CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making

In medical visual question answering (Med-VQA), achieving accurate responses relies on three critical steps: precise perception of medical imaging data, logical reasoning grounded in visual input and textual questions, and coherent answer derivation from the reasoning process. Recent advances in general vision-language models (VLMs) show that large-scale reinforcement learning (RL) could significantly enhance both reasoning capabilities and overall model performance. However, their application in medical domains is hindered by two fundamental challenges: 1) misalignment between perceptual understanding and reasoning stages, and 2) inconsistency between reasoning pathways and answer generation, both compounded by the scarcity of high-quality medical datasets for effective large-scale RL. In this paper, we first introduce Med-Zero-17K, a curated dataset for pure RL-based training, encompassing over 30 medical image modalities and 24 clinical tasks. Moreover, we propose a novel large-scale RL framework for Med-VLMs, Consistency-Aware Preference Optimization (CAPO), which integrates rewards to ensure fidelity between perception and reasoning, consistency in reasoning-to-answer derivation, and rule-based accuracy for final responses. Extensive experiments on both in-domain and out-of-domain scenarios demonstrate the superiority of our method over strong VLM baselines, showcasing strong generalization capability to 3D Med-VQA benchmarks and R1-like training paradigms.

Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning

Medical Question-Answering (QA) encompasses a broad spectrum of tasks, including multiple choice questions (MCQ), open-ended text generation, and complex computational reasoning. Despite this variety, a unified framework for delivering high-quality medical QA has yet to emerge. Although recent progress in reasoning-augmented large language models (LLMs) has shown promise, their ability to achieve comprehensive medical understanding is still largely unexplored. In this paper, we present Med-U1, a unified framework for robust reasoning across medical QA tasks with diverse output formats, ranging from MCQs to complex generation and computation tasks. Med-U1 employs pure large-scale reinforcement learning with mixed rule-based binary reward functions, incorporating a length penalty to manage output verbosity. With multi-objective reward optimization, Med-U1 directs LLMs to produce concise and verifiable reasoning chains. Empirical results reveal that Med-U1 significantly improves performance across multiple challenging Med-QA benchmarks, surpassing even larger specialized and proprietary models. Furthermore, Med-U1 demonstrates robust generalization to out-of-distribution (OOD) tasks. Extensive analysis presents insights into training strategies, reasoning chain length control, and reward design for medical LLMs. The code will be released.

3D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks

Medical Visual Question Answering (Med-VQA) holds significant potential for clinical decision support, yet existing efforts primarily focus on 2D imaging with limited task diversity. This paper presents 3D-RAD, a large-scale dataset designed to advance 3D Med-VQA using radiology CT scans. The 3D-RAD dataset encompasses six diverse VQA tasks: anomaly detection, image observation, medical computation, existence detection, static temporal diagnosis, and longitudinal temporal diagnosis. It supports both open- and closed-ended questions while introducing complex reasoning challenges, including computational tasks and multi-stage temporal analysis, to enable comprehensive benchmarking. Extensive evaluations demonstrate that existing vision-language models (VLMs), especially medical VLMs exhibit limited generalization, particularly in multi-temporal tasks, underscoring the challenges of real-world 3D diagnostic reasoning. To drive future advancements, we release a high-quality training set 3D-RAD-T of 136,195 expert-aligned samples, showing that fine-tuning on this dataset could significantly enhance model performance. Our dataset and code, aiming to catalyze multimodal medical AI research and establish a robust foundation for 3D medical visual understanding, are publicly available at https://github.com/Tang-xiaoxiao/M3D-RAD.

SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis

Surgical video understanding is pivotal for enabling automated intraoperative decision-making, skill assessment, and postoperative quality improvement. However, progress in developing surgical video foundation models (FMs) remains hindered by the scarcity of large-scale, diverse datasets for pretraining and systematic evaluation. In this paper, we introduce \textbf{SurgBench}, a unified surgical video benchmarking framework comprising a pretraining dataset, \textbf{SurgBench-P}, and an evaluation benchmark, \textbf{SurgBench-E}. SurgBench offers extensive coverage of diverse surgical scenarios, with SurgBench-P encompassing 53 million frames across 22 surgical procedures and 11 specialties, and SurgBench-E providing robust evaluation across six categories (phase classification, camera motion, tool recognition, disease diagnosis, action classification, and organ detection) spanning 72 fine-grained tasks. Extensive experiments reveal that existing video FMs struggle to generalize across varied surgical video analysis tasks, whereas pretraining on SurgBench-P yields substantial performance improvements and superior cross-domain generalization to unseen procedures and modalities. Our dataset and code are available upon request.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning

Text Image Machine Translation (TIMT)-the task of translating textual content embedded in images-is critical for applications in accessibility, cross-lingual information access, and real-world document understanding. However, TIMT remains a complex challenge due to the need for accurate optical character recognition (OCR), robust visual-text reasoning, and high-quality translation, often requiring cascading multi-stage pipelines. Recent advances in large-scale Reