanding how pedestrians respond to different vehicle types in safety-critical interactions is essential for the safe deployment of automated driving technologies. This study extracts safety-critical pedestrian-vehicle interactions from the Argoverse 2 dataset to capture real-world crash avoidance behav… ▽ More As automated vehicles (AVs) increasingly share roadways with human-driven vehicles (HDVs), understanding how pedestrians respond to different vehicle types in safety-critical interactions is essential for the safe deployment of automated driving technologies. This study extracts safety-critical pedestrian-vehicle interactions from the Argoverse 2 dataset to capture real-world crash avoidance behaviors in encounters involving AVs and HDVs. To model vehicle-type-specific pedestrian crash avoidance behavior, we develop a Smooth-Mamba Deep Deterministic Policy Gradient framework, termed SMamba-DDPG, which integrates smooth action constraints with efficient temporal representation learning. To quantify pedestrian behavioral differences, the framework trains separate crash avoidance policies for pedestrian interactions with AVs and HDVs. Results show that SMamba-DDPG outperforms baseline reinforcement learning and supervised learning models in reproducing pedestrian crash avoidance behaviors. Reconstructed trajectories demonstrate strong behavioral realism, accurately reproducing crash avoidance kinematics in both AV and HDV scenarios. Reaction time analysis shows that the model captures human-like response delays and reveals that pedestrians respond more quickly to AVs than to HDVs. Counterfactual analysis further indicates that pedestrians adopt lower crossing speeds when interacting with AVs. Large-scale safety analysis of model-generated data revealed that pedestrian-AV interactions consistently yielded lower conflict rates and higher pedestrian yielding rates compared to pedestrian-HDV interactions. The findings highlight the importance of incorporating vehicle-type-specific pedestrian behavioral models for safer automated driving system design and more realistic traffic simulations in mixed-traffic environments. △ Less

Submitted 27 May, 2026; originally announced May 2026.

Comments: 37 page. 15 Figure, 9 table

MSC Class: 68T05; 68T07; 90B20; 93E35 ACM Class: I.2.6; I.2.9; I.6.5; J.7

OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025

Authors: Hanna Hoffmann, Setareh Bady, Claas de Boer, Max Kirchner, Jan Egger, Rainer Röhrig, Frank Hölzle, Lennart Johannes Gruber, Kunpeng Xie, Marlon Neuhaus, Victor Alves, Guilherme Barbosa, Leonardo Barroso, João Carvalho, Hao Chen, Gabriella d'Albenzio, André Ferreira, Nuno Gomes, Yuichiro Hayashi, Kousuke Hirasawa, Rebecca Hisey, Seungjae Hong, Seoi Jeong, Tiago Jesus, Daehong Kang , et al. (32 additional authors not shown)

Abstract: Achieving high levels of surgical skill through effective training is essential for optimal patient outcomes. Automated, data-driven skill assessment holds significant potential to improve surgical training. While machine learning-based methods are increasingly popular for assessing skills in minimally invasive surgery, their application to open surgery remains limited. We present the results of a… ▽ More Achieving high levels of surgical skill through effective training is essential for optimal patient outcomes. Automated, data-driven skill assessment holds significant potential to improve surgical training. While machine learning-based methods are increasingly popular for assessing skills in minimally invasive surgery, their application to open surgery remains limited. We present the results of a dedicated MICCAI challenge designed to benchmark and advance vision-based skill assessment in open surgery. The challenge dataset comprises videos of an open suturing training task recorded with a static GoPro camera in a dry-lab setting, with instrument trajectories available in addition to the primary video modality. The OSS Challenge was hosted over two consecutive years, comprising two and three independent tasks, respectively: (1) classifying skill level into four classes, (2) predicting the full Objective Structured Assessment of Technical Skills across eight categories, and (3) tracking hands and surgical tools. Participants submitted diverse solutions including deep learning-based video models, tracking-driven methods, and hybrid approaches. General-purpose spatiotemporal video models consistently achieved the strongest performance, though conceptually diverse approaches reached competitive levels when well-executed. Predicting fine-grained OSATS scores remains challenging but benefits substantially from increased training data. Keypoint tracking proves difficult given frequent occlusions and out-of-frame instances, limiting current applicability for motion-based skill analysis. This work benchmarks innovative and diverse solutions for surgical skill assessment, highlighting both the promise and current limitations of video-based evaluation in open surgery and identifying critical directions for advancing automated skill assessment toward clinical impact. △ Less

Submitted 21 May, 2026; originally announced May 2026.

Comments: Stefanie Speidel and Behrus Hinrichs-Puladi jointly supervised this work. Submitted to MEDIA

Generating Realistic Safety-Critical Scenarios for Vehicle-Pedestrian Interactions

Authors: Qingwen Pu, Kun Xie, Yuan Zhu, Guocong Zhai

Abstract: Automated driving system deployment requires rigorous validation across safety-critical vehicle-pedestrian interactions, yet real-world datasets rarely capture high-risk scenarios while simulation platforms lack realistic behavior. In response, this study proposes a three-stage framework that combines real-world grounding with adaptive simulation to generate behaviorally realistic safety-critical… ▽ More Automated driving system deployment requires rigorous validation across safety-critical vehicle-pedestrian interactions, yet real-world datasets rarely capture high-risk scenarios while simulation platforms lack realistic behavior. In response, this study proposes a three-stage framework that combines real-world grounding with adaptive simulation to generate behaviorally realistic safety-critical scenarios at scale. Stage 1 pre-trains multi-agent state-space Transformer-enhanced DDPG (MA-SST-DDPG) agents on real-world safety-critical data to learn human-like interactive evasive behaviors through data-driven learning. Stage 2 deploys pre-trained multi-agents in CARLA for online reinforcement learning to generalize across diverse scenarios, integrating real-world knowledge with simulation experience to produce a refined MA-SST-DDPG model. Stage 3 uses CARLA with the refined model to generate over 198,000 high-resolution interaction episodes from eight intersection scenarios, culminating in the Vehicle-Pedestrian Safety-Critical Interaction (VPSCI) dataset. The Refined MA-SST-DDPG model outperformed baseline methods in reproducing realistic evasive behaviors, achieving the lowest trajectory errors (ADE = 0.072 m, FDE = 0.142 m). Statistical comparison confirmed distributional equivalence between the generated and real-world data in both conflict severity and behavioral response. A Turing test confirmed that the three-stage framework generated evasive behaviors were indistinguishable from real-world interactions. These results demonstrate the framework's effectiveness in producing high-fidelity safety-critical data, offering valuable sources for the development of ADS and simulation-based safety evaluations. △ Less

Submitted 16 May, 2026; originally announced May 2026.

Comments: 49 pages, 13 figures, 11 table

MSC Class: 68T05; 68T42; 68T07; 91A15; 90B20 ACM Class: I.2.11; I.2.6; I.6.3; I.2.9

Human-AI Co-Evolution and Epistemic Collapse: A Dynamical Systems Perspective

Authors: Xuening Wu, Yanlan Kang, Qianya Xu, Kexuan Xie, Jiaqi Mi, Honggang Wang, Yubin Liu, Zeping Chen

Abstract: Large language models (LLMs) are reshaping how knowledge is produced, with increasing reliance on AI systems for generation, summarization, and reasoning. While prior work has studied cognitive offloading in humans and model collapse in recursive training, these effects are typically considered in isolation. We propose a unified perspective: humans and language models form a coupled dynamical syst… ▽ More Large language models (LLMs) are reshaping how knowledge is produced, with increasing reliance on AI systems for generation, summarization, and reasoning. While prior work has studied cognitive offloading in humans and model collapse in recursive training, these effects are typically considered in isolation. We propose a unified perspective: humans and language models form a coupled dynamical system linked by a feedback loop of usage, generation, and retraining. We introduce a minimal model with three variables -- human cognition, data quality, and model capability -- and show that this feedback can give rise to distinct dynamical regimes. Our analysis identifies three regimes: co-evolutionary enhancement, fragile equilibrium, and degenerative convergence. Through a simple simulation, we demonstrate that increasing reliance on AI can induce a transition toward a low-diversity, suboptimal equilibrium. From an information-theoretic perspective, this transition corresponds to an emergent information bottleneck in the human-AI loop, where entropy reduction reflects loss of diversity and support under closed-loop feedback rather than beneficial compression. These results suggest that the trajectory of AI systems is shaped not only by model design, but by the dynamics of human-AI co-evolution. △ Less

Submitted 7 May, 2026; originally announced May 2026.

Comments: 5 pages, 3 figures, ICML EIML Workshop submitted

SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition

Authors: Kunyuan Xie, Zhixi Cai, Kalin Stefanov

Abstract: Subtle hand differences make sign language recognition challenging, yet many existing methods rely on encoders pretrained on generic action datasets that poorly capture such fine-grained cues. We propose a self-supervised pretraining method for sign language recognition that uses segmentation-based masking to adapt to the presence and motion of key body parts, rather than treating hand poses as st… ▽ More Subtle hand differences make sign language recognition challenging, yet many existing methods rely on encoders pretrained on generic action datasets that poorly capture such fine-grained cues. We propose a self-supervised pretraining method for sign language recognition that uses segmentation-based masking to adapt to the presence and motion of key body parts, rather than treating hand poses as static visual tokens. The resulting mask-and-reconstruct objective improves fine-grained sign representation learning. On WLASL, NMFs-CSL, and Slovo, our encoder achieves state-of-the-art performance, improving per-instance and per-class Top-1 accuracy while using fewer input frames and modalities than comparable encoders. △ Less

Submitted 3 May, 2026; originally announced May 2026.

Comments: Accepted by ICPR 2026

GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment

Authors: Kidus Zewde, Simiao Ren, Xingyu Shen, Jiaqi Wu, Yuchen Zhou, Tommy Duong, Zikang Zhang, Ethan Traister, Kewen Xie

Abstract: The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset, the first published dataset of GPT-image-2 generated images, sourced from publicly available Twitter/X posts in the immediate aftermath of the model's April 21,… ▽ More The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset, the first published dataset of GPT-image-2 generated images, sourced from publicly available Twitter/X posts in the immediate aftermath of the model's April 21, 2026 release. Leveraging the Twitter API v2 and a multi-stage curation pipeline spanning multilingual text heuristics (English, Japanese, and Chinese), browser-automated Twitter "Made with AI" badge verification, and model name variant matching, we curate 10,217 confirmed GPT-image-2 images from 27,662 collected records over a six-day window. We characterize the dataset across four analyses: CLIP-based zero-shot subject taxonomy, OCR text legibility (82.0% of images contain detectable text), face detection (59.2% of images, 22,583 total faces), and semantic clustering (137 CLIP ViT-L/14 clusters). A key negative result is that C2PA content credentials are systematically stripped by Twitter's CDN on upload, rendering cryptographic provenance verification infeasible for social-media-sourced AI images. The dataset and all curation code are released publicly. △ Less

Submitted 5 May, 2026; v1 submitted 28 April, 2026; originally announced April 2026.

Comments: 11 pages; GPT-image-2 social media dataset; Twitter API collection and multilingual curation; C2PA watermark stripping on platform upload; browser-automated AI badge verification; CLIP semantic clustering; AI-generated image provenance and attribution

MEDN: Motion-Emotion Feature Decoupling Network for Micro-Expression Recognition

Authors: Chenxing Hu, Kun Xie, Qiguang Miao, Ruyi Liu, Quan Wang, Zongkai Yang

Abstract: Unlike macro-expression, micro-expression does not follow a strictly consistent mapping rule between emotions and Action Units (AUs). As a result, some micro-expressions share identical AUs yet represent completely opposite emotional categories, making them highly visually similar. Existing microexpression recognition (MER) methods mostly rely on explicit facial motion cues (e.g., optical flow, fr… ▽ More Unlike macro-expression, micro-expression does not follow a strictly consistent mapping rule between emotions and Action Units (AUs). As a result, some micro-expressions share identical AUs yet represent completely opposite emotional categories, making them highly visually similar. Existing microexpression recognition (MER) methods mostly rely on explicit facial motion cues (e.g., optical flow, frame differences, AU features) while ignoring implicit emotion information. To tackle this issue, this paper presents a Motion Emotion Feature Decoupling Network (MEDN) for MER. We design a dual-branch framework to separately extract motion and emotion features. In the motion branch, an AU-detection task restricts features to the explicit motion domain, and orthogonal loss is adopted to reduce motion emotion feature coupling. For implicit emotion modeling, we propose a Sparse Emotion Vision Transformer (SEVit) that sparsifies spatial tokens to highlight local temporal variations with multi-scale sparsity rates. A Collaborative Fusion Module (CoFM) is further developed to fuse disentangled motion and emotion features adaptively. Extensive experiments on three benchmark datasets validate that MEDN effectively decouples motion and emotion features and achieves superior recognition performance, offering a new perspective for enhancing recognition accuracy and generalization. △ Less

Submitted 15 July, 2026; v1 submitted 20 April, 2026; originally announced April 2026.

Comments: 14 pages, 8 figures, 7 tabels

LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling

Authors: Keqin Xie

Abstract: Most current long-context language models still rely on attention to handle both local interaction and long-range state, which leaves relatively little room to test alternative decompositions of sequence modeling. We propose LPC-SM, a hybrid autoregressive architecture that separates local attention, persistent memory, predictive correction, and run-time control within the same block, and we use O… ▽ More Most current long-context language models still rely on attention to handle both local interaction and long-range state, which leaves relatively little room to test alternative decompositions of sequence modeling. We propose LPC-SM, a hybrid autoregressive architecture that separates local attention, persistent memory, predictive correction, and run-time control within the same block, and we use Orthogonal Novelty Transport (ONT) to govern slow-memory writes. We evaluate a 158M-parameter model in three stages spanning base language modeling, mathematical continuation, and 4096-token continuation. Removing mHC raises the Stage-A final LM loss from 12.630 to 15.127, while adaptive sparse control improves the Stage-B final LM loss from 12.137 to 10.787 relative to a matched fixed-ratio continuation. The full route remains stable at sequence length 4096, where Stage C ends with final LM loss 11.582 and improves the delayed-identifier diagnostic from 14.396 to 12.031 in key cross-entropy. Taken together, these results show that long-context autoregressive modeling can be organized around a broader division of labor than attention alone. △ Less

Submitted 12 March, 2026; originally announced April 2026.

Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rays

Authors: Kang Liu, Zhuoqi Ma, Siyu Liang, Yunan Li, Xiyue Gao, Chao Liang, Kun Xie, Qiguang Miao

Abstract: Despite recent advances in medical vision-language pretraining, existing models still struggle to capture the diagnostic workflow: radiographs are typically treated as context-agnostic images, while radiologists' gaze -- a crucial cue for visual reasoning -- remains largely underexplored by existing methods. These limitations hinder the modeling of disease-specific patterns and weaken cross-modal… ▽ More Despite recent advances in medical vision-language pretraining, existing models still struggle to capture the diagnostic workflow: radiographs are typically treated as context-agnostic images, while radiologists' gaze -- a crucial cue for visual reasoning -- remains largely underexplored by existing methods. These limitations hinder the modeling of disease-specific patterns and weaken cross-modal alignment. To bridge this gap, we introduce CoGaze, a Context- and Gaze-guided vision-language pretraining framework for chest X-rays. We first propose a context-infused vision encoder that models how radiologists integrate clinical context -- including patient history, symptoms, and diagnostic intent -- to guide diagnostic reasoning. We then present a multi-level supervision paradigm that (1) enforces intra- and inter-modal semantic alignment through hybrid-positive contrastive learning, (2) injects diagnostic priors via disease-aware cross-modal representation learning, and (3) leverages radiologists' gaze as probabilistic priors to guide attention toward diagnostically salient regions. Extensive experiments demonstrate that CoGaze consistently outperforms state-of-the-art methods across diverse tasks, achieving up to +2.0% CheXbertF1 and +1.2% BLEU2 for free-text and structured report generation, +23.2% AUROC for zero-shot classification, and +12.2% Precision@1 for image-text retrieval. Code is available at https://github.com/mk-runner/CoGaze. △ Less

Submitted 26 March, 2026; originally announced March 2026.

Comments: Code: https://github.com/mk-runner/CoGaze

VLM-AutoDrive: Post-Training Vision-Language Models for Safety-Critical Autonomous Driving Events

Authors: Mohammad Qazim Bhat, Yufan Huang, Niket Agarwal, Hao Wang, Michael Woods, John Kenyon, Tsung-Yi Lin, Xiaodong Yang, Ming-Yu Liu, Kevin Xie

Abstract: The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-collisions, scenarios that are brief, rare, and difficult for generic vision models to capture. While multimodal large language models (MLLMs) demonstrate strong general reasoning ability, they underperform in driving contexts due to domain and temporal misali… ▽ More The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-collisions, scenarios that are brief, rare, and difficult for generic vision models to capture. While multimodal large language models (MLLMs) demonstrate strong general reasoning ability, they underperform in driving contexts due to domain and temporal misalignment. We introduce VLM-AutoDrive, a modular post-training framework for adapting pretrained Vision-Language Models (VLMs) to high-fidelity anomaly detection. The framework integrates metadata-derived captions, LLM-generated descriptions, visual question answering (VQA) pairs, and chain-of-thought (CoT) reasoning supervision to enable domain-aligned and interpretable learning. Off-the-shelf VLMs such as NVIDIA's Cosmos-Reason1 7B (CR1) exhibit near-zero Collision recall in zero-shot settings; fine-tuning with VLM-AutoDrive improves Collision F1 from 0.00 to 0.69 and overall accuracy from 35.35% to 77.27%. VLM-AutoDrive offers a scalable recipe for adapting general-purpose VLMs to safety-critical, temporally localized perception tasks. Evaluated on real-world Nexar dashcam videos, it achieves substantial gains in Collision and Near-Collision detection while producing interpretable reasoning traces, bridging the gap between perception, causality, and decision reasoning in autonomous driving. △ Less

Submitted 15 May, 2026; v1 submitted 18 March, 2026; originally announced March 2026.

Comments: 16 pages, 9 figures, submitted to arXiv

Refining 3D Medical Segmentation with Verbal Instruction

Authors: Kangxian Xie, Jiancheng Yang, Nandor Pinter, Chao Wu, Behzad Bozorgtabar, Mingchen Gao

Abstract: Accurate 3D anatomical segmentation is essential for clinical diagnosis and surgical planning. However, automated models frequently generate suboptimal shape predictions due to factors such as limited and imbalanced training data, inadequate labeling quality, and distribution shifts between training and deployment settings. A natural solution is to iteratively refine the predicted shape based on t… ▽ More Accurate 3D anatomical segmentation is essential for clinical diagnosis and surgical planning. However, automated models frequently generate suboptimal shape predictions due to factors such as limited and imbalanced training data, inadequate labeling quality, and distribution shifts between training and deployment settings. A natural solution is to iteratively refine the predicted shape based on the radiologists' verbal instructions. However, this is hindered by the scarcity of paired data that explicitly links erroneous shapes to corresponding corrective instructions. As an initial step toward addressing this limitation, we introduce CoWTalk, a benchmark comprising 3D arterial anatomies with controllable synthesized anatomical errors and their corresponding repairing instructions. Building on this benchmark, we further propose an iterative refinement model that represents 3D shapes as vector sets and interacts with textual instructions to progressively update the target shape. Experimental results demonstrate that our method achieves significant improvements over corrupted inputs and competitive baselines, highlighting the feasibility of language-driven clinician-in-the-loop refinement for 3D medical shapes modeling. △ Less

Submitted 15 March, 2026; originally announced March 2026.

Volumetric Directional Diffusion: Anchoring Uncertainty Quantification in Anatomical Consensus for Ambiguous Medical Image Segmentation

Authors: Chao Wu, Mahesh Bhosale, Kangxian Xie, Pouya Karimian, David Doermann, Mingchen Gao

Abstract: Ambiguous 3D medical image segmentation often involves boundaries where different expert delineations are non-identical yet clinically plausible. Modeling such inter-observer variability requires a careful balance between diversity and anatomical fidelity: deterministic models preserve coherent volumetric structures but collapse expert disagreement into a single mask, while stochastic generative m… ▽ More Ambiguous 3D medical image segmentation often involves boundaries where different expert delineations are non-identical yet clinically plausible. Modeling such inter-observer variability requires a careful balance between diversity and anatomical fidelity: deterministic models preserve coherent volumetric structures but collapse expert disagreement into a single mask, while stochastic generative models can produce diverse samples but may introduce disconnected components or slice-to-slice inconsistency when generating full 3D masks from unstructured noise. We propose Volumetric Directional Diffusion (VDD), a prior-anchored diffusion framework that shifts stochastic generation from full-mask synthesis to residual boundary exploration. VDD uses a coarse consensus prediction as an anatomical anchor and learns a directional diffusion process to generate plausible boundary variations around ambiguous regions while preserving stable volumetric topology. Experiments on three multi-rater datasets, including LIDC-IDRI, KiTS21, and ISBI 2015, show that VDD improves uncertainty distribution alignment while maintaining competitive segmentation accuracy and 3D structural consistency. These results suggest that prior-anchored residual diffusion can model clinically plausible expert disagreement without sacrificing anatomical fidelity. △ Less

Submitted 7 July, 2026; v1 submitted 4 March, 2026; originally announced March 2026.

Mozi: Governed Autonomy for Drug Discovery LLM Agents

Authors: He Cao, Siyu Liu, Fan Zhang, Zijing Liu, Hao Li, Bin Feng, Shengyuan Bai, Leqing Chen, Kai Xie, Yu Li

Abstract: Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlenecked by two critical barriers: unconstrained tool-use governance and poor long-horizon reliability. In dependency-heavy pharmaceutical pipelines, autonomous agents often drift into irreproducible trajectories, where earl… ▽ More Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlenecked by two critical barriers: unconstrained tool-use governance and poor long-horizon reliability. In dependency-heavy pharmaceutical pipelines, autonomous agents often drift into irreproducible trajectories, where early-stage hallucinations multiplicatively compound into downstream failures. To overcome this, we present Mozi, a dual-layer architecture that bridges the flexibility of generative AI with the deterministic rigor of computational biology. Layer A (Control Plane) establishes a governed supervisor--worker hierarchy that enforces role-based tool isolation, limits execution to constrained action spaces, and drives reflection-based replanning. Layer B (Workflow Plane) operationalizes canonical drug discovery stages -- from Target Identification to Lead Optimization -- as stateful, composable skill graphs. This layer integrates strict data contracts and strategic human-in-the-loop (HITL) checkpoints to safeguard scientific validity at high-uncertainty decision boundaries. Operating on the design principle of ``free-form reasoning for safe tasks, structured execution for long-horizon pipelines,'' Mozi provides built-in robustness mechanisms and trace-level audibility to completely mitigate error accumulation. We evaluate Mozi on PharmaBench, a curated benchmark for biomedical agents, demonstrating superior orchestration accuracy over existing baselines. Furthermore, through end-to-end therapeutic case studies, we demonstrate Mozi's ability to navigate massive chemical spaces, enforce stringent toxicity filters, and generate highly competitive in silico candidates, effectively transforming the LLM from a fragile conversationalist into a reliable, governed co-scientist. △ Less

Submitted 3 March, 2026; originally announced March 2026.

Multimodal Adversarial Quality Policy for Safe Grasping

Authors: Kunlin Xie, Chenghao Li, Haolan Zhang, Nak Young Chong

Abstract: Vision-guided robot grasping based on Deep Neural Networks (DNNs) generalizes well but poses safety risks in the Human-Robot Interaction (HRI). Recent works solved it by designing benign adversarial attacks and patches with RGB modality, yet depth-independent characteristics limit their effectiveness on RGBD modality. In this work, we propose the Multimodal Adversarial Quality Policy (MAQP) to rea… ▽ More Vision-guided robot grasping based on Deep Neural Networks (DNNs) generalizes well but poses safety risks in the Human-Robot Interaction (HRI). Recent works solved it by designing benign adversarial attacks and patches with RGB modality, yet depth-independent characteristics limit their effectiveness on RGBD modality. In this work, we propose the Multimodal Adversarial Quality Policy (MAQP) to realize multimodal safe grasping. Our framework introduces two key components. First, the Heterogeneous Dual-Patch Optimization Scheme (HDPOS) mitigates the distribution discrepancy between RGB and depth modalities in patch generation by adopting modality-specific initialization strategies, employing a Gaussian distribution for depth patches and a uniform distribution for RGB patches, while jointly optimizing both modalities under a unified objective function. Second, the Gradient-Level Modality Balancing Strategy (GLMBS) is designed to resolve the optimization imbalance from RGB and Depth patches in patch shape adaptation by reweighting gradient contributions based on per-channel sensitivity analysis and applying distance-adaptive perturbation bounds. We conduct extensive experiments on the benchmark datasets and a cobot, showing the effectiveness of MAQP. △ Less

Submitted 9 March, 2026; v1 submitted 2 March, 2026; originally announced March 2026.

Comments: submitted

MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusion

Authors: Dongyang Li, Kunpeng Xie, Mingyang Wu, Yiwei Kong, Jiahua Tang, Haoyang Qin, Chen Wei, Quanying Liu

Abstract: Whereas most brain-computer interface research has focused on decoding neural signals into behavior or intent, the reverse challenge-using controlled stimuli to steer brain activity-remains far less understood, particularly in the visual domain. However, designing images that consistently elicit desired neural responses is difficult: subjective states lack clear quantitative measures, and EEG feed… ▽ More Whereas most brain-computer interface research has focused on decoding neural signals into behavior or intent, the reverse challenge-using controlled stimuli to steer brain activity-remains far less understood, particularly in the visual domain. However, designing images that consistently elicit desired neural responses is difficult: subjective states lack clear quantitative measures, and EEG feedback is both noisy and non-differentiable. We introduce MindPilot, the first closed-loop framework that uses EEG signals as optimization feedback to guide naturalistic image generation. Unlike prior work limited to invasive settings or low-level flicker stimuli, MindPilot leverages non-invasive EEG with natural images, treating the brain as a black-box function and employing a pseudo-model guidance mechanism to iteratively refine images without requiring explicit rewards or gradients. We validate MindPilot in both simulation and human experiments, demonstrating (i) efficient retrieval of semantic targets, (ii) closed-loop optimization of EEG features, and (iii) human-subject validations in mental matching and emotion regulation tasks. Our results establish the feasibility of EEG-guided image synthesis and open new avenues for non-invasive closed-loop brain modulation, bidirectional brain-computer interfaces, and neural signal-guided generative modeling. △ Less

Submitted 21 July, 2026; v1 submitted 11 February, 2026; originally announced February 2026.

Comments: 10 pages

Learning Topology-Aware Implicit Field for Unified Pulmonary Tree Modeling with Incomplete Topological Supervision

Authors: Ziqiao Weng, Jiancheng Yang, Kangxian Xie, Bo Zhou, Weidong Cai

Abstract: Pulmonary trees extracted from CT images frequently exhibit topological incompleteness, such as missing or disconnected branches, which substantially degrades downstream anatomical analysis and limits the applicability of existing pulmonary tree modeling pipelines. Current approaches typically rely on dense volumetric processing, explicit graph reasoning, or generic point cloud completion priors,… ▽ More Pulmonary trees extracted from CT images frequently exhibit topological incompleteness, such as missing or disconnected branches, which substantially degrades downstream anatomical analysis and limits the applicability of existing pulmonary tree modeling pipelines. Current approaches typically rely on dense volumetric processing, explicit graph reasoning, or generic point cloud completion priors, leading to limited efficiency, weak structural awareness, and reduced robustness under realistic structural corruption. We propose TopoField, a topology-aware implicit modeling framework that treats topology repair as a first-class modeling problem and enables unified multi-task inference for pulmonary tree analysis. TopoField represents pulmonary anatomy using sparse surface and skeleton point clouds and learns a continuous implicit field that supports topology repair without relying on complete or explicit disconnection annotations, by training on synthetically introduced structural disruptions over \textit{already} incomplete trees. Building upon the repaired implicit representation, anatomical labeling and lung segment reconstruction are jointly inferred through task-specific implicit functions within a single forward pass. Extensive experiments on the Lung3D+ dataset demonstrate that TopoField consistently improves topological completeness and achieves accurate anatomical labeling and lung segment reconstruction under challenging incomplete scenarios. We further validate TopoField on real incomplete outputs from an external segmentation model, demonstrating its applicability to realistic segmentation pipelines. Owing to its implicit formulation, TopoField attains high computational efficiency, completing all tasks in just over one second per case, highlighting its practicality for large-scale and time-sensitive clinical applications. △ Less

Submitted 15 June, 2026; v1 submitted 2 February, 2026; originally announced February 2026.

Comments: 20 pages

RoboBrain 2.5: Depth in Sight, Time in Mind

Authors: Huajie Tan, Enshen Zhou, Zhiyu Li, Yijie Xu, Yuheng Ji, Xiansheng Chen, Cheng Chi, Pengwei Wang, Huizhu Jia, Yulong Ao, Mingyu Cao, Sixiang Chen, Zhe Li, Mengzhen Liu, Zixiao Wang, Shanyu Rong, Yaoxu Lyu, Zhongxia Zhao, Peterson Co, Yibo Li, Yi Han, Shaoxuan Xie, Guocai Yao, Songjing Wang, Leiduo Zhang , et al. (10 additional authors not shown)

Abstract: We introduce RoboBrain 2.5, a next-generation embodied AI foundation model that advances general perception, spatial reasoning, and temporal modeling through extensive training on high-quality spatiotemporal supervision. Building upon its predecessor, RoboBrain 2.5 introduces two major capability upgrades. Specifically, it unlocks Precise 3D Spatial Reasoning by shifting from 2D pixel-relative gro… ▽ More We introduce RoboBrain 2.5, a next-generation embodied AI foundation model that advances general perception, spatial reasoning, and temporal modeling through extensive training on high-quality spatiotemporal supervision. Building upon its predecessor, RoboBrain 2.5 introduces two major capability upgrades. Specifically, it unlocks Precise 3D Spatial Reasoning by shifting from 2D pixel-relative grounding to depth-aware coordinate prediction and absolute metric constraint comprehension, generating complete 3D manipulation traces as ordered keypoint sequences under physical constraints. Complementing this spatial precision, the model establishes Dense Temporal Value Estimation that provides dense, step-aware progress prediction and execution state understanding across varying viewpoints, producing stable feedback signals for downstream learning. Together, these upgrades extend the framework toward more physically grounded and execution-aware embodied intelligence for complex, fine-grained manipulation. The code and checkpoints are available at project website: https://superrobobrain.github.io △ Less

Submitted 20 January, 2026; originally announced January 2026.

Comments: 37 pages, 13 figures, Technical Report

CellularSpecSec-Bench: A Staged Benchmark for Evidence-Grounded Interpretation and Security Reasoning over 3GPP Specifications

Authors: Ke Xie, Xingyi Zhao, Yiwen Hu, Shuhan Yuan, Tian Xie

Abstract: Cellular networks are critical infrastructure supporting billions of worldwide users and safety- and mission-critical services. Vulnerabilities in cellular networks can therefore cause service disruption, privacy breaches, and broad societal harm, motivating growing efforts to analyze 3GPP specifications that define required device and operator behavior. While large language models (LLMs) have dem… ▽ More Cellular networks are critical infrastructure supporting billions of worldwide users and safety- and mission-critical services. Vulnerabilities in cellular networks can therefore cause service disruption, privacy breaches, and broad societal harm, motivating growing efforts to analyze 3GPP specifications that define required device and operator behavior. While large language models (LLMs) have demonstrated the capability for reading technical documents, cellular specifications impose unique challenges: faithful interpretation of normative language, reasoning across cross-referenced clauses, and verifiable conclusions grounded in multimodal evidence such as tables and figures. To address these challenges, we propose CellSpecSec-ARI, a unified Adapt-Retrieve-Integrate framework for systematic understanding and standard-driven security analysis of 3GPP specifications; CellularSpecSec-Bench, a staged benchmark, containing newly constructed high-quality datasets with expert-verified and corrected subsets from prior open-source resources. Together, they establish an accessible and reproducible foundation for quantifying progress in specification understanding and security reasoning in the cellular network security domain. △ Less

Submitted 18 January, 2026; originally announced January 2026.

LEMAS: Large A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models

Authors: Zhiyuan Zhao, Lijian Lin, Ye Zhu, Kai Xie, Yunfei Liu, Yu Li

Abstract: We present the LEMAS-Dataset, which, to our knowledge, is currently the largest open-source multilingual speech corpus with word-level timestamps. Covering over 150,000 hours across 10 major languages, LEMAS-Dataset is constructed via a efficient data processing pipeline that ensures high-quality data and annotations. To validate the effectiveness of LEMAS-Dataset across diverse generative paradig… ▽ More We present the LEMAS-Dataset, which, to our knowledge, is currently the largest open-source multilingual speech corpus with word-level timestamps. Covering over 150,000 hours across 10 major languages, LEMAS-Dataset is constructed via a efficient data processing pipeline that ensures high-quality data and annotations. To validate the effectiveness of LEMAS-Dataset across diverse generative paradigms, we train two benchmark models with distinct architectures and task specializations on this dataset. LEMAS-TTS, built upon a non-autoregressive flow-matching framework, leverages the dataset's massive scale and linguistic diversity to achieve robust zero-shot multilingual synthesis. Our proposed accent-adversarial training and CTC loss mitigate cross-lingual accent issues, enhancing synthesis stability. Complementarily, LEMAS-Edit employs an autoregressive decoder-only architecture that formulates speech editing as a masked token infilling task. By exploiting precise word-level alignments to construct training masks and adopting adaptive decoding strategies, it achieves seamless, smooth-boundary speech editing with natural transitions. Experimental results demonstrate that models trained on LEMAS-Dataset deliver high-quality synthesis and editing performance, confirming the dataset's quality. We envision that this richly timestamp-annotated, fine-grained multilingual corpus will drive future advances in prompt-based speech generation systems. △ Less

Submitted 3 January, 2026; originally announced January 2026.

Comments: Demo page: https://lemas-project.github.io/LEMAS-Project

A Vision-and-Knowledge Enhanced Large Language Model for Generalizable Pedestrian Crossing Behavior Inference

Authors: Qingwen Pu, Kun Xie, Hong Yang, Guocong Zhai

Abstract: Existing paradigms for inferring pedestrian crossing behavior, ranging from statistical models to supervised learning methods, demonstrate limited generalizability and perform inadequately on new sites. Recent advances in Large Language Models (LLMs) offer a shift from numerical pattern fitting to semantic, context-aware behavioral reasoning, yet existing LLM applications lack domain-specific adap… ▽ More Existing paradigms for inferring pedestrian crossing behavior, ranging from statistical models to supervised learning methods, demonstrate limited generalizability and perform inadequately on new sites. Recent advances in Large Language Models (LLMs) offer a shift from numerical pattern fitting to semantic, context-aware behavioral reasoning, yet existing LLM applications lack domain-specific adaptation and visual context. This study introduces Pedestrian Crossing LLM (PedX-LLM), a vision-and-knowledge enhanced framework designed to transform pedestrian crossing inference from site-specific pattern recognition to generalizable behavioral reasoning. By integrating LLaVA-extracted visual features with textual data and transportation domain knowledge, PedX-LLM fine-tunes a LLaMA-2-7B foundation model via Low-Rank Adaptation (LoRA) to infer crossing decisions. PedX-LLM achieves 82.0% balanced accuracy, outperforming the best statistical and supervised learning methods. Results demonstrate that the vision-augmented module contributes a 2.9% performance gain by capturing the built environment and integrating domain knowledge yields an additional 4.1% improvement. To evaluate generalizability across unseen environments, cross-site validation was conducted using site-based partitioning. The zero-shot PedX-LLM configuration achieves 66.9% balanced accuracy on five unseen test sites, outperforming the baseline data-driven methods by at least 18 percentage points. Incorporating just five validation examples via few-shot learning to PedX-LLM further elevates the balanced accuracy to 72.2%. PedX-LLM demonstrates strong generalizability to unseen scenarios, confirming that vision-and-knowledge-enhanced reasoning enables the model to mimic human-like decision logic and overcome the limitations of purely data-driven methods. △ Less

Submitted 2 January, 2026; originally announced January 2026.

Constructing a Neuro-Symbolic Mathematician from First Principles

Authors: Keqin Xie

Abstract: Large Language Models (LLMs) exhibit persistent logical failures in complex reasoning due to the lack of an internal axiomatic framework. We propose Mathesis, a neuro-symbolic architecture that encodes mathematical states as higher-order hypergraphs and uses a Symbolic Reasoning Kernel (SRK)--a differentiable logic engine that maps constraints to a continuous energy landscape. By defining a global… ▽ More Large Language Models (LLMs) exhibit persistent logical failures in complex reasoning due to the lack of an internal axiomatic framework. We propose Mathesis, a neuro-symbolic architecture that encodes mathematical states as higher-order hypergraphs and uses a Symbolic Reasoning Kernel (SRK)--a differentiable logic engine that maps constraints to a continuous energy landscape. By defining a global energy function E(G), where zero energy implies logical consistency, the SRK yields gradient-based signals to train a Hypergraph Transformer Brain, turning proof search into energy minimization. Multi-step deduction is enabled via Monte Carlo Tree Search and Evolutionary Proof Search, guided by learned value functions and semantic unification. △ Less

Submitted 31 December, 2025; originally announced January 2026.

CellSecInspector: Safeguarding Cellular Networks via Automated Security Analysis on Specifications

Authors: Ke Xie, Xingyi Zhao, Min-Yue Chen, Yu-An Chen, Yiwen Hu, Munshi Saifuzzaman, Wen Li, Shuhan Yuan, Guan-Hua Tu, Tian Xie

Abstract: The complexity, interdependence, and rapid evolution of 3GPP specifications present fundamental challenges for ensuring the security of modern cellular networks. Manual reviews and existing automated approaches, which often depend on rule-based parsing or small sets of manually crafted security requirements, fail to capture deep semantic dependencies, cross-sentence/clause relationships, and evolv… ▽ More The complexity, interdependence, and rapid evolution of 3GPP specifications present fundamental challenges for ensuring the security of modern cellular networks. Manual reviews and existing automated approaches, which often depend on rule-based parsing or small sets of manually crafted security requirements, fail to capture deep semantic dependencies, cross-sentence/clause relationships, and evolving specification behaviors. In this work, we present CellSecInspector, an automated framework for security analysis of 3GPP specifications. CellSecInspector extracts structured state-condition-action (SCA) representations, models mobile network procedures with comprehensive function chains, systematically validates them against 9 foundational security properties under 4 adversarial scenarios, and automatically generates test cases. This end-to-end approach enables the automated discovery of vulnerabilities without relying on manually predefined security requirements or rules. Applying CellSecInspector to the well-studied 5G and 4G NAS and RRC specifications and selected sections of TS 23.501 and TS 24.229, it discovers 43 vulnerabilities, 7 of which are previously unreported. Our findings show that CellSecInspector is a scalable, adaptive, and effective solution to assess 3GPP specifications for safeguarding operational and next-generation cellular networks. △ Less

Submitted 31 March, 2026; v1 submitted 31 December, 2025; originally announced December 2025.

The Alignment Paradox of Medical Large Language Models in Infertility Care: Decoupling Algorithmic Improvement from Clinical Decision-making Quality

Authors: Dou Liu, Ying Long, Sophia Zuoqiu, Kaipeng Xie, Runze Yang, Di Liu, Kang Li, Yiting Lin, Hanyi Liu, Rong Yin, Tian Tang

Abstract: Large language models (LLMs) are increasingly adopted in clinical decision support, yet aligning them with the multifaceted reasoning pathways of real-world medicine remains a major challenge. Using more than 8,000 infertility treatment records, we systematically evaluate four alignment strategies: Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), Group Relative Policy Optimizati… ▽ More Large language models (LLMs) are increasingly adopted in clinical decision support, yet aligning them with the multifaceted reasoning pathways of real-world medicine remains a major challenge. Using more than 8,000 infertility treatment records, we systematically evaluate four alignment strategies: Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), Group Relative Policy Optimization (GRPO), and In-Context Learning (ICL) through a dual-layer framework combining automatic benchmarks with blinded doctor-in-the-loop assessments. GRPO achieves the highest algorithmic accuracy across multiple decision layers, confirming the value of reinforcement-based optimization for structured prediction tasks. However, clinicians consistently prefer the SFT model, citing clearer reasoning processes (p = 0.035) and higher therapeutic feasibility (p = 0.019). In blinded pairwise comparisons, SFT attains the highest winning rate (51.2%), outperforming both GRPO (26.2%) and even physicians' original decisions (22.7%). These results reveal an alignment paradox: algorithmic improvements do not necessarily translate into higher clinical trust, and may diverge from human-centered preferences. Our findings highlight the need for alignment strategies that prioritize clinically interpretable and practically feasible reasoning, rather than solely optimizing decision-level accuracy. △ Less

Submitted 22 November, 2025; originally announced November 2025.

Comments: 22 pages 5 figures

OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios

Authors: Hong Gao, Jingyu Wu, Xiangkai Xu, Kangni Xie, Yunchen Zhang, Bin Zhong, Xurui Gao, Min-Ling Zhang

Abstract: Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. Despite recent advances in Multimodal Large Language Models, a significant gap remains between current models and real-world demands involving diverse objects and complex queries. We attribute this to limited benchmark scope, causing models to exhibit category bias, oversimplifi… ▽ More Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. Despite recent advances in Multimodal Large Language Models, a significant gap remains between current models and real-world demands involving diverse objects and complex queries. We attribute this to limited benchmark scope, causing models to exhibit category bias, oversimplified reasoning, and poor linguistic robustness. To address these limitations, we introduce OmniGround, a comprehensive benchmark with 3,475 videos spanning 81 categories and complex real-world queries. We propose the Forward-Backward-Refinement annotation pipeline that combines multi-directional tracking with intelligent error correction for high-quality labels. We further introduce DeepSTG, a systematic evaluation framework quantifying dataset quality across four complementary dimensions beyond superficial statistics. Evaluations reveal performance average drop of 10.4% on complex real-world scenes, particularly with small/occluded objects and intricate spatial relations. Motivated by these, we propose PG-TAF, a training-free two-stage framework decomposing STVG into high-level temporal grounding and fine-grained spatio-temporal propagation. Experiments demonstrate PG-TAF achieves 25.6% and 35.6% improvements in m\_tIoU and m\_vIoU on OmniGround with consistent gains across four benchmarks. △ Less

Submitted 20 November, 2025; originally announced November 2025.

Comments: 20 pages

The Economics of AI Foundation Models: Openness, Competition, and Governance

Authors: Fasheng Xu, Xiaoyu Wang, Wei Chen, Karen Xie

Abstract: The strategic choice of model "openness" has become a defining issue for the foundation model (FM) ecosystem. While this choice is intensely debated, its underlying economic drivers remain underexplored. We construct a two-period game-theoretic model to analyze how openness shapes competition in an AI value chain, featuring an incumbent developer, a downstream deployer, and an entrant developer. O… ▽ More The strategic choice of model "openness" has become a defining issue for the foundation model (FM) ecosystem. While this choice is intensely debated, its underlying economic drivers remain underexplored. We construct a two-period game-theoretic model to analyze how openness shapes competition in an AI value chain, featuring an incumbent developer, a downstream deployer, and an entrant developer. Openness exerts a dual effect: it amplifies knowledge spillovers to the entrant, but it also enhances the incumbent's advantage through a "data flywheel effect," whereby greater user engagement today further lowers the deployer's future fine-tuning cost. Our analysis reveals that the incumbent's optimal first-period openness is surprisingly non-monotonic in the strength of the data flywheel effect. When the data flywheel effect is either weak or very strong, the incumbent prefers a higher level of openness; however, for an intermediate range, it strategically restricts openness to impair the entrant's learning. This dynamic gives rise to an "openness trap," a critical policy paradox where transparency mandates can backfire by removing firms' strategic flexibility, reducing investment, and lowering welfare. We extend the model to show that other common interventions can be similarly ineffective. Vertical integration, for instance, only benefits the ecosystem when the data flywheel effect is strong enough to overcome the loss of a potentially more efficient competitor. Likewise, government subsidies intended to spur adoption can be captured entirely by the incumbent through strategic price and openness adjustments, leaving the rest of the value chain worse off. By modeling the developer's strategic response to competitive and regulatory pressures, we provide a robust framework for analyzing competition and designing effective policy in the complex and rapidly evolving FM ecosystem. △ Less

Submitted 16 October, 2025; originally announced October 2025.

Aerial Path Planning for Urban Geometry and Texture Co-Capture

Authors: Weidan Xiong, Bochuan Zeng, Ziyu Hu, Jianwei Guo, Ke Xie, Hui Huang

Abstract: Recent advances in image acquisition and scene reconstruction have enabled the generation of high-quality structural urban scene geometry, given sufficient site information. However, current capture techniques often overlook the crucial importance of texture quality, resulting in noticeable visual artifacts in the textured models. In this work, we introduce the urban geometry and texture co-captur… ▽ More Recent advances in image acquisition and scene reconstruction have enabled the generation of high-quality structural urban scene geometry, given sufficient site information. However, current capture techniques often overlook the crucial importance of texture quality, resulting in noticeable visual artifacts in the textured models. In this work, we introduce the urban geometry and texture co-capture problem under limited prior knowledge before a site visit. The only inputs are a 2D building contour map of the target area and a safe flying altitude above the buildings. We propose an innovative aerial path planning framework designed to co-capture images for reconstructing both structured geometry and high-fidelity textures. To evaluate and guide view planning, we introduce a comprehensive texture quality assessment system, including two novel metrics tailored for building facades. Firstly, our method generates high-quality vertical dipping views and horizontal planar views to effectively capture both geometric and textural details. A multi-objective optimization strategy is then proposed to jointly maximize texture fidelity, improve geometric accuracy, and minimize the cost associated with aerial views. Furthermore, we present a sequential path planning algorithm that accounts for texture consistency during image capture. Extensive experiments on large-scale synthetic and real-world urban datasets demonstrate that our approach effectively produces image sets suitable for concurrent geometric and texture reconstruction, enabling the creation of realistic, textured scene proxies at low operational cost. △ Less

Submitted 26 September, 2025; originally announced September 2025.

Comments: ACM TOG and SIGGRAPH Asia 2025 (Patent Protected); Project page: https://vcc.tech/research/2025/DroneTex

Why Chain of Thought Fails in Clinical Text Understanding

Authors: Jiageng Wu, Kevin Xie, Bowen Gu, Nils Krüger, Kueiyu Joshua Lin, Jie Yang

Abstract: Large language models (LLMs) are increasingly being applied to clinical care, a domain where both accuracy and transparent reasoning are critical for safe and trustworthy deployment. Chain-of-thought (CoT) prompting, which elicits step-by-step reasoning, has demonstrated improvements in performance and interpretability across a wide range of tasks. However, its effectiveness in clinical contexts r… ▽ More Large language models (LLMs) are increasingly being applied to clinical care, a domain where both accuracy and transparent reasoning are critical for safe and trustworthy deployment. Chain-of-thought (CoT) prompting, which elicits step-by-step reasoning, has demonstrated improvements in performance and interpretability across a wide range of tasks. However, its effectiveness in clinical contexts remains largely unexplored, particularly in the context of electronic health records (EHRs), the primary source of clinical documentation, which are often lengthy, fragmented, and noisy. In this work, we present the first large-scale systematic study of CoT for clinical text understanding. We assess 95 advanced LLMs on 87 real-world clinical text tasks, covering 9 languages and 8 task types. Contrary to prior findings in other domains, we observe that 86.3\% of models suffer consistent performance degradation in the CoT setting. More capable models remain relatively robust, while weaker ones suffer substantial declines. To better characterize these effects, we perform fine-grained analyses of reasoning length, medical concept alignment, and error profiles, leveraging both LLM-as-a-judge evaluation and clinical expert evaluation. Our results uncover systematic patterns in when and why CoT fails in clinical contexts, which highlight a critical paradox: CoT enhances interpretability but may undermine reliability in clinical text tasks. This work provides an empirical basis for clinical reasoning strategies of LLMs, highlighting the need for transparent and trustworthy approaches. △ Less

Submitted 8 December, 2025; v1 submitted 26 September, 2025; originally announced September 2025.

Enhancing Molecular Property Prediction with Knowledge from Large Language Models

Authors: Peng Zhou, Lai Hou Tim, Zhixiang Cheng, Kun Xie, Chaoyi Li, Wei Liu, Xiangxiang Zeng

Abstract: Predicting molecular properties is a critical component of drug discovery. Recent advances in deep learning, particularly Graph Neural Networks (GNNs), have enabled end-to-end learning from molecular structures, reducing reliance on manual feature engineering. However, while GNNs and self-supervised learning approaches have advanced molecular property prediction (MPP), the integration of human pri… ▽ More Predicting molecular properties is a critical component of drug discovery. Recent advances in deep learning, particularly Graph Neural Networks (GNNs), have enabled end-to-end learning from molecular structures, reducing reliance on manual feature engineering. However, while GNNs and self-supervised learning approaches have advanced molecular property prediction (MPP), the integration of human prior knowledge remains indispensable, as evidenced by recent methods that leverage large language models (LLMs) for knowledge extraction. Despite their strengths, LLMs are constrained by knowledge gaps and hallucinations, particularly for less-studied molecular properties. In this work, we propose a novel framework that, for the first time, integrates knowledge extracted from LLMs with structural features derived from pre-trained molecular models to enhance MPP. Our approach prompts LLMs to generate both domain-relevant knowledge and executable code for molecular vectorization, producing knowledge-based features that are subsequently fused with structural representations. We employ three state-of-the-art LLMs, GPT-4o, GPT-4.1, and DeepSeek-R1, for knowledge extraction. Extensive experiments demonstrate that our integrated method outperforms existing approaches, confirming that the combination of LLM-derived knowledge and structural information provides a robust and effective solution for MPP. △ Less

Submitted 24 September, 2025; originally announced September 2025.

Comments: 9 pages, 5 figures

The Impact of Structural Changes on Learning Capacity in the Fly Olfactory Neural Circuit

Authors: Katherine Xie, Gabriel Koch Ocker

Abstract: The Drosophila mushroom body (MB) is known to be involved in olfactory learning and memory; the synaptic plasticity of the Kenyon cell (KC) to mushroom body output neuron (MBON) synapses plays a key role in the learning process. Previous research has focused on projection neuron (PN) to Kenyon cell (KC) connectivity within the MB; we examine how perturbations to the mushroom body circuit structure… ▽ More The Drosophila mushroom body (MB) is known to be involved in olfactory learning and memory; the synaptic plasticity of the Kenyon cell (KC) to mushroom body output neuron (MBON) synapses plays a key role in the learning process. Previous research has focused on projection neuron (PN) to Kenyon cell (KC) connectivity within the MB; we examine how perturbations to the mushroom body circuit structure and changes in connectivity, specifically within the KC to mushroom body output neuron (MBON) neural circuit, affect the MBONs' ability to distinguish between odor classes. We constructed a neural network that incorporates the connectivity between PNs, KCs, and MBONs. To train our model, we generated ten artificial input classes, which represent the projection neuron activity in response to different odors. We collected data on the number of KC-to-MBON connections, MBON error rates, and KC-to-MBON synaptic weights, among other metrics. We observed that MBONs with very few presynaptic KCs consistently performed worse than others in the odor classification task. The developmental types of KCs also played a significant role in each MBON's output. We performed random and targeted KC ablation and observed that ablating developmentally mature KCs had a greater negative impact on MBONs' learning capacity than ablating immature KCs. Random and targeted pruning of KC-MBON synaptic connections yielded results largely consistent with the ablation experiments. To further explore the various types of KCs, we also performed rewiring experiments in the PN to KC circuit. Our study furthers our understanding of olfactory neuroplasticity and provides important clues to understanding learning and memory in general. Understanding how the olfactory circuits process and learn can also have potential applications in artificial intelligence and treatments for neurodegenerative diseases. △ Less

Submitted 17 September, 2025; originally announced September 2025.

VQT-Light:Lightweight HDR Illumination Map Prediction with Richer Texture.pdf

Authors: Kunliang Xie

Abstract: Accurate lighting estimation is a significant yet challenging task in computer vision and graphics. However, existing methods either struggle to restore detailed textures of illumination map, or face challenges in running speed and texture fidelity. To tackle this problem, we propose a novel framework (VQT-Light) based on VQVAE and ViT architecture. VQT-Light includes two modules: feature extracti… ▽ More Accurate lighting estimation is a significant yet challenging task in computer vision and graphics. However, existing methods either struggle to restore detailed textures of illumination map, or face challenges in running speed and texture fidelity. To tackle this problem, we propose a novel framework (VQT-Light) based on VQVAE and ViT architecture. VQT-Light includes two modules: feature extraction and lighting estimation. First, we take advantages of VQVAE to extract discrete features of illumination map rather than continuous features to avoid "posterior collapse". Second, we capture global context and dependencies of input image through ViT rather than CNNs to improve the prediction of illumination outside the field of view. Combining the above two modules, we formulate the lighting estimation as a multiclass classification task, which plays a key role in our pipeline. As a result, our model predicts light map with richer texture and better fidelity while keeping lightweight and fast. VQT-Light achieves an inference speed of 40FPS and improves multiple evaluation metrics. Qualitative and quantitative experiments demonstrate that the proposed method realizes superior results compared to existing state-of-the-art methods. △ Less

Submitted 15 September, 2025; originally announced September 2025.

Comments: 11 pages, 8 figures

FireRedChat: A Pluggable, Full-Duplex Voice Interaction System with Cascaded and Semi-Cascaded Implementations

Authors: Junjie Chen, Yao Hu, Junjie Li, Kangyue Li, Kun Liu, Wenpeng Li, Xu Li, Ziyuan Li, Feiyu Shen, Xu Tang, Manzhen Wei, Yichen Wu, Fenglong Xie, Kaituo Xu, Kun Xie

Abstract: Full-duplex voice interaction allows users and agents to speak simultaneously with controllable barge-in, enabling lifelike assistants and customer service. Existing solutions are either end-to-end, difficult to design and hard to control, or modular pipelines governed by turn-taking controllers that ease upgrades and per-module optimization; however, prior modular frameworks depend on non-open co… ▽ More Full-duplex voice interaction allows users and agents to speak simultaneously with controllable barge-in, enabling lifelike assistants and customer service. Existing solutions are either end-to-end, difficult to design and hard to control, or modular pipelines governed by turn-taking controllers that ease upgrades and per-module optimization; however, prior modular frameworks depend on non-open components and external providers, limiting holistic optimization. In this work, we present a complete, practical full-duplex voice interaction system comprising a turn-taking controller, an interaction module, and a dialogue manager. The controller integrates streaming personalized VAD (pVAD) to suppress false barge-ins from noise and non-primary speakers, precisely timestamp primary-speaker segments, and explicitly enable primary-speaker barge-ins; a semantic end-of-turn detector improves stop decisions. It upgrades heterogeneous half-duplex pipelines, cascaded, semi-cascaded, and speech-to-speech, to full duplex. Using internal models, we implement cascaded and semi-cascaded variants; the semi-cascaded one captures emotional and paralinguistic cues, yields more coherent responses, lowers latency and error propagation, and improves robustness. A dialogue manager extends capabilities via tool invocation and context management. We also propose three system-level metrics, barge-in, end-of-turn detection accuracy, and end-to-end latency, to assess naturalness, control accuracy, and efficiency. Experiments show fewer false interruptions, more accurate semantic ends, and lower latency approaching industrial systems, enabling robust, natural, real-time full-duplex interaction. Demos: https://fireredteam.github.io/demos/firered_chat. △ Less

Submitted 8 September, 2025; originally announced September 2025.

Comments: 12 pages, 2 figures

FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot

Authors: Kun Xie, Feiyu Shen, Junjie Li, Fenglong Xie, Xu Tang, Yao Hu

Abstract: Current dialogue generation approaches typically require the complete dialogue text before synthesis and produce a single, inseparable speech containing all voices, making them unsuitable for interactive chat; moreover, they suffer from unstable synthesis, inaccurate speaker transitions, and incoherent prosody. In this work, we present FireRedTTS-2, a long-form streaming TTS system for multi-speak… ▽ More Current dialogue generation approaches typically require the complete dialogue text before synthesis and produce a single, inseparable speech containing all voices, making them unsuitable for interactive chat; moreover, they suffer from unstable synthesis, inaccurate speaker transitions, and incoherent prosody. In this work, we present FireRedTTS-2, a long-form streaming TTS system for multi-speaker dialogue generation, delivering stable, natural speech with reliable speaker switching and context-aware prosody. A new 12.5Hz streaming speech tokenizer accelerates training and inference, extends maximum dialogue length, encodes richer semantics to stabilize text-to-token modeling and supports high-fidelity streaming generation for real-time applications. We adopt a text-speech interleaved format, concatenating speaker-labeled text with aligned speech tokens in chronological order, and model it with a dual-transformer: a large decoder-only transformer predicts tokens at the first layer, and a smaller one completes subsequent layers. Experimental results show that FireRedTTS-2 integrates seamlessly with chat frameworks and, with minimal fine-tuning, produces emotionally expressive speech guided by implicit contextual cues. In podcast generation, it surpasses existing systems including MoonCast, Zipvoice-Dialogue, and MOSS-TTSD in objective intelligibility, speaker-turn reliability, and perceived naturalness with context-consistent prosody. Our demos are available at https://fireredteam.github.io/demos/firered_tts_2. △ Less

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

Organ-Agents: Virtual Human Physiology Simulator via LLMs

Authors: Rihao Chang, He Jiao, Weizhi Nie, Honglin Guo, Keliang Xie, Zhenhua Wu, Lina Zhao, Yunpeng Bai, Yongtao Ma, Lanjun Wang, Yuting Su, Xi Gao, Weijie Wang, Nicu Sebe, Bruno Lepri, Bingwei Sun

Abstract: Recent advances in large language models (LLMs) have enabled new possibilities in simulating complex physiological systems. We introduce Organ-Agents, a multi-agent framework that simulates human physiology via LLM-driven agents. Each Simulator models a specific system (e.g., cardiovascular, renal, immune). Training consists of supervised fine-tuning on system-specific time-series data, followed b… ▽ More Recent advances in large language models (LLMs) have enabled new possibilities in simulating complex physiological systems. We introduce Organ-Agents, a multi-agent framework that simulates human physiology via LLM-driven agents. Each Simulator models a specific system (e.g., cardiovascular, renal, immune). Training consists of supervised fine-tuning on system-specific time-series data, followed by reinforcement-guided coordination using dynamic reference selection and error correction. We curated data from 7,134 sepsis patients and 7,895 controls, generating high-resolution trajectories across 9 systems and 125 variables. Organ-Agents achieved high simulation accuracy on 4,509 held-out patients, with per-system MSEs <0.16 and robustness across SOFA-based severity strata. External validation on 22,689 ICU patients from two hospitals showed moderate degradation under distribution shifts with stable simulation. Organ-Agents faithfully reproduces critical multi-system events (e.g., hypotension, hyperlactatemia, hypoxemia) with coherent timing and phase progression. Evaluation by 15 critical care physicians confirmed realism and physiological plausibility (mean Likert ratings 3.9 and 3.7). Organ-Agents also enables counterfactual simulations under alternative sepsis treatment strategies, generating trajectories and APACHE II scores aligned with matched real-world patients. In downstream early warning tasks, classifiers trained on synthetic data showed minimal AUROC drops (<0.04), indicating preserved decision-relevant patterns. These results position Organ-Agents as a credible, interpretable, and generalizable digital twin for precision diagnosis, treatment simulation, and hypothesis testing in critical care. △ Less

Submitted 19 August, 2025; originally announced August 2025.

ViPE: Video Pose Engine for 3D Geometric Perception

Authors: Jiahui Huang, Qunjie Zhou, Hesam Rabeti, Aleksandr Korovko, Huan Ling, Xuanchi Ren, Tianchang Shen, Jun Gao, Dmitry Slepichev, Chen-Hsuan Lin, Jiawei Ren, Kevin Xie, Joydeep Biswas, Laura Leal-Taixe, Sanja Fidler

Abstract: Accurate 3D geometric perception is an important prerequisite for a wide range of spatial AI systems. While state-of-the-art methods depend on large-scale training data, acquiring consistent and precise 3D annotations from in-the-wild videos remains a key challenge. In this work, we introduce ViPE, a handy and versatile video processing engine designed to bridge this gap. ViPE efficiently estimate… ▽ More Accurate 3D geometric perception is an important prerequisite for a wide range of spatial AI systems. While state-of-the-art methods depend on large-scale training data, acquiring consistent and precise 3D annotations from in-the-wild videos remains a key challenge. In this work, we introduce ViPE, a handy and versatile video processing engine designed to bridge this gap. ViPE efficiently estimates camera intrinsics, camera motion, and dense, near-metric depth maps from unconstrained raw videos. It is robust to diverse scenarios, including dynamic selfie videos, cinematic shots, or dashcams, and supports various camera models such as pinhole, wide-angle, and 360° panoramas. We have benchmarked ViPE on multiple benchmarks. Notably, it outperforms existing uncalibrated pose estimation baselines by 18%/50% on TUM/KITTI sequences, and runs at 3-5FPS on a single GPU for standard input resolutions. We use ViPE to annotate a large-scale collection of videos. This collection includes around 100K real-world internet videos, 1M high-quality AI-generated videos, and 2K panoramic videos, totaling approximately 96M frames -- all annotated with accurate camera poses and dense depth maps. We open-source ViPE and the annotated dataset with the hope of accelerating the development of spatial AI systems. △ Less

Submitted 12 August, 2025; originally announced August 2025.

Comments: Paper website: https://research.nvidia.com/labs/toronto-ai/vipe/

Generative Video Matting

Authors: Yongtao Ge, Kangyang Xie, Guangkai Xu, Mingyu Liu, Li Ke, Longtao Huang, Hui Xue, Hao Chen, Chunhua Shen

Abstract: Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background images or videos during the training stage. Thus, the generalization capability of previous methods in real-world scenarios is typically poor. In this work, we… ▽ More Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background images or videos during the training stage. Thus, the generalization capability of previous methods in real-world scenarios is typically poor. In this work, we propose to solve the problem from two perspectives. First, we emphasize the importance of large-scale pre-training by pursuing diverse synthetic and pseudo-labeled segmentation datasets. We also develop a scalable synthetic data generation pipeline that can render diverse human bodies and fine-grained hairs, yielding around 200 video clips with a 3-second duration for fine-tuning. Second, we introduce a novel video matting approach that can effectively leverage the rich priors from pre-trained video diffusion models. This architecture offers two key advantages. First, strong priors play a critical role in bridging the domain gap between synthetic and real-world scenes. Second, unlike most existing methods that process video matting frame-by-frame and use an independent decoder to aggregate temporal information, our model is inherently designed for video, ensuring strong temporal consistency. We provide a comprehensive quantitative evaluation across three benchmark datasets, demonstrating our approach's superior performance, and present comprehensive qualitative results in diverse real-world scenes, illustrating the strong generalization capability of our method. The code is available at https://github.com/aim-uofa/GVM. △ Less

Submitted 11 August, 2025; originally announced August 2025.

Journal ref: SIGGRAPH Conference Papers 2025

PriorRG: Prior-Guided Contrastive Pre-training and Coarse-to-Fine Decoding for Chest X-ray Report Generation

Authors: Kang Liu, Zhuoqi Ma, Zikang Fang, Yunan Li, Kun Xie, Qiguang Miao

Abstract: Chest X-ray report generation aims to reduce radiologists' workload by automatically producing high-quality preliminary reports. A critical yet underexplored aspect of this task is the effective use of patient-specific prior knowledge -- including clinical context (e.g., symptoms, medical history) and the most recent prior image -- which radiologists routinely rely on for diagnostic reasoning. Mos… ▽ More Chest X-ray report generation aims to reduce radiologists' workload by automatically producing high-quality preliminary reports. A critical yet underexplored aspect of this task is the effective use of patient-specific prior knowledge -- including clinical context (e.g., symptoms, medical history) and the most recent prior image -- which radiologists routinely rely on for diagnostic reasoning. Most existing methods generate reports from single images, neglecting this essential prior information and thus failing to capture diagnostic intent or disease progression. To bridge this gap, we propose PriorRG, a novel chest X-ray report generation framework that emulates real-world clinical workflows via a two-stage training pipeline. In Stage 1, we introduce a prior-guided contrastive pre-training scheme that leverages clinical context to guide spatiotemporal feature extraction, allowing the model to align more closely with the intrinsic spatiotemporal semantics in radiology reports. In Stage 2, we present a prior-aware coarse-to-fine decoding for report generation that progressively integrates patient-specific prior knowledge with the vision encoder's hidden states. This decoding allows the model to align with diagnostic focus and track disease progression, thereby enhancing the clinical accuracy and fluency of the generated reports. Extensive experiments on MIMIC-CXR and MIMIC-ABN datasets demonstrate that PriorRG outperforms state-of-the-art methods, achieving a 3.6% BLEU-4 and 3.8% F1 score improvement on MIMIC-CXR, and a 5.9% BLEU-1 gain on MIMIC-ABN. Code and checkpoints will be released upon acceptance. △ Less

Submitted 4 January, 2026; v1 submitted 7 August, 2025; originally announced August 2025.

Comments: Accepted by AAAI 2026

Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder

Authors: Chao Wu, Zhenyi Wang, Kangxian Xie, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Mingchen Gao

Abstract: Text-to-image (T2I) diffusion models often exhibit gender bias, particularly by generating stereotypical associations between professions and gendered subjects. This paper presents SAE Debias, a lightweight and model-agnostic framework for mitigating such bias in T2I generation. Unlike prior approaches that rely on CLIP-based filtering or prompt engineering, which often require model-specific adju… ▽ More Text-to-image (T2I) diffusion models often exhibit gender bias, particularly by generating stereotypical associations between professions and gendered subjects. This paper presents SAE Debias, a lightweight and model-agnostic framework for mitigating such bias in T2I generation. Unlike prior approaches that rely on CLIP-based filtering or prompt engineering, which often require model-specific adjustments and offer limited control, SAE Debias operates directly within the feature space without retraining or architectural modifications. By leveraging a k-sparse autoencoder pre-trained on a gender bias dataset, the method identifies gender-relevant directions within the sparse latent space, capturing professional stereotypes. Specifically, a biased direction per profession is constructed from sparse latents and suppressed during inference to steer generations toward more gender-balanced outputs. Trained only once, the sparse autoencoder provides a reusable debiasing direction, offering effective control and interpretable insight into biased subspaces. Extensive evaluations across multiple T2I models, including Stable Diffusion 1.4, 1.5, 2.1, and SDXL, demonstrate that SAE Debias substantially reduces gender bias while preserving generation quality. To the best of our knowledge, this is the first work to apply sparse autoencoders for identifying and intervening in gender bias within T2I models. These findings contribute toward building socially responsible generative AI, providing an interpretable and model-agnostic tool to support fairness in text-to-image generation. △ Less

Submitted 21 November, 2025; v1 submitted 28 July, 2025; originally announced July 2025.

RoboBrain 2.0 Technical Report

Authors: BAAI RoboBrain Team, Mingyu Cao, Huajie Tan, Yuheng Ji, Xiansheng Chen, Minglan Lin, Zhiyu Li, Zhou Cao, Pengwei Wang, Enshen Zhou, Yi Han, Yingbo Tang, Xiangqi Xu, Wei Guo, Yaoxu Lyu, Yijie Xu, Jiayu Shi, Mengfei Du, Cheng Chi, Mengdi Zhao, Xiaoshuai Hao, Junkai Zhao, Xiaojie Zhang, Shanyu Rong, Huaihai Lyu , et al. (28 additional authors not shown)

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

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

QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration

Authors: Junze Hu, Xiangyu Jin, Yizhe Zeng, Yuling Liu, Yunpeng Li, Dan Du, Kaiyu Xie, Hongsong Zhu

Abstract: We introduce QLPro, a vulnerability detection framework that systematically integrates LLMs and static analysis tools to enable comprehensive vulnerability detection across entire open-source projects.We constructed a new dataset, JavaTest, comprising 10 open-source projects from GitHub with 62 confirmed vulnerabilities. CodeQL, a state-of-the-art static analysis tool, detected only 24 of these vu… ▽ More We introduce QLPro, a vulnerability detection framework that systematically integrates LLMs and static analysis tools to enable comprehensive vulnerability detection across entire open-source projects.We constructed a new dataset, JavaTest, comprising 10 open-source projects from GitHub with 62 confirmed vulnerabilities. CodeQL, a state-of-the-art static analysis tool, detected only 24 of these vulnerabilities while QLPro detected 41. Furthermore, QLPro discovered 6 previously unknown vulnerabilities, 2 of which have been confirmed as 0-days. △ Less

Submitted 19 July, 2025; v1 submitted 30 June, 2025; originally announced June 2025.

Comments: The experimental data in the experimental section needs to be improved, and there are some errors

Analyzing the Impact of Strategic Bidding on the Reserve Capacity via a Bi-Level Model

Authors: Yun Xu, Yunxiao Bai, Yunyong Zhang, Peng Wang, Xuelin Wang, Jiqun Guo, Kaijun Xie, Rusheng Zhao

Abstract: The growing integration of renewable energy sources necessitates adequate reserve capacity to maintain power balance. However, in market clearing, power companies with flexible resources may submit strategic bids to maximize profits, potentially compromising system reserves. This paper examines the effects of such strategic behavior by modeling the market as a bi-level problem. The upper level rep… ▽ More The growing integration of renewable energy sources necessitates adequate reserve capacity to maintain power balance. However, in market clearing, power companies with flexible resources may submit strategic bids to maximize profits, potentially compromising system reserves. This paper examines the effects of such strategic behavior by modeling the market as a bi-level problem. The upper level represents a strategic company aiming to maximize profit, while the lower level simulates the system operator clearing the market based on submitted offers. To enable duality-based solution methods, we approximate unit commitments with a continuous reserve capacity calculation. Case studies indicate that, in an imperfectly competitive market, more units are incentivized to operate,enhancing system reserves. However, some units go online mainly for profit, ultimately raising electricity costs for consumers. These findings highlight the importance of market design in managing the trade-off between reserve adequacy and economic efficiency in the presence of strategic bidding behavior. △ Less

Submitted 25 June, 2025; originally announced June 2025.