Showing 1–50 of 117 results for author: Ouyang, J

Expert-Guided g-computation with Large Language Models for Estimating Causal Effects on Timings: Applications to Hospital Quality Improvement

Authors: Patrick Vossler, Jialin Ouyang, F. Richard Guo, Anran Huang, Ali Shojaie, Lucas Zier, Fan Xia, Jean Feng

Abstract: Hospital quality improvement (QI) programs routinely face multiple candidate interventions to optimize hospital flow, but existing methods struggle to estimate and rank the causal effects of such interventions. This work focuses on one of the most standard hospital metrics, the average length of stay (LOS), and its causal estimand, the average time saved. To characterize this causal effect, qualit… ▽ More Hospital quality improvement (QI) programs routinely face multiple candidate interventions to optimize hospital flow, but existing methods struggle to estimate and rank the causal effects of such interventions. This work focuses on one of the most standard hospital metrics, the average length of stay (LOS), and its causal estimand, the average time saved. To characterize this causal effect, qualitative approaches rely on expert judgment to map patient trajectories, making them susceptible to cognitive biases; quantitative approaches rely on data-driven models, which fail when interventions are hypothetical with no historical data or have complex causal mechanisms that require clinical reasoning rather than data alone. We propose expert-guided g-computation, or egg-computation, which combines the complementary strengths of both approaches by connecting the Gantt charts commonly used to map patient trajectories with the causal DAG literature. We introduce a causal model over Gantt charts and establish identification using a variant of g-computation that seeks expert input only for components unidentifiable from data. To make egg-computation practical, we develop an LLM-assisted pipeline that reliably scales up expert reasoning. In simulations, egg-computation outperforms conventional causal inference methods when patients have diverse causal structures and intervention mechanisms. In a study of eleven candidate QI interventions at an urban safety-net hospital, the LLM pipeline generated graphs and time-saving estimates highly concordant with those of human experts. Beyond healthcare, egg-computation is a broadly applicable framework for estimating the average time saved for candidate interventions whose causal mechanisms can be represented using Gantt charts. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Contrastive Mask Fidelity: Reference-Free Auditing of Ground-Truth Masks in Remote Sensing Semantic Segmentation

Authors: Shuaishuai Cao, Shuwei Peng, Meng Tang, Min Huang, Youjin Wang, Jie Chen, Jing Ouyang, Zhiwei Zhai

Abstract: Semantic segmentation models are trained and evaluated against human-drawn masks, yet remote-sensing annotations are often coarse, incomplete, or misaligned; high overlap scores may then reflect agreement with imperfect labels rather than faithfulness to the image, creating an evaluation paradox. We introduce Contrastive Mask Fidelity (CMF), a training-free, reference-free metric that scores compe… ▽ More Semantic segmentation models are trained and evaluated against human-drawn masks, yet remote-sensing annotations are often coarse, incomplete, or misaligned; high overlap scores may then reflect agreement with imperfect labels rather than faithfulness to the image, creating an evaluation paradox. We introduce Contrastive Mask Fidelity (CMF), a training-free, reference-free metric that scores competing class masks directly against image evidence. CMF composites keep and erase counterfactual views of each mask and asks a frozen vision-language judge whether class evidence is concentrated inside the mask and absent outside. We validate CMF on controlled mask corruptions, then audit 10,731 image-class pairs across ten remote-sensing benchmarks using candidate masks from Seg-Probe, a training-free open-vocabulary probe built on SegEarth-OV3 that outperforms prior baselines on nine of ten datasets. The audit reveals systematic, class-dependent annotation distortion: man-made classes such as buildings, roads, and cars favor the candidate mask on 62-85% of pairs, whereas ambiguous land cover more often favors human annotations. On a blinded three-annotator consensus, CMF matches expert judgment on 81% of pairs, exceeding keep-only scoring, model confidence, and a trained label-quality baseline. Finally, conservative class-wise arbitration yields supervision that improves cross-domain transfer over raw annotations and matched replacement controls, positioning CMF as a scalable tool for auditing ground truth rather than presuming it infallible. △ Less

Submitted 10 August, 2026; originally announced August 2026.

LEACL: LLM-Enhanced Automatic Curriculum Learning for Reinforcement Learning in Long-Horizon Manipulation Tasks

Authors: Faraz Heravi, James Ouyang, Zifan Xu, Arjun Kumar, Yoonchang Sung, Peter Stone

Abstract: Long-horizon manipulation tasks pose significant challenges for reinforcement learning due to sparse reward signals and long horizons. Automatic curriculum learning (ACL) has been proposed to tackle these challenges by progressively training agents on a sequence of tasks, from easier to more difficult. However, the success of ACL depends heavily on task-dependent specifications-such as well-define… ▽ More Long-horizon manipulation tasks pose significant challenges for reinforcement learning due to sparse reward signals and long horizons. Automatic curriculum learning (ACL) has been proposed to tackle these challenges by progressively training agents on a sequence of tasks, from easier to more difficult. However, the success of ACL depends heavily on task-dependent specifications-such as well-defined task parameter spaces and difficulty measures-which are often manually crafted and difficult to generalize across diverse tasks. Recent advances in large language models (LLMs) offer a promising alternative by enabling the decomposition of complex tasks into meaningful subtasks using the LLMs' web-scale common-sense knowledge. This decomposition can provide a natural curriculum structure for efficient learning of long-horizon tasks. However, existing LLM-based methods typically rely on hand-designed dense reward functions to learn each subtask, which can introduce bias and still requires significant human supervision. In this work, we propose LLM-enhanced automatic curriculum learning (LEACL), a framework that integrates LLMs and ACL to address these limitations. Specifically, LLMs are used to both decompose tasks into subtasks and to generate task-dependent specifications for each subtask. These specifications are then used by ACL algorithms to guide learning using only sparse reward signals, eliminating the need for dense reward design. We evaluate LEACL on five long-horizon manipulation tasks from the LIBERO benchmark. LEACL achieves better asymptotic performance in terms of the success rates compared to human-designed dense rewards. △ Less

Submitted 26 July, 2026; originally announced July 2026.

Comments: 8 pages, 4 figures, Published in the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026

InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics

Authors: Erich Liang, Caleb Kha-Uong, Chinmaya Saran, Sreemanti Dey, David W. Liu, Junhan Ouyang, Benjamin Zhou, Jia Deng

Abstract: Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assumption that often fails for real-world in-the-wild videos. Consequently, estimating per-frame intrinsics from RGB images is critical for making 3D methods robust to videos with dynamic intrinsics. InFlux previously advanced this research direction by… ▽ More Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assumption that often fails for real-world in-the-wild videos. Consequently, estimating per-frame intrinsics from RGB images is critical for making 3D methods robust to videos with dynamic intrinsics. InFlux previously advanced this research direction by establishing the first real-world benchmark with per-frame ground truth intrinsics for dynamic intrinsics videos. Nevertheless, existing methods remain inaccurate due to two obstacles: (i) training data is scarce and lacks intrinsics diversity; and (ii) benchmarks, including InFlux, have limited scene and camera motion diversity, making it difficult to properly evaluate methods. To address both gaps, we present InFlux++, consisting of two components. InFlux++ Synth is a large-scale procedurally generated synthetic video dataset with 441K+ annotated frames from 1841 high-resolution videos, providing accurate per-frame ground truth intrinsics for training dynamic intrinsics prediction models; a subset also includes per-frame pose, depth, and normals. The videos feature rich intrinsics diversity through changes in camera zoom and focus, as well as dynamic objects and realistic rendering effects such as lens distortion and defocus blur. InFlux++ Real is a large-scale real-world benchmark that extends InFlux with 514K+ newly captured frames across 334 high-resolution videos, spanning a wider range of scenes and camera motions. Finetuning existing intrinsics prediction methods on InFlux++ Synth consistently improves focal length estimation across both InFlux++ Real and InFlux, suggesting that synthetic supervision is promising for RGB-based intrinsics prediction. For the dataset, benchmark, code, videos, submission instructions, and live leaderboard, please visit https://influx.cs.princeton.edu/ . △ Less

Submitted 6 July, 2026; originally announced July 2026.

Comments: Accepted to ECCV 2026

GRASP: Graph-Reasoning Aided Survey Planning for High-Fidelity Related Work Generation

Authors: Haoming Li, Jessica Ouyang

Abstract: Writing a literature review requires a deep understanding of the relationships among cited papers: how they build on, challenge, or offer alternative perspectives to one another. We present Graph-Reasoning Aided Survey Planning (GRASP), a framework combining LLM planning for related work generation with graph algorithms to extract key relationships among cited papers. Our two-layer graph structure… ▽ More Writing a literature review requires a deep understanding of the relationships among cited papers: how they build on, challenge, or offer alternative perspectives to one another. We present Graph-Reasoning Aided Survey Planning (GRASP), a framework combining LLM planning for related work generation with graph algorithms to extract key relationships among cited papers. Our two-layer graph structure consists of a Graph of Thoughts and an Argument-Counterargument Planning Network, representing the cited papers at different levels of granularity, and we apply topology-aware pruning via a Steiner tree to identify the core inter-paper relationships captured in our graph. Our citation analysis-based evaluation shows that GRASP generates related work sections (RWS) that closely match human-written targets in terms of the discourse roles, intents, and grouping of citations. △ Less

Submitted 4 July, 2026; originally announced July 2026.

Comments: 23 pages, 3 figures. Published in Findings of the Association for Computational Linguistics: ACL 2026

ACM Class: I.2.7; I.2.6

Journal ref: Findings of the Association for Computational Linguistics: ACL 2026, pages 36427-36449, San Diego, California, United States. Association for Computational Linguistics

Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries

Authors: Jean Feng, Vishal Patel, Patrick Heagerty, Yifan Mai, Venkatesh Sivaraman, Patrick Vossler, Jialin Ouyang, Anupam B. Jena

Abstract: Physicians now pose millions of clinical questions to AI tools each week, yet these tools are evaluated largely on hypothetical or exam-style questions, not those actually asked in practice. We report a blinded evaluation built on 620 Real-world Point-Of-Care Queries (Real-POCQi) submitted to the OpenEvidence (OE) platform by physicians spanning 30 specialties, as well as 187 questions from Health… ▽ More Physicians now pose millions of clinical questions to AI tools each week, yet these tools are evaluated largely on hypothetical or exam-style questions, not those actually asked in practice. We report a blinded evaluation built on 620 Real-world Point-Of-Care Queries (Real-POCQi) submitted to the OpenEvidence (OE) platform by physicians spanning 30 specialties, as well as 187 questions from HealthBench. 149 practicing physicians across 36 states made head-to-head comparisons between answers from three frontier general-purpose models (Claude Opus 4.8, Gemini 3.1 Pro, and GPT-5.5) and a specialized clinical tool (OE), with graders matched to each question's specialty. When comparing answers along five dimensions relevant to clinical decision support -- accuracy, clinical utility, source quality, verifiability, & completeness -- physicians scored the specialized tool highest on all axes; in the primary analysis on Real-POCQi, win differences (margins between win and loss rates) ranged from 25 to 39 percentage points (p<0.001). Results remained consistent in sensitivity analyses stratifying by citation display, answer length, OE-user status, and Real-POCQi versus HealthBench. In parallel, LLM judges were found to systematically differ from expert judges, though both generally agreed on the best model. These findings underscore two conclusions: (i) AI tool evaluations should reflect real-world query distributions and use expert judges that mirror the specialization defining modern medicine and (ii) the consistent advantage of the specialized tool over general-purpose models does not necessarily mean that the latter cannot serve similar purposes, but that targeted engineering and customization can yield meaningful gains in performance for its users. We release Real-POCQi as a public benchmark, as well as the prespecified statistical analysis for reproducing results of this study. △ Less

Submitted 27 June, 2026; originally announced June 2026.

Democratizing and accelerating AI-driven pathology research through agentic intelligence

Authors: Jiabo Ma, Cheng Jin, Yihui Wang, Hao Jiang, Ling Liang, Yingxue Xu, Junlin Hou, Zhengrui Guo, Zhengyu Zhang, Yifei Xia, Hongyi Wang, Fengtao Zhou, Zhe Xu, Huajun Zhou, Jiarui Ouyang, Qian Zeng, On Ki Tang, Eunhyang Park, Carolyn Glass, Ronald Cheong Kin Chan, Li Liang, Hao Chen

Abstract: Computational pathology has advanced rapidly with the emergence of foundation models, yet widespread adoption remains limited by substantial technical complexity and programming requirements. Here we present PathLab, an autonomous agentic framework that translates natural-language research objectives into executable and validated computational pathology workflows through the structured composition… ▽ More Computational pathology has advanced rapidly with the emergence of foundation models, yet widespread adoption remains limited by substantial technical complexity and programming requirements. Here we present PathLab, an autonomous agentic framework that translates natural-language research objectives into executable and validated computational pathology workflows through the structured composition of domain-specific skills and tools. By organizing workflow generation around reusable methodological modules, including data preprocessing, model development, evaluation and interpretation, PathLab enables studies to be specified at the level of scientific intent rather than implementation details. We evaluated PathLab across 12 public datasets spanning four representative task families: region-of-interest classification, whole-slide image classification, segmentation and survival prediction. Across all task categories, PathLab achieved non-inferior performance relative to expert implementations, while consistently enforcing semantic validity of user prompts and proactively rejecting incompatible workflow specifications prior to execution. In controlled user studies, PathLab substantially reduced the time required to generate executable analytical pipelines and enabled domain experts without programming experience to independently design, execute and evaluate computational pathology studies. Together, these results establish PathLab as a reliable interface between biomedical intent and computational execution, enabling computational pathology studies to be designed at the level of scientific questions rather than programming expertise. By lowering technical barriers to advanced AI methodologies, PathLab provides a foundation for the broader democratization of computational pathology. △ Less

Submitted 12 June, 2026; originally announced June 2026.

Comments: 29 pages, 4 figures

ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments

Authors: Tingyue Pan, Mingyue Cheng, Daoyu Wang, Yitong Zhou, Jie Ouyang, Qi Liu, Enhong Chen

Abstract: Academic paper search is a core step in scientific research, and LLM-based search agents are emerging as a promising paradigm for iterative, intent-driven literature exploration. However, existing benchmarks are insufficient for systematically evaluating agentic academic search under realistic open literature environments. We propose ScholarQuest, a large-scale, taxonomy-guided benchmark for agent… ▽ More Academic paper search is a core step in scientific research, and LLM-based search agents are emerging as a promising paradigm for iterative, intent-driven literature exploration. However, existing benchmarks are insufficient for systematically evaluating agentic academic search under realistic open literature environments. We propose ScholarQuest, a large-scale, taxonomy-guided benchmark for agentic academic paper search. ScholarQuest is constructed from over 1,000 computer science topics and four representative research intents, including method-oriented, setting-anchored, comparison-based, and scope-controlled queries. It further provides scalable answer construction and a shared retrieval backend ScholarBase for reproducible evaluation. Benchmarking results show that agentic methods outperform single-shot retrieval baselines, yet the best-performing agent only achieves 0.314 Recall@100 and 0.355 Recall@All, indicating substantial room for improvement. In addition, analyses of search efficiency, intent-level robustness, and failure cases further highlight the benchmark's ability to provide multi-dimensional evaluation signals for academic paper search agents. △ Less

Submitted 18 June, 2026; originally announced June 2026.

SocraticPO: Policy Optimization via Interactive Guidance

Authors: Zirui Liu, Jie Ouyang, Qi Liu, Xianquan Wang, Jiayu Liu, Tingyue Pan, Qingchuan Li, Jing Sha, Zhenya Huang, Shijin Wang, Enhong Chen

Abstract: Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization direction but rarely explain how a model should revise its mistaken reasoning, which can encourage shortcut learning and brittle policies. We propose \textbf{SocraticPO} (Socratic Policy Optimization), a policy-optimization… ▽ More Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization direction but rarely explain how a model should revise its mistaken reasoning, which can encourage shortcut learning and brittle policies. We propose \textbf{SocraticPO} (Socratic Policy Optimization), a policy-optimization framework that augments RL rollouts with Socratic-style natural-language guidance. During rollout, the student first answers independently; if the answer is incorrect, a teacher diagnoses the attempt and provides concise corrective guidance, after which the student continues under the expanded context. Crucially, this guidance is paired with reward decay: correct answers obtained after teacher intervention only receive decayed rewards, preventing the policy from treating teacher help as a free path to reward. Since SocraticPO only modifies the rollout process while leaving the standard expected-reward objective intact, it can be plugged into existing policy-gradient backends such as Reinforce++. Moreover, because the teacher provides only text-level guidance, SocraticPO can leverage stronger black-box teacher models without requiring access to logits or distribution matching. On undergraduate-level scientific reasoning benchmarks from SciKnowEval, SocraticPO improves over strong RL and self-distillation baselines. Ablations show that both targeted guidance and reward decay are necessary, with reward decay mitigating reliance on assisted correction. △ Less

Submitted 3 June, 2026; originally announced June 2026.

Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning

Authors: Daoyu Wang, Mingyue Cheng, Qingchuan Li, Shuo Yu, Jie Ouyang, Qi Liu

Abstract: Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw. Existing work mainly focuses on policy optimization algorithms and training frameworks, but pays less attention to the full data lifecycle of agent-environment interactions, from data productio… ▽ More Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw. Existing work mainly focuses on policy optimization algorithms and training frameworks, but pays less attention to the full data lifecycle of agent-environment interactions, from data production to training consumption. To bridge this gap, we present Claw-R1, an interactive step-level data middleware system for agentic RL. Claw-R1 connects heterogeneous agent runtimes with RL training backends through two core components: a Gateway Server and a Data Pool. The Gateway Server captures multi-turn interaction steps through a unified LLM API entry point, while the Data Pool organizes them into step-level records consisting of prompt IDs, response IDs, rewards and other metadata. In our demo, users can interactively inspect live trajectories, examine the state, action, and reward of each step, curate data by quality and readiness, and configure training-ready batches for different downstream RL algorithms. Overall, Claw-R1 treats agent interaction traces as managed data assets rather than temporary runtime logs. Through this demonstration, we hope to encourage the community to recognize the importance of data management in agentic RL. Our code is available at https://github.com/AgentR1/Claw-R1 and the demonstration video can be found at link https://youtu.be/Pw47dAOw6B0. △ Less

Submitted 8 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.

An Open Multi-Center Whole-Body FDG PET/CT Foundation Model for Tumor Segmentation

Authors: Xiaofeng Liu, Qianru Zhang, Thibault Marin, Menghua Xia, Chi Liu, Georges El Fakhri, Jinsong Ouyang

Abstract: The synergistic interpretation of anatomical information from computed tomography (CT) and metabolic information from positron emission tomography (PET) is important to oncologic imaging. However, existing deep learning methods for PET/CT remain largely task-specific, are often trained on single-center cohorts, or adopt dual-branch fusion schemes that delay cross-modal interaction and underutilize… ▽ More The synergistic interpretation of anatomical information from computed tomography (CT) and metabolic information from positron emission tomography (PET) is important to oncologic imaging. However, existing deep learning methods for PET/CT remain largely task-specific, are often trained on single-center cohorts, or adopt dual-branch fusion schemes that delay cross-modal interaction and underutilize early spatial correspondence between PET and CT. To address these limitations, we present an open-source, multi-center, whole-body FDG PET/CT foundation model utilizing 4,997 harmonized scans from four public datasets. Our framework employs hierarchical UNet-shaped backbones with early channel-wise concatenation, enabling anatomical and metabolic features to interact from the first embedding layer onward. We further introduce a masked autoencoding objective based on zero-mean imputation, combined with a weighted global reconstruction loss. This design avoids non-physical intensity discontinuities at masked-region boundaries that arise from learnable mask tokens. On downstream AutoPET lesion segmentation, the proposed models demonstrate strong label efficiency: with only 10\% of the labeled training data, they achieve performance comparable to models trained from scratch on the full dataset. Under extreme 5-shot linear probing, joint PET/CT pretraining also achieves higher Dice scores than separated-modality pretraining. This multi-center foundation model demonstrates label efficiency and cross-modality representation learning for PET/CT tumor segmentation. It provides a robust, open-source basis for advancing automated oncologic imaging, significantly reducing the need for large-scale manual annotations in clinical practice. △ Less

Submitted 20 May, 2026; originally announced May 2026.

Comments: Code available at: https://github.com/liu-xiaofeng/Foundation-Model-for-PET-CT

Proximal State Nudging: Reducing Skill Atrophy from AI Assistance

Authors: Megha Srivastava, Jonathan Ouyang, Eric Zhou, Andrew Silva, Emily Sumner, Dorsa Sadigh, Yuchen Cui, Deepak Gopinath, Guy Rosman

Abstract: Skill atrophy, the gradual decline of human capability under AI assistance, poses a safety risk in shared-control of semi-autonomous systems, where operators may be unable to distinguish their own inputs from autonomous corrections. We propose Proximal State Nudging (PSN), a shared autonomy algorithm that jointly optimizes for skill development and task performance by nudging users toward states e… ▽ More Skill atrophy, the gradual decline of human capability under AI assistance, poses a safety risk in shared-control of semi-autonomous systems, where operators may be unable to distinguish their own inputs from autonomous corrections. We propose Proximal State Nudging (PSN), a shared autonomy algorithm that jointly optimizes for skill development and task performance by nudging users toward states estimated to be most learnable. We first show that PSN outperforms existing shared autonomy baselines in balancing student improvement in unassisted reward with overall shared performance, using simulated students in the classic LunarLander environment. We then present, to the best of our knowledge, the first human subject studies of a planner incorporating learning-compatible shared autonomy: across two driving tasks in the CARLA simulator (High Performance Racing and Parallel Parking, n = 60), PSN produces up to 7x larger gains in unassisted skill than standard blended shared autonomy, while incurring 50% fewer collisions than unassisted self-practice. △ Less

Submitted 19 May, 2026; originally announced May 2026.

Comments: 9 pages

CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities

Authors: Daoyu Wang, Qingchuan Li, Mingyue Cheng, Jie Ouyang, Shuo Yu, Chunli Liu, Shijin Wang, Qi Liu, Enhong Chen

Abstract: Reinforcement learning (RL) has become a key technique for improving the agentic capabilities of large language models (LLMs). Although critic-free methods such as GRPO are increasingly popular, we argue that critic-based methods remain well suited to long-horizon agentic tasks because their critic models can assess each state and assign credit to different decisions. However, representative criti… ▽ More Reinforcement learning (RL) has become a key technique for improving the agentic capabilities of large language models (LLMs). Although critic-free methods such as GRPO are increasingly popular, we argue that critic-based methods remain well suited to long-horizon agentic tasks because their critic models can assess each state and assign credit to different decisions. However, representative critic-based methods such as PPO still organize value estimation, credit assignment, and policy updates at token granularity, whereas the environment state changes only after the agent completes a full action. In this work, we propose CAPO, a critic-guided action-aligned policy optimization method for advancing LLM agent capabilities. CAPO introduces two action-aligned designs. First, it estimates the state value at the action boundary using a critic model and assigns the corresponding advantage to the complete action rather than individual tokens. Second, CAPO introduces a novel action-aware policy ratio that aggregates token ratios within each action with length calibration for consistent updates across actions of different lengths. These two designs effectively achieve fine-grained credit assignment and consistent policy updates while remaining compatible with token-level gradient computation. Experiments across multi-hop QA, academic paper search, and text-world action tasks show that CAPO consistently outperforms representative RL methods. Further analyses validate both designs and reveal how action-aligned optimization improves multi-turn RL training. We hope this work provides a practical path for training more capable LLM agents. △ Less

Submitted 10 August, 2026; v1 submitted 20 April, 2026; originally announced April 2026.

Ranking XAI Methods for Head and Neck Cancer Outcome Prediction

Authors: Baoqiang Ma, Djennifer K. Madzia-Madzou, Rosa C. J. Kraaijveld, Jin Ouyang

Abstract: For head and neck cancer (HNC) patients, prognostic outcome prediction can support personalized treatment strategy selection. Improving prediction performance of HNC outcomes has been extensively explored by using advanced artificial intelligence (AI) techniques on PET/CT data. However, the interpretability of AI remains a critical obstacle for its clinical adoption. Unlike previous HNC studies th… ▽ More For head and neck cancer (HNC) patients, prognostic outcome prediction can support personalized treatment strategy selection. Improving prediction performance of HNC outcomes has been extensively explored by using advanced artificial intelligence (AI) techniques on PET/CT data. However, the interpretability of AI remains a critical obstacle for its clinical adoption. Unlike previous HNC studies that empirically selected explainable AI (XAI) techniques, we are the first to comprehensively evaluate and rank 13 XAI methods across 24 metrics, covering faithfulness, robustness, complexity and plausibility. Experimental results on the multi-center HECKTOR challenge dataset show large variations across evaluation aspects among different XAI methods, with Integrated Gradients (IG) and DeepLIFT (DL) consistently obtained high rankings for faithfulness, complexity and plausibility. This work highlights the importance of comprehensive XAI method evaluation and can be extended to other medical imaging tasks. △ Less

Submitted 17 April, 2026; originally announced April 2026.

Comments: 4-page conference paper, accepted at IEEE ISBI 2026 (International Symposium on Biomedical Imaging)

Analyzing the Presentation, Content, and Utilization of References in LLM-powered Conversational AI Systems

Authors: Jianheng Ouyang, Arpit Narechania

Abstract: As conversational AI systems become popular for information retrieval and question-answering, the references they cite are key to ensuring their answers are reliable and trustworthy. Yet, no prior work systematically analyzes how these references are presented or their quality. We examine 1,517 references from 30 question-answer pairs across nine systems, focusing on their (1) presentation in the… ▽ More As conversational AI systems become popular for information retrieval and question-answering, the references they cite are key to ensuring their answers are reliable and trustworthy. Yet, no prior work systematically analyzes how these references are presented or their quality. We examine 1,517 references from 30 question-answer pairs across nine systems, focusing on their (1) presentation in the user interface and (2) quality using the CRAAP criteria. We find notable variations in the presentation, quality, and quantity of references across systems. For instance, ChatGPT provides more references (9.5 per response on average) with higher quality (15.48/20 CRAAP score), while Hunyuan-TurboS provides fewer references (4.0) and lower quality (11.65/20). Additionally, a preliminary user study shows that people rarely interact with these references and that their behavior differs across systems. These findings highlight the need for better interface designs that help users engage with and trust references more effectively. △ Less

Submitted 5 March, 2026; originally announced April 2026.

Comments: 8 pages, 5 figures, Accepted to ACM CHI 2026 Extended Abstract/Poster/Case Study Track

Hessian-informed machine learning interatomic potential towards bridging theory and experiments

Authors: Bangchen Yin, Jian Ouyang, Zhen Fan, Kailai Lin, Hanshi Hu, Dingshun Lv, Weiluo Ren, Hai Xiao, Ji Chen, Changsu Cao

Abstract: Local curvature of potential energy surfaces is critical for predicting certain experimental observables of molecules and materials from first principles, yet it remains far beyond reach for complex systems. In this work, we introduce a Hessian-informed Machine Learning Interatomic Potential (Hi-MLIP) that captures such curvature reliably, thereby enabling accurate analysis of associated thermodyn… ▽ More Local curvature of potential energy surfaces is critical for predicting certain experimental observables of molecules and materials from first principles, yet it remains far beyond reach for complex systems. In this work, we introduce a Hessian-informed Machine Learning Interatomic Potential (Hi-MLIP) that captures such curvature reliably, thereby enabling accurate analysis of associated thermodynamic and kinetic phenomena. To make Hessian supervision practically viable, we develop a highly efficient training protocol, termed Hessian INformed Training (HINT), achieving two to four orders of magnitude reduction for the requirement of expensive Hessian labels. HINT integrates critical techniques, including Hessian pre-training, configuration sampling, curriculum learning and stochastic projection Hessian loss. Enabled by HINT, Hi-MLIP significantly improves transition-state search and brings Gibbs free-energy predictions close to chemical accuracy especially in data-scarce regimes. Our framework also enables accurate treatment of strongly anharmonic hydrides, reproducing phonon renormalization and superconducting critical temperatures in close agreement with experiment while bypassing the computational bottleneck of anharmonic calculations. These results establish a practical route to enhancing curvature awareness of machine learning interatomic potentials, bridging simulation and experimental observables across a wide range of systems. △ Less

Submitted 26 March, 2026; originally announced March 2026.

Comments: 13 pages, 4 figures

DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation

Authors: Junyi Ouyang, Wenbin Teng, Gonglin Chen, Yajie Zhao, Haiwei Chen

Abstract: Long-trajectory video generation is a crucial yet challenging task for world modeling primarily due to the limited scalability of existing video diffusion models (VDMs). Autoregressive models, while offering infinite rollout, suffer from visual drift and poor controllability. To address these issues, we propose DCARL, a novel divide-and-conquer, autoregressive framework that effectively combines t… ▽ More Long-trajectory video generation is a crucial yet challenging task for world modeling primarily due to the limited scalability of existing video diffusion models (VDMs). Autoregressive models, while offering infinite rollout, suffer from visual drift and poor controllability. To address these issues, we propose DCARL, a novel divide-and-conquer, autoregressive framework that effectively combines the structural stability of the divide-and-conquer scheme with the high-fidelity generation of VDMs. Our approach first employs a dedicated Keyframe Generator trained without temporal compression to establish long-range, globally consistent structural anchors. Subsequently, an Interpolation Generator synthesizes the dense frames in an autoregressive manner with overlapping segments, utilizing the keyframes for global context and a single clean preceding frame for local coherence. Trained on a large-scale internet long trajectory video dataset, our method achieves superior performance in both visual quality (lower FID and FVD) and camera adherence (lower ATE and ARE) compared to state-of-the-art autoregressive and divide-and-conquer baselines, demonstrating stable and high-fidelity generation for long trajectory videos up to 32 seconds in length. △ Less

Submitted 25 March, 2026; originally announced March 2026.

Comments: 29 pages, 11 figures. Project page: https://junyiouy.github.io/projects/dcarl

3DCity-LLM: Empowering Multi-modality Large Language Models for 3D City-scale Perception and Understanding

Authors: Yiping Chen, Jinpeng Li, Wenyu Ke, Yang Luo, Jie Ouyang, Zhongjie He, Li Liu, Hongchao Fan, Hao Wu

Abstract: While multi-modality large language models excel in object-centric or indoor scenarios, scaling them to 3D city-scale environments remains a formidable challenge. To bridge this gap, we propose 3DCity-LLM, a unified framework designed for 3D city-scale vision-language perception and understanding. 3DCity-LLM employs a coarse-to-fine feature encoding strategy comprising three parallel branches for… ▽ More While multi-modality large language models excel in object-centric or indoor scenarios, scaling them to 3D city-scale environments remains a formidable challenge. To bridge this gap, we propose 3DCity-LLM, a unified framework designed for 3D city-scale vision-language perception and understanding. 3DCity-LLM employs a coarse-to-fine feature encoding strategy comprising three parallel branches for target object, inter-object relationship, and global scene. To facilitate large-scale training, we introduce 3DCity-LLM-1.2M dataset that comprises approximately 1.2 million high-quality samples across seven representative task categories, ranging from fine-grained object analysis to multi-faceted scene planning. This strictly quality-controlled dataset integrates explicit 3D numerical information and diverse user-oriented simulations, enriching the question-answering diversity and realism of urban scenarios. Furthermore, we apply a multi-dimensional protocol based on text-similarity metrics and LLM-based semantic assessment to ensure faithful and comprehensive evaluations for all methods. Extensive experiments on two benchmarks demonstrate that 3DCity-LLM significantly outperforms existing state-of-the-art methods, offering a promising and meaningful direction for advancing spatial reasoning and urban intelligence. The source code and dataset are available at https://github.com/SYSU-3DSTAILab/3D-City-LLM. △ Less

Submitted 24 March, 2026; originally announced March 2026.

Comments: 24 pages, 11 figures, 12 tables

ACM Class: I.2.10

Semi-Supervised Learning with Balanced Deep Representation Distributions

Authors: Changchun Li, Ximing Li, Bingjie Zhang, Wenting Wang, Jihong Ouyang

Abstract: Semi-Supervised Text Classification (SSTC) mainly works under the spirit of self-training. They initialize the deep classifier by training over labeled texts; and then alternatively predict unlabeled texts as their pseudo-labels and train the deep classifier over the mixture of labeled and pseudo-labeled texts. Naturally, their performance is largely affected by the accuracy of pseudo-labels for u… ▽ More Semi-Supervised Text Classification (SSTC) mainly works under the spirit of self-training. They initialize the deep classifier by training over labeled texts; and then alternatively predict unlabeled texts as their pseudo-labels and train the deep classifier over the mixture of labeled and pseudo-labeled texts. Naturally, their performance is largely affected by the accuracy of pseudo-labels for unlabeled texts. Unfortunately, they often suffer from low accuracy because of the margin bias problem caused by the large difference between representation distributions of labels in SSTC. To alleviate this problem, we apply the angular margin loss, and perform several Gaussian linear transformations to achieve balanced label angle variances, i.e., the variance of label angles of texts within the same label. More accuracy of predicted pseudo-labels can be achieved by constraining all label angle variances balanced, where they are estimated over both labeled and pseudo-labeled texts during self-training loops. With this insight, we propose a novel SSTC method, namely Semi-Supervised Text Classification with Balanced Deep representation Distributions (S2TC-BDD). We implement both multi-class classification and multi-label classification versions of S2TC-BDD by introducing some pseudo-labeling tricks and regularization terms. To evaluate S2 TC-BDD, we compare it against the state-of-the-art SSTC methods. Empirical results demonstrate the effectiveness of S2 TC-BDD, especially when the labeled texts are scarce. △ Less

Submitted 22 March, 2026; originally announced March 2026.

Unsupervised Adaptation from FDG to PSMA PET/CT for 3D Lesion Detection under Label Shift

Authors: Xiaofeng Liu, Menghua Xia, Yanis Chemli, Georges El Fakhri, Chi Liu, Jinsong Ouyang

Abstract: In this work, we propose an unsupervised domain adaptation (UDA) framework for 3D volumetric lesion detection that adapts a detector trained on labeled FDG PET/CT to unlabeled PSMA PET/CT. Beyond covariate shift, cross tracer adaptation also exhibits label shift in both lesion size composition and the number of lesions per subject. We introduce self-training with two mechanisms that explicitly mod… ▽ More In this work, we propose an unsupervised domain adaptation (UDA) framework for 3D volumetric lesion detection that adapts a detector trained on labeled FDG PET/CT to unlabeled PSMA PET/CT. Beyond covariate shift, cross tracer adaptation also exhibits label shift in both lesion size composition and the number of lesions per subject. We introduce self-training with two mechanisms that explicitly model and compensate for this label shift. First, we adaptively adjust the detection anchor shapes by re-estimating target domain box scales from selected pseudo labels and updating anchors with an exponential moving average. This increases positive anchor coverage for small PSMA lesions and stabilizes box regression. Second, instead of a fixed confidence threshold for pseudo-label selection, we allocate size bin-wise quotas according to the estimated target domain histogram over lesion volumes. The self-training alternates between supervised learning with prior-guided pseudo labeling on PSMA and supervised learning on labeled FDG. On AutoPET 2024, adapting from 501 labeled FDG studies to 369 $^{18}$F-PSMA studies, the proposed method improves both AP and FROC over the source-only baseline and conventional self-training without label-shift mitigation, indicating that modeling target lesion prevalence and size composition is an effective path to robust cross-tracer detection. △ Less

Submitted 13 March, 2026; originally announced March 2026.

Comments: IEEE International Symposium on Biomedical Imaging (ISBI) 2026

TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning

Authors: Mingyue Cheng, Shuo Yu, Chuang Jiang, Xiaoyu Tao, Qingyang Mao, Jie Ouyang, Qi Liu, Enhong Chen

Abstract: Table reasoning requires models to jointly perform semantic understanding and precise numerical operations. Most existing methods rely on a single-turn reasoning paradigm over tables which suffers from context overflow and weak numerical sensitivity. To address these limitations, we previously proposed TableMind as a tuning-based autonomous programmatic agent that simulates human-like interaction… ▽ More Table reasoning requires models to jointly perform semantic understanding and precise numerical operations. Most existing methods rely on a single-turn reasoning paradigm over tables which suffers from context overflow and weak numerical sensitivity. To address these limitations, we previously proposed TableMind as a tuning-based autonomous programmatic agent that simulates human-like interaction within a lightweight large language model (LLM). TableMind internalizes planning, action, and reflection through a two-stage training strategy involving supervised fine-tuning (SFT) on filtered high-quality data and reinforcement learning (RL) via a multi-perspective reward and the Rank-Aware Policy Optimization (RAPO) algorithm. While TableMind establishes a solid foundation for programmatic agents, the inherent stochasticity of LLMs remains a critical challenge that leads to hallucinations. In this paper, we extend this foundation to TableMind++ by introducing a novel uncertainty-aware inference framework to mitigate hallucinations. Specifically, we propose memory-guided plan pruning to retrieve historical trajectories for validating and filtering out logically flawed plans to address epistemic uncertainty. To ensure execution precision, we introduce confidence-based action refinement which monitors token-level probabilities to detect and self-correct syntactic noise for aleatoric uncertainty mitigation. Finally, we employ dual-weighted trajectory aggregation to synthesize a robust consensus from multiple reasoning paths. Extensive experiments on diverse benchmarks demonstrate that TableMind++ consistently outperforms previous baselines and proprietary models to validate the effectiveness of integrating autonomous training with uncertainty quantification. Our code is available. △ Less

Submitted 9 March, 2026; v1 submitted 8 March, 2026; originally announced March 2026.

Comments: 6 tables, 9 figures. arXiv admin note: text overlap with arXiv:2509.06278

QDBFT: A Dynamic Consensus Algorithm for Quantum-Secured Blockchain

Authors: Fei Xu, Cheng Ye, Jie OuYang, Ziqiang Wu, Haoze Chen, An Hua, Meifeng Gao, Qiandong Zhang, Minghan Li, Feilong Li, Yajun Miao, Wei Qi

Abstract: The security foundation of blockchain system relies primarily on classical cryptographic methods and consensus algorithms. However, the advent of quantum computing poses a significant threat to conventional public-key cryptosystems based on computational hardness assumptions. In particular, Shor's algorithm can efficiently solve discrete logarithm and integer factorization problems in polynomial t… ▽ More The security foundation of blockchain system relies primarily on classical cryptographic methods and consensus algorithms. However, the advent of quantum computing poses a significant threat to conventional public-key cryptosystems based on computational hardness assumptions. In particular, Shor's algorithm can efficiently solve discrete logarithm and integer factorization problems in polynomial time, thereby undermining the immutability and security guarantees of existing systems. Moreover, current Practical Byzantine Fault Tolerance (PBFT) protocols, widely adopted in consortium blockchains, suffer from high communication overhead and limited efficiency when coping with dynamic node reconfigurations, while offering no intrinsic protection against quantum adversaries. To address these challenges, we propose QDBFT, a quantum-secured dynamic consensus algorithm, with two main contributions: first,we design a primary node automatic rotation mechanism based on a consistent hash ring to enable consensus under dynamic membership changes, ensuring equitable authority distribution; second, we integrate Quantum Key Distribution (QKD) networks to provide message authentication for inter-node communication, thereby achieving information-theoretic security in the consensus process. Experimental evaluations demonstrate that QDBFT achieves performance comparable to traditional PBFT while delivering strong resilience against quantum attacks, making it a promising solution for future quantum-secure decentralized infrastructures. △ Less

Submitted 12 February, 2026; originally announced February 2026.

Comments: 24 pages, 11 figures

Bayesian Inference of Contextual Bandit Policies via Empirical Likelihood

Authors: Jiangrong Ouyang, Mingming Gong, Howard Bondell

Abstract: Policy inference plays an essential role in the contextual bandit problem. In this paper, we use empirical likelihood to develop a Bayesian inference method for the joint analysis of multiple contextual bandit policies in finite sample regimes. The proposed inference method is robust to small sample sizes and is able to provide accurate uncertainty measurements for policy value evaluation. In addi… ▽ More Policy inference plays an essential role in the contextual bandit problem. In this paper, we use empirical likelihood to develop a Bayesian inference method for the joint analysis of multiple contextual bandit policies in finite sample regimes. The proposed inference method is robust to small sample sizes and is able to provide accurate uncertainty measurements for policy value evaluation. In addition, it allows for flexible inferences on policy comparison with full uncertainty quantification. We demonstrate the effectiveness of the proposed inference method using Monte Carlo simulations and its application to an adolescent body mass index data set. △ Less

Submitted 11 February, 2026; originally announced February 2026.

Comments: Accepted for publication in JMLR

Kelix Technical Report

Authors: Boyang Ding, Chenglong Chu, Dunju Zang, Han Li, Jiangxia Cao, Kun Gai, Muhao Wei, Ruiming Tang, Shiyao Wang, Siyang Mao, Xinchen Luo, Yahui Liu, Zhixin Ling, Zhuoran Yang, Ziming Li, Chengru Song, Guorui Zhou, Guowang Zhang, Hao Peng, Hao Wang, Jiaxin Deng, Jin Ouyang, Jinghao Zhang, Lejian Ren, Qianqian Wang , et al. (6 additional authors not shown)

Abstract: Autoregressive large language models (LLMs) scale well by expressing diverse tasks as sequences of discrete natural-language tokens and training with next-token prediction, which unifies comprehension and generation under self-supervision. Extending this paradigm to multimodal data requires a shared, discrete representation across modalities. However, most vision-language models (VLMs) still rely… ▽ More Autoregressive large language models (LLMs) scale well by expressing diverse tasks as sequences of discrete natural-language tokens and training with next-token prediction, which unifies comprehension and generation under self-supervision. Extending this paradigm to multimodal data requires a shared, discrete representation across modalities. However, most vision-language models (VLMs) still rely on a hybrid interface: discrete text tokens paired with continuous Vision Transformer (ViT) features. Because supervision is largely text-driven, these models are often biased toward understanding and cannot fully leverage large-scale self-supervised learning on non-text data. Recent work has explored discrete visual tokenization to enable fully autoregressive multimodal modeling, showing promising progress toward unified understanding and generation. Yet existing discrete vision tokens frequently lose information due to limited code capacity, resulting in noticeably weaker understanding than continuous-feature VLMs. We present Kelix, a fully discrete autoregressive unified model that closes the understanding gap between discrete and continuous visual representations. △ Less

Submitted 12 February, 2026; v1 submitted 10 February, 2026; originally announced February 2026.

Comments: Work in progress

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Authors: Xiaoyu Tian, Haotian Wang, Shuaiting Chen, Hao Zhou, Kaichi Yu, Yudian Zhang, Jade Ouyang, Junxi Yin, Jiong Chen, Baoyan Guo, Lei Zhang, Junjie Tao, Yuansheng Song, Ming Cui, Chengwei Liu

Abstract: Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing methods still require manual intervention, depend on non-verifiable simulated environments, rely exclusively on either supervised fine-tuning (SFT) or reinforcement learning (RL), and struggle with stable long-horizon, multi… ▽ More Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing methods still require manual intervention, depend on non-verifiable simulated environments, rely exclusively on either supervised fine-tuning (SFT) or reinforcement learning (RL), and struggle with stable long-horizon, multi-turn learning. To address these challenges, we introduce ASTRA, a fully automated end-to-end framework for training tool-augmented language model agents via scalable data synthesis and verifiable reinforcement learning. ASTRA integrates two complementary components. First, a pipeline that leverages the static topology of tool-call graphs synthesizes diverse, structurally grounded trajectories, instilling broad and transferable tool-use competence. Second, an environment synthesis framework that captures the rich, compositional topology of human semantic reasoning converts decomposed question-answer traces into independent, code-executable, and rule-verifiable environments, enabling deterministic multi-turn RL. Based on this method, we develop a unified training methodology that integrates SFT with online RL using trajectory-level rewards to balance task completion and interaction efficiency. Experiments on multiple agentic tool-use benchmarks demonstrate that ASTRA-trained models achieve state-of-the-art performance at comparable scales, approaching closed-source systems while preserving core reasoning ability. We release the full pipelines, environments, and trained models at https://github.com/LianjiaTech/astra. △ Less

Submitted 30 January, 2026; v1 submitted 29 January, 2026; originally announced January 2026.

PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization

Authors: Tingyue Pan, Jie Ouyang, Mingyue Cheng, Qingchuan Li, Zirui Liu, Daoyu Wang, Mingfan Pan, Shuo Yu, Qi Liu

Abstract: Academic paper search is a fundamental task in scientific research, yet most existing approaches rely on rigid, predefined workflows that struggle with complex, conditional queries. To address this limitation, we propose PaperScout, an autonomous agent that reformulates paper search as a sequential decision-making process. Unlike static workflows, PaperScout dynamically decides whether, when, and… ▽ More Academic paper search is a fundamental task in scientific research, yet most existing approaches rely on rigid, predefined workflows that struggle with complex, conditional queries. To address this limitation, we propose PaperScout, an autonomous agent that reformulates paper search as a sequential decision-making process. Unlike static workflows, PaperScout dynamically decides whether, when, and how to invoke search and expand tools based on accumulated retrieval context. However, training such agents presents a fundamental challenge: standard reinforcement learning methods, typically designed for single-turn tasks, suffer from a granularity mismatch when applied to multi-turn agentic tasks-where token-level optimization diverges from the granularity of sequence-level interactions-leading to noisy credit assignment and unstable training dynamics. We introduce Proximal Sequence Policy Optimization (PSPO), a process-aware, sequence-level policy optimization method that aligns optimization with agent--environment interaction. Comprehensive experiments on both synthetic and real-world benchmarks demonstrate that PaperScout significantly outperforms strong workflow-driven and RL baselines in both recall and relevance, validating the effectiveness of our adaptive agentic framework and optimization strategy. △ Less

Submitted 18 March, 2026; v1 submitted 14 January, 2026; originally announced January 2026.

Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces

Authors: Siyang Li, Jiayi Ouyang, Zhenyao Cui, Ziwei Wang, Tianwang Jia, Feng Wan, Dongrui Wu

Abstract: Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) face significant deployment challenges due to inter-subject variability, signal non-stationarity, and computational constraints. While test-time adaptation (TTA) mitigates distribution shifts under online data streams without per-use calibration sessions, existing TTA approaches heavily rely on explicitly defined loss objectives tha… ▽ More Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) face significant deployment challenges due to inter-subject variability, signal non-stationarity, and computational constraints. While test-time adaptation (TTA) mitigates distribution shifts under online data streams without per-use calibration sessions, existing TTA approaches heavily rely on explicitly defined loss objectives that require backpropagation for updating model parameters, which incurs computational overhead, privacy risks, and sensitivity to noisy data streams. This paper proposes Backpropagation-Free Transformations (BFT), a TTA approach for EEG decoding that avoids these issues. BFT applies multiple sample-wise transformations, based on knowledge-guided augmentations or structured feature masking, to each test trial, producing multiple predictions for a single test sample using only forward passes. A learning-to-rank module, trained on source data, estimates the reliability of each transformed prediction, so that a weighted aggregation suppresses prediction uncertainty during online inference, with theoretical justification. Extensive experiments on five EEG datasets, covering motor imagery classification and driver drowsiness regression, demonstrate the effectiveness, versatility, robustness, and efficiency of BFT. This research enables lightweight plug-and-play BCIs on resource-constrained devices, broadening the real-world deployment of EEG-based BCIs. △ Less

Submitted 17 August, 2026; v1 submitted 12 January, 2026; originally announced January 2026.

Intent at a Glance: Gaze-Guided Robotic Manipulation via Foundation Models

Authors: Tracey Yee Hsin Tay, Xu Yan, Jonathan Ouyang, Daniel Wu, William Jiang, Jonathan Kao, Yuchen Cui

Abstract: Designing intuitive interfaces for robotic control remains a central challenge in enabling effective human-robot interaction, particularly in assistive care settings. Eye gaze offers a fast, non-intrusive, and intent-rich input modality, making it an attractive channel for conveying user goals. In this work, we present GAMMA (Gaze Assisted Manipulation for Modular Autonomy), a system that leverage… ▽ More Designing intuitive interfaces for robotic control remains a central challenge in enabling effective human-robot interaction, particularly in assistive care settings. Eye gaze offers a fast, non-intrusive, and intent-rich input modality, making it an attractive channel for conveying user goals. In this work, we present GAMMA (Gaze Assisted Manipulation for Modular Autonomy), a system that leverages ego-centric gaze tracking and a vision-language model to infer user intent and autonomously execute robotic manipulation tasks. By contextualizing gaze fixations within the scene, the system maps visual attention to high-level semantic understanding, enabling skill selection and parameterization without task-specific training. We evaluate GAMMA on a range of table-top manipulation tasks and compare it against baseline gaze-based control without reasoning. Results demonstrate that GAMMA provides robust, intuitive, and generalizable control, highlighting the potential of combining foundation models and gaze for natural and scalable robot autonomy. Project website: https://gamma0.vercel.app/ △ Less

Submitted 8 January, 2026; originally announced January 2026.

Comments: Accepted to 2025 RSS Robot Planning in the Era of Foundation Models (FM4RoboPlan) Workshop

EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture

Authors: Xin He, Longhui Wei, Jianbo Ouyang, Minghui Liao, Lingxi Xie, Qi Tian

Abstract: We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the number of tokens required for generation. This also ensures the training balance between understanding and generation tasks by applying the same compression rat… ▽ More We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the number of tokens required for generation. This also ensures the training balance between understanding and generation tasks by applying the same compression ratio to images. 2) Channel-wise concatenation instead of token-wise concatenation among visual understanding and generation tokens, which further reduces the visual tokens in unified architectures. 3) A shared-and-decoupled network that enables mutual improvements across tasks while meeting the task-specific modeling requirements. 4) A mixture-of-experts mechanism adopted for visual understanding encoder, which substantially improves perceptual capabilities with a few parameters increase. Extensive experiments have shown that EMMA-4B can significantly outperform state-of-the-art unified multimodal approaches (e.g., BAGEL-7B) in both efficiency and performance, while also achieving competitive results compared to recent multimodal understanding and generation experts (e.g., Qwen3-VL and Qwen-Image). We believe that EMMA lays a solid foundation for the future development of unified multimodal architectures. △ Less

Submitted 15 December, 2025; v1 submitted 4 December, 2025; originally announced December 2025.

Comments: Project Page: https://emma-umm.github.io/emma/

PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards

Authors: Shulei Wang, Longhui Wei, Xin He, Jianbo Ouyang, Hui Lu, Zhou Zhao, Qi Tian

Abstract: Personalized generation models for a single subject have demonstrated remarkable effectiveness, highlighting their significant potential. However, when extended to multiple subjects, existing models often exhibit degraded performance, particularly in maintaining subject consistency and adhering to textual prompts. We attribute these limitations to the absence of high-quality multi-subject datasets… ▽ More Personalized generation models for a single subject have demonstrated remarkable effectiveness, highlighting their significant potential. However, when extended to multiple subjects, existing models often exhibit degraded performance, particularly in maintaining subject consistency and adhering to textual prompts. We attribute these limitations to the absence of high-quality multi-subject datasets and refined post-training strategies. To address these challenges, we propose a scalable multi-subject data generation pipeline that leverages powerful single-subject generation models to construct diverse and high-quality multi-subject training data. Through this dataset, we first enable single-subject personalization models to acquire knowledge of synthesizing multi-image and multi-subject scenarios. Furthermore, to enhance both subject consistency and text controllability, we design a set of Pairwise Subject-Consistency Rewards and general-purpose rewards, which are incorporated into a refined reinforcement learning stage. To comprehensively evaluate multi-subject personalization, we introduce a new benchmark that assesses model performance using seven subsets across three dimensions. Extensive experiments demonstrate the effectiveness of our approach in advancing multi-subject personalized image generation. Github Link: https://github.com/wang-shulei/PSR △ Less

Submitted 9 April, 2026; v1 submitted 30 November, 2025; originally announced December 2025.

Comments: Accepted by CVPR 2026

Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning

Authors: Mingyue Cheng, Shuo Yu, Daoyu Wang, Qingchuan Li, Xiaoyu Tao, Jie Ouyang, Yucong Luo, Yitong Zhou, Qi Liu, Enhong Chen

Abstract: Large language models (LLMs) have rapidly evolved from single-turn text generators into the foundation of increasingly capable agents. As these agents take on more complex reasoning, decision making, tool use, and long-horizon tasks, reinforcement learning (RL) is becoming increasingly important for shaping their behavior. This shift is especially visible in agentic RL, where models must interact… ▽ More Large language models (LLMs) have rapidly evolved from single-turn text generators into the foundation of increasingly capable agents. As these agents take on more complex reasoning, decision making, tool use, and long-horizon tasks, reinforcement learning (RL) is becoming increasingly important for shaping their behavior. This shift is especially visible in agentic RL, where models must interact with tools and environments across multiple rounds rather than produce a single standalone response. In this regime, the usual view of a trajectory as one ever-growing token sequence becomes increasingly inadequate: it makes context evolution rigid and creates representation mismatches between rollout and training. This paper presents Agent-R1, a unified and modular framework for agentic RL built around step-level trajectory representation, flexible context management, and layered interfaces for workflows, environments and optimization. The key idea is to treat each interaction step as the basic reinforcement-learning transition, while keeping the optimization layer flexible: once the interaction is modeled at the step level, the framework can support token-level credit assignment, step-level credit assignment, or other compatible designs. These design choices make the framework compatible with a range of optimization strategies rather than tying it to a single algorithm. Together, these components provide a principled, extensible, and reusable substrate for agentic RL. △ Less

Submitted 30 May, 2026; v1 submitted 18 November, 2025; originally announced November 2025.

Comments: This paper serves as the technical report of the Agent-R1 project

A Voice-Enabled Virtual Patient System for Interactive Training in Standardized Clinical Assessment

Authors: Veronica Bossio Botero, Vijay Yadav, Jacob Ouyang, Anzar Abbas, Michelle Worthington

Abstract: Training mental health clinicians to conduct standardized clinical assessments is challenging due to a lack of scalable, realistic practice opportunities, which can impact data quality in clinical trials. To address this gap, we introduce a voice-enabled virtual patient simulation system powered by a large language model (LLM). This study describes the system's development and validates its abilit… ▽ More Training mental health clinicians to conduct standardized clinical assessments is challenging due to a lack of scalable, realistic practice opportunities, which can impact data quality in clinical trials. To address this gap, we introduce a voice-enabled virtual patient simulation system powered by a large language model (LLM). This study describes the system's development and validates its ability to generate virtual patients who accurately adhere to pre-defined clinical profiles, maintain coherent narratives, and produce realistic dialogue. We implemented a system using a LLM to simulate patients with specified symptom profiles, demographics, and communication styles. The system was evaluated by 5 experienced clinical raters who conducted 20 simulated structured MADRS interviews across 4 virtual patient personas. The virtual patients demonstrated strong adherence to their clinical profiles, with a mean item difference between rater-assigned MADRS scores and configured scores of 0.52 (SD=0.75). Inter-rater reliability across items was 0.90 (95% CI=0.68-0.99). Expert raters consistently rated the qualitative realism and cohesiveness of the virtual patients favorably, giving average ratings between "Agree" and "Strongly Agree." Our findings suggest that LLM-powered virtual patient simulations are a viable and scalable tool for training clinicians, capable of producing high-fidelity, clinically relevant practice scenarios. △ Less

Submitted 28 December, 2025; v1 submitted 1 November, 2025; originally announced November 2025.

Subverting Flexible Multiuser Communications via Movable Antenna-Enabled Jammer

Authors: Guojie Hu, Qingqing Wu, Lipeng Zhu, Kui Xu, Guoxin Li, Jiangbo Si, Jian Ouyang, Tong-Xing Zheng

Abstract: Movable antenna (MA) is an emerging technology which can reconfigure wireless channels via adaptive antenna position adjustments at transceivers, thereby bringing additional spatial degrees of freedom for improving system performance. In this paper, from a security perspective, we exploit the MAenabled legitimate jammer (MAJ) to subvert suspicious multiuser downlink communications consisting of on… ▽ More Movable antenna (MA) is an emerging technology which can reconfigure wireless channels via adaptive antenna position adjustments at transceivers, thereby bringing additional spatial degrees of freedom for improving system performance. In this paper, from a security perspective, we exploit the MAenabled legitimate jammer (MAJ) to subvert suspicious multiuser downlink communications consisting of one suspicious transmitter (ST) and multiple suspicious receivers (SRs). Specifically, our objective is to minimize the benefit (the sum rate of all SRs or the minimum rate among all SRs) of such suspicious communications, by jointly optimizing antenna positions and the jamming beamforming at the MAJ. However, the key challenge lies in that given the MAJ's actions, the ST can reactively adjust its power allocations to instead maximize its benefit for mitigating the unfavorable interference. Such flexible behavior of the ST confuses the optimization design of the MAJ to a certain extent. Facing this difficulty, corresponding to the above two different benefits: i) we respectively determine the optimal behavior of the ST given the MAJ's actions; ii) armed with these, we arrive at two simplified problems and then develop effective alternating optimization based algorithms to iteratively solve them. In addition to these, we also focus on the special case of two SRs, and reveal insightful conclusions about the deployment rule of antenna positions at the MAJ. Furthermore, we analyze the ideal antenna deployment scheme at the MAJ for achieving the globally performance lower bound. Numerical results demonstrate the effectiveness of our proposed schemes compared to conventional fixed-position antenna (FPA) and other competitive benchmarks. △ Less

Submitted 17 October, 2025; originally announced October 2025.

YpathRAG:A Retrieval-Augmented Generation Framework and Benchmark for Pathology

Authors: Deshui Yu, Yizhi Wang, Saihui Jin, Taojie Zhu, Fanyi Zeng, Wen Qian, Zirui Huang, Jingli Ouyang, Jiameng Li, Zhen Song, Tian Guan, Yonghong He

Abstract: Large language models (LLMs) excel on general tasks yet still hallucinate in high-barrier domains such as pathology. Prior work often relies on domain fine-tuning, which neither expands the knowledge boundary nor enforces evidence-grounded constraints. We therefore build a pathology vector database covering 28 subfields and 1.53 million paragraphs, and present YpathRAG, a pathology-oriented RAG fr… ▽ More Large language models (LLMs) excel on general tasks yet still hallucinate in high-barrier domains such as pathology. Prior work often relies on domain fine-tuning, which neither expands the knowledge boundary nor enforces evidence-grounded constraints. We therefore build a pathology vector database covering 28 subfields and 1.53 million paragraphs, and present YpathRAG, a pathology-oriented RAG framework with dual-channel hybrid retrieval (BGE-M3 dense retrieval coupled with vocabulary-guided sparse retrieval) and an LLM-based supportive-evidence judgment module that closes the retrieval-judgment-generation loop. We also release two evaluation benchmarks, YpathR and YpathQA-M. On YpathR, YpathRAG attains Recall@5 of 98.64%, a gain of 23 percentage points over the baseline; on YpathQA-M, a set of the 300 most challenging questions, it increases the accuracies of both general and medical LLMs by 9.0% on average and up to 15.6%. These results demonstrate improved retrieval quality and factual reliability, providing a scalable construction paradigm and interpretable evaluation for pathology-oriented RAG. △ Less

Submitted 7 October, 2025; originally announced October 2025.

GenAR: Next-Scale Autoregressive Generation for Spatial Gene Expression Prediction

Authors: Jiarui Ouyang, Yihui Wang, Yihang Gao, Yingxue Xu, Shu Yang, Hao Chen

Abstract: Spatial Transcriptomics (ST) offers spatially resolved gene expression but remains costly. Predicting expression directly from widely available Hematoxylin and Eosin (H&E) stained images presents a cost-effective alternative. However, most computational approaches (i) predict each gene independently, overlooking co-expression structure, and (ii) cast the task as continuous regression despite expre… ▽ More Spatial Transcriptomics (ST) offers spatially resolved gene expression but remains costly. Predicting expression directly from widely available Hematoxylin and Eosin (H&E) stained images presents a cost-effective alternative. However, most computational approaches (i) predict each gene independently, overlooking co-expression structure, and (ii) cast the task as continuous regression despite expression being discrete counts. This mismatch can yield biologically implausible outputs and complicate downstream analyses. We introduce GenAR, a multi-scale autoregressive framework that refines predictions from coarse to fine. GenAR clusters genes into hierarchical groups to expose cross-gene dependencies, models expression as codebook-free discrete token generation to directly predict raw counts, and conditions decoding on fused histological and spatial embeddings. From an information-theoretic perspective, the discrete formulation avoids log-induced biases and the coarse-to-fine factorization aligns with a principled conditional decomposition. Extensive experimental results on four Spatial Transcriptomics datasets across different tissue types demonstrate that GenAR achieves state-of-the-art performance, offering potential implications for precision medicine and cost-effective molecular profiling. Code is publicly available at https://github.com/oyjr/genar. △ Less

Submitted 5 October, 2025; originally announced October 2025.

OTTER: Open-Tagging via Text-Image Representation for Multi-modal Understanding

Authors: Jieer Ouyang, Xiaoneng Xiang, Zheng Wang, Yangkai Ding

Abstract: We introduce OTTER, a unified open-set multi-label tagging framework that harmonizes the stability of a curated, predefined category set with the adaptability of user-driven open tags. OTTER is built upon a large-scale, hierarchically organized multi-modal dataset, collected from diverse online repositories and annotated through a hybrid pipeline combining automated vision-language labeling with h… ▽ More We introduce OTTER, a unified open-set multi-label tagging framework that harmonizes the stability of a curated, predefined category set with the adaptability of user-driven open tags. OTTER is built upon a large-scale, hierarchically organized multi-modal dataset, collected from diverse online repositories and annotated through a hybrid pipeline combining automated vision-language labeling with human refinement. By leveraging a multi-head attention architecture, OTTER jointly aligns visual and textual representations with both fixed and open-set label embeddings, enabling dynamic and semantically consistent tagging. OTTER consistently outperforms competitive baselines on two benchmark datasets: it achieves an overall F1 score of 0.81 on Otter and 0.75 on Favorite, surpassing the next-best results by margins of 0.10 and 0.02, respectively. OTTER attains near-perfect performance on open-set labels, with F1 of 0.99 on Otter and 0.97 on Favorite, while maintaining competitive accuracy on predefined labels. These results demonstrate OTTER's effectiveness in bridging closed-set consistency with open-vocabulary flexibility for multi-modal tagging applications. △ Less

Submitted 1 October, 2025; originally announced October 2025.

Comments: Accepted at ICDM 2025 BigIS Workshop

How Much of Your Data Can Suck? Thresholds for Domain Performance and Emergent Misalignment in LLMs

Authors: Jian Ouyang, Arman T, Ge Jin

Abstract: This paper investigates the impact of incorrect data on the performance and safety of large language models (LLMs), specifically gpt-4o, during supervised fine-tuning (SFT). Although LLMs become increasingly vital across broad domains like finance, coding, law, and health, fine-tuning on incorrect data can lead to "emergent misalignment," producing harmful or deceptive outputs unrelated to the int… ▽ More This paper investigates the impact of incorrect data on the performance and safety of large language models (LLMs), specifically gpt-4o, during supervised fine-tuning (SFT). Although LLMs become increasingly vital across broad domains like finance, coding, law, and health, fine-tuning on incorrect data can lead to "emergent misalignment," producing harmful or deceptive outputs unrelated to the intended task. We evaluate gpt-4o models fine-tuned with varying ratios (10\% to 90\% correct) of both obviously and subtly incorrect data across four domains: coding, finance, health, and legal. Our findings show that even modest amounts of incorrect data (10-25\%) dramatically degrade domain performance and not moral alignment. A clear threshold of at least 50\% correct data is needed for models to consistently recover strong performance, though they rarely match the robustness and safety of the base model, which exhibits near-perfect alignment and zero dangerous completions out-of-the-box. This research emphasizes that the cost of incorrect data is heavy, highlighting the critical need for extremely high-quality data curation or, alternatively, leveraging robust base models without unnecessary fine-tuning for high-stakes applications. △ Less

Submitted 13 September, 2025; originally announced September 2025.

TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning

Authors: Chuang Jiang, Mingyue Cheng, Xiaoyu Tao, Qingyang Mao, Jie Ouyang, Qi Liu

Abstract: Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although recent large language model (LLM)-based methods have achieved promising results, most of them still rely on a single-turn reasoning paradigm that processes flattened tables in a single forward pass. This paradigm suffers from inherent limitations, including context ove… ▽ More Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although recent large language model (LLM)-based methods have achieved promising results, most of them still rely on a single-turn reasoning paradigm that processes flattened tables in a single forward pass. This paradigm suffers from inherent limitations, including context overflow on large tables, weak sensitivity to continuous numerical values, and the absence of explicit tool-use and reflection. In this paper, we propose TableMind, a tuning-based autonomous programmatic table agent that simulates the human-like cognitive schema of the multi-turn interaction within a lightweight LLM. Instead of adopting a training-free workflow design, TableMind learns to internalize planning, action, and reflection through a principled two-stage training strategy. To bootstrap structured table reasoning capabilities, we construct and filter high-quality reasoning data for the supervised fine-tuning (SFT) stage. To enable precise code generation, we introduce a designed multi-perspective reward scheme and a novel optimization objective in the reinforcement learning (RL) stage. Extensive experiments on diverse benchmarks demonstrate that TableMind consistently outperforms previous baselines, validating the effectiveness of training autonomous agents to improve overall performance. △ Less

Submitted 26 July, 2026; v1 submitted 7 September, 2025; originally announced September 2025.

Comments: Comments: 10 pages, 6 figures. Submitted to WSDM 2026

Re3: Learning to Balance Relevance & Recency for Temporal Information Retrieval

Authors: Jiawei Cao, Jie Ouyang, Zhaomeng Zhou, Mingyue Cheng, Yupeng Li, Jiaxian Yan, Qi Liu

Abstract: Temporal Information Retrieval (TIR) is a critical yet unresolved task for modern search systems, retrieving documents that not only satisfy a query's information need but also adhere to its temporal constraints. This task is shaped by two challenges: Relevance, ensuring alignment with the query's explicit temporal requirements, and Recency, selecting the freshest document among multiple versions.… ▽ More Temporal Information Retrieval (TIR) is a critical yet unresolved task for modern search systems, retrieving documents that not only satisfy a query's information need but also adhere to its temporal constraints. This task is shaped by two challenges: Relevance, ensuring alignment with the query's explicit temporal requirements, and Recency, selecting the freshest document among multiple versions. Existing methods often address the two challenges in isolation, relying on brittle heuristics that fail in scenarios where temporal requirements and staleness resistance are intertwined. To address this gap, we introduce Re2Bench, a benchmark specifically designed to disentangle and evaluate Relevance, Recency, and their hybrid combination. Building on this foundation, we propose Re3, a unified and lightweight framework that dynamically balances semantic and temporal information through a query-aware gating mechanism. On Re2Bench, Re3 achieves state-of-the-art results, leading in R@1 across all three subsets. Ablation studies with backbone sensitivity tests confirm robustness, showing strong generalization across diverse encoders and real-world settings. This work provides both a generalizable solution and a principled evaluation suite, advancing the development of temporally aware retrieval systems. Re3 and Re2Bench are available online: https://anonymous.4open.science/r/Re3-0C5A △ Less

Submitted 5 January, 2026; v1 submitted 1 September, 2025; originally announced September 2025.

Comments: This version is withdrawn because the authors are preparing a substantially revised manuscript with a significantly different problem setting, methodology, and overall framing. The current version no longer reflects the direction or contributions of the ongoing work

Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions

Authors: Bangsheng Tang, Carl Chengyan Fu, Fei Kou, Grigory Sizov, Haoci Zhang, Jason Park, Jiawen Liu, Jie You, Qirui Yang, Sachin Mehta, Shengyong Cai, Xiaodong Wang, Xingyu Liu, Yunlu Li, Yanjun Zhou, Wei Wei, Zhiwei Zhao, Zixi Qi, Adolfo Victoria, Aya Ibrahim, Bram Wasti, Changkyu Kim, Daniel Haziza, Fei Sun, Giancarlo Delfin , et al. (13 additional authors not shown)

Abstract: Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different operations (e.g., tree attention and multi-round speculative decoding) on GPU. In this paper, we detail the training and inference optimization techniques that we h… ▽ More Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different operations (e.g., tree attention and multi-round speculative decoding) on GPU. In this paper, we detail the training and inference optimization techniques that we have implemented to enable EAGLE-based speculative decoding at a production scale for Llama models. With these changes, we achieve a new state-of-the-art inference latency for Llama models. For example, Llama4 Maverick decodes at a speed of about 4 ms per token (with a batch size of one) on 8 NVIDIA H100 GPUs, which is 10% faster than the previously best known method. Furthermore, for EAGLE-based speculative decoding, our optimizations enable us to achieve a speed-up for large batch sizes between 1.4x and 2.0x at production scale. △ Less

Submitted 11 August, 2025; originally announced August 2025.

Comments: 15 pages

Power Battery Detection

Authors: Xiaoqi Zhao, Peiqian Cao, Chenyang Yu, Zonglei Feng, Lihe Zhang, Hanqi Liu, Jiaming Zuo, Youwei Pang, Jinsong Ouyang, Weisi Lin, Georges El Fakhri, Huchuan Lu, Xiaofeng Liu

Abstract: Power batteries are essential components in electric vehicles, where internal structural defects can pose serious safety risks. We conduct a comprehensive study on a new task, power battery detection (PBD), which aims to localize the dense endpoints of cathode and anode plates from industrial X-ray images for quality inspection. Manual inspection is inefficient and error-prone, while traditional v… ▽ More Power batteries are essential components in electric vehicles, where internal structural defects can pose serious safety risks. We conduct a comprehensive study on a new task, power battery detection (PBD), which aims to localize the dense endpoints of cathode and anode plates from industrial X-ray images for quality inspection. Manual inspection is inefficient and error-prone, while traditional vision algorithms struggle with densely packed plates, low contrast, scale variation, and imaging artifacts. To address this issue and drive more attention into this meaningful task, we present PBD5K, the first large-scale benchmark for this task, consisting of 5,000 X-ray images from nine battery types with fine-grained annotations and eight types of real-world visual interference. To support scalable and consistent labeling, we develop an intelligent annotation pipeline that combines image filtering, model-assisted pre-labeling, cross-verification, and layered quality evaluation. We formulate PBD as a point-level segmentation problem and propose MDCNeXt, a model designed to extract and integrate multi-dimensional structure clues including point, line, and count information from the plate itself. To improve discrimination between plates and suppress visual interference, MDCNeXt incorporates two state space modules. The first is a prompt-filtered module that learns contrastive relationships guided by task-specific prompts. The second is a density-aware reordering module that refines segmentation in regions with high plate density. In addition, we propose a distance-adaptive mask generation strategy to provide robust supervision under varying spatial distributions of anode and cathode positions. The source code and datasets will be publicly available at \href{https://github.com/Xiaoqi-Zhao-DLUT/X-ray-PBD}{PBD5K}. △ Less

Submitted 13 June, 2026; v1 submitted 11 August, 2025; originally announced August 2025.

Comments: Accepted by International Journal of Computer Vision (IJCV). Code: https://github.com/NTU-AI4X/X-ray-PBD

DiagR1: A Vision-Language Model Trained via Reinforcement Learning for Digestive Pathology Diagnosis

Authors: Minxi Ouyang, Lianghui Zhu, Yaqing Bao, Qiang Huang, Jingli Ouyang, Tian Guan, Xitong Ling, Jiawen Li, Song Duan, Wenbin Dai, Li Zheng, Xuemei Zhang, Yonghong He

Abstract: Multimodal large models have shown great potential in automating pathology image analysis. However, current multimodal models for gastrointestinal pathology are constrained by both data quality and reasoning transparency: pervasive noise and incomplete annotations in public datasets predispose vision language models to factual hallucinations when generating diagnostic text, while the absence of ex… ▽ More Multimodal large models have shown great potential in automating pathology image analysis. However, current multimodal models for gastrointestinal pathology are constrained by both data quality and reasoning transparency: pervasive noise and incomplete annotations in public datasets predispose vision language models to factual hallucinations when generating diagnostic text, while the absence of explicit intermediate reasoning chains renders the outputs difficult to audit and thus less trustworthy in clinical practice. To address these issues, we construct a large scale gastrointestinal pathology dataset containing both microscopic descriptions and diagnostic conclusions, and propose a prompt argumentation strategy that incorporates lesion classification and anatomical site information. This design guides the model to better capture image specific features and maintain semantic consistency in generation. Furthermore, we employ a post training pipeline that combines supervised fine tuning with Group Relative Policy Optimization (GRPO) to improve reasoning quality and output structure. Experimental results on real world pathology report generation tasks demonstrate that our approach significantly outperforms state of the art open source and proprietary baselines in terms of generation quality, structural completeness, and clinical relevance. Our solution outperforms state of the art models with 18.7% higher clinical relevance, 32.4% improved structural completeness, and 41.2% fewer diagnostic errors, demonstrating superior accuracy and clinical utility compared to existing solutions. △ Less

Submitted 24 July, 2025; originally announced July 2025.

Kwai Keye-VL Technical Report

Authors: Kwai Keye Team, Biao Yang, Bin Wen, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Hao Peng, Haojie Ding, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Jin Ouyang, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Shengnan Zhang, Siyang Mao , et al. (35 additional authors not shown)

Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce \textbf{Kwai Keye-VL}, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video unde… ▽ More While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce \textbf{Kwai Keye-VL}, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video understanding while maintaining robust general-purpose vision-language abilities. The development of Keye-VL rests on two core pillars: a massive, high-quality dataset exceeding 600 billion tokens with a strong emphasis on video, and an innovative training recipe. This recipe features a four-stage pre-training process for solid vision-language alignment, followed by a meticulous two-phase post-training process. The first post-training stage enhances foundational capabilities like instruction following, while the second phase focuses on stimulating advanced reasoning. In this second phase, a key innovation is our five-mode ``cold-start'' data mixture, which includes ``thinking'', ``non-thinking'', ``auto-think'', ``think with image'', and high-quality video data. This mixture teaches the model to decide when and how to reason. Subsequent reinforcement learning (RL) and alignment steps further enhance these reasoning capabilities and correct abnormal model behaviors, such as repetitive outputs. To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks (Figure 1). Furthermore, we develop and release the \textbf{KC-MMBench}, a new benchmark tailored for real-world short-video scenarios, where Keye-VL shows a significant advantage. △ Less

Submitted 2 July, 2025; originally announced July 2025.

Comments: Technical Report: https://github.com/Kwai-Keye/Keye

Score-based Generative Diffusion Models to Synthesize Full-dose FDG Brain PET from MRI in Epilepsy Patients

Authors: Jiaqi Wu, Jiahong Ouyang, Farshad Moradi, Mohammad Mehdi Khalighi, Greg Zaharchuk

Abstract: Fluorodeoxyglucose (FDG) PET to evaluate patients with epilepsy is one of the most common applications for simultaneous PET/MRI, given the need to image both brain structure and metabolism, but is suboptimal due to the radiation dose in this young population. Little work has been done synthesizing diagnostic quality PET images from MRI data or MRI data with ultralow-dose PET using advanced generat… ▽ More Fluorodeoxyglucose (FDG) PET to evaluate patients with epilepsy is one of the most common applications for simultaneous PET/MRI, given the need to image both brain structure and metabolism, but is suboptimal due to the radiation dose in this young population. Little work has been done synthesizing diagnostic quality PET images from MRI data or MRI data with ultralow-dose PET using advanced generative AI methods, such as diffusion models, with attention to clinical evaluations tailored for the epilepsy population. Here we compared the performance of diffusion- and non-diffusion-based deep learning models for the MRI-to-PET image translation task for epilepsy imaging using simultaneous PET/MRI in 52 subjects (40 train/2 validate/10 hold-out test). We tested three different models: 2 score-based generative diffusion models (SGM-Karras Diffusion [SGM-KD] and SGM-variance preserving [SGM-VP]) and a Transformer-Unet. We report results on standard image processing metrics as well as clinically relevant metrics, including congruency measures (Congruence Index and Congruency Mean Absolute Error) that assess hemispheric metabolic asymmetry, which is a key part of the clinical analysis of these images. The SGM-KD produced the best qualitative and quantitative results when synthesizing PET purely from T1w and T2 FLAIR images with the least mean absolute error in whole-brain specific uptake value ratio (SUVR) and highest intraclass correlation coefficient. When 1% low-dose PET images are included in the inputs, all models improve significantly and are interchangeable for quantitative performance and visual quality. In summary, SGMs hold great potential for pure MRI-to-PET translation, while all 3 model types can synthesize full-dose FDG-PET accurately using MRI and ultralow-dose PET. △ Less

Submitted 29 June, 2025; v1 submitted 12 June, 2025; originally announced June 2025.

Differential Privacy for Network Assortativity

Authors: Fei Ma, Jinzhi Ouyang, Xincheng Hu

Abstract: The analysis of network assortativity is of great importance for understanding the structural characteristics of and dynamics upon networks. Often, network assortativity is quantified using the assortativity coefficient that is defined based on the Pearson correlation coefficient between vertex degrees. It is well known that a network may contain sensitive information, such as the number of friend… ▽ More The analysis of network assortativity is of great importance for understanding the structural characteristics of and dynamics upon networks. Often, network assortativity is quantified using the assortativity coefficient that is defined based on the Pearson correlation coefficient between vertex degrees. It is well known that a network may contain sensitive information, such as the number of friends of an individual in a social network (which is abstracted as the degree of vertex.). So, the computation of the assortativity coefficient leads to privacy leakage, which increases the urgent need for privacy-preserving protocol. However, there has been no scheme addressing the concern above. To bridge this gap, in this work, we are the first to propose approaches based on differential privacy (DP for short). Specifically, we design three DP-based algorithms: $Local_{ru}$, $Shuffle_{ru}$, and $Decentral_{ru}$. The first two algorithms, based on Local DP (LDP) and Shuffle DP respectively, are designed for settings where each individual only knows his/her direct friends. In contrast, the third algorithm, based on Decentralized DP (DDP), targets scenarios where each individual has a broader view, i.e., also knowing his/her friends' friends. Theoretically, we prove that each algorithm enables an unbiased estimation of the assortativity coefficient of the network. We further evaluate the performance of the proposed algorithms using mean squared error (MSE), showing that $Shuffle_{ru}$ achieves the best performance, followed by $Decentral_{ru}$, with $Local_{ru}$ performing the worst. Note that these three algorithms have different assumptions, so each has its applicability scenario. Lastly, we conduct extensive numerical simulations, which demonstrate that the presented approaches are adequate to achieve the estimation of network assortativity under the demand for privacy protection. △ Less

Submitted 6 May, 2025; originally announced May 2025.

am-ELO: A Stable Framework for Arena-based LLM Evaluation

Authors: Zirui Liu, Jiatong Li, Yan Zhuang, Qi Liu, Shuanghong Shen, Jie Ouyang, Mingyue Cheng, Shijin Wang

Abstract: Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating system suffers from the inevitable instability problem due to ranking inconsistency and the lack of attention to the varying abilities of annotators. In this paper, we introduce a novel stable arena framework to address th… ▽ More Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating system suffers from the inevitable instability problem due to ranking inconsistency and the lack of attention to the varying abilities of annotators. In this paper, we introduce a novel stable arena framework to address these issues by enhancing the ELO Rating System. Specifically, we replace the iterative update method with a Maximum Likelihood Estimation (MLE) approach, m-ELO, and provide theoretical proof of the consistency and stability of the MLE approach for model ranking. Additionally, we proposed the am-ELO, which modify the Elo Rating's probability function to incorporate annotator abilities, enabling the simultaneous estimation of model scores and annotator reliability. Experiments demonstrate that this method ensures stability, proving that this framework offers a more robust, accurate, and stable evaluation method for LLMs. △ Less

Submitted 29 May, 2025; v1 submitted 6 May, 2025; originally announced May 2025.

Comments: ICML2025 Accepted

Dual Prompting for Diverse Count-level PET Denoising

Authors: Xiaofeng Liu, Yongsong Huang, Thibault Marin, Samira Vafay Eslahi, Tiss Amal, Yanis Chemli, Keith Johnson, Georges El Fakhri, Jinsong Ouyang

Abstract: The to-be-denoised positron emission tomography (PET) volumes are inherent with diverse count levels, which imposes challenges for a unified model to tackle varied cases. In this work, we resort to the recently flourished prompt learning to achieve generalizable PET denoising with different count levels. Specifically, we propose dual prompts to guide the PET denoising in a divide-and-conquer manne… ▽ More The to-be-denoised positron emission tomography (PET) volumes are inherent with diverse count levels, which imposes challenges for a unified model to tackle varied cases. In this work, we resort to the recently flourished prompt learning to achieve generalizable PET denoising with different count levels. Specifically, we propose dual prompts to guide the PET denoising in a divide-and-conquer manner, i.e., an explicitly count-level prompt to provide the specific prior information and an implicitly general denoising prompt to encode the essential PET denoising knowledge. Then, a novel prompt fusion module is developed to unify the heterogeneous prompts, followed by a prompt-feature interaction module to inject prompts into the features. The prompts are able to dynamically guide the noise-conditioned denoising process. Therefore, we are able to efficiently train a unified denoising model for various count levels, and deploy it to different cases with personalized prompts. We evaluated on 1940 low-count PET 3D volumes with uniformly randomly selected 13-22\% fractions of events from 97 $^{18}$F-MK6240 tau PET studies. It shows our dual prompting can largely improve the performance with informed count-level and outperform the count-conditional model. △ Less

Submitted 5 May, 2025; originally announced May 2025.

Comments: Published in IEEE International Symposium on Biomedical Imaging (ISBI) 2025

A Transformer-based Neural Architecture Search Method

Authors: Shang Wang, Huanrong Tang, Jianquan Ouyang

Abstract: This paper presents a neural architecture search method based on Transformer architecture, searching cross multihead attention computation ways for different number of encoder and decoder combinations. In order to search for neural network structures with better translation results, we considered perplexity as an auxiliary evaluation metric for the algorithm in addition to BLEU scores and iterativ… ▽ More This paper presents a neural architecture search method based on Transformer architecture, searching cross multihead attention computation ways for different number of encoder and decoder combinations. In order to search for neural network structures with better translation results, we considered perplexity as an auxiliary evaluation metric for the algorithm in addition to BLEU scores and iteratively improved each individual neural network within the population by a multi-objective genetic algorithm. Experimental results show that the neural network structures searched by the algorithm outperform all the baseline models, and that the introduction of the auxiliary evaluation metric can find better models than considering only the BLEU score as an evaluation metric. △ Less

Submitted 2 May, 2025; originally announced May 2025.

Comments: GECCO 2023

A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture

Authors: Shang Wang, Huanrong Tang, Jianquan Ouyang

Abstract: This paper proposes a neural architecture search space using ResNet as a framework, with search objectives including parameters for convolution, pooling, fully connected layers, and connectivity of the residual network. In addition to recognition accuracy, this paper uses the loss value on the validation set as a secondary objective for optimization. The experimental results demonstrate that the s… ▽ More This paper proposes a neural architecture search space using ResNet as a framework, with search objectives including parameters for convolution, pooling, fully connected layers, and connectivity of the residual network. In addition to recognition accuracy, this paper uses the loss value on the validation set as a secondary objective for optimization. The experimental results demonstrate that the search space of this paper together with the optimisation approach can find competitive network architectures on the MNIST, Fashion-MNIST and CIFAR100 datasets. △ Less

Submitted 2 May, 2025; originally announced May 2025.

Comments: GECCO 2023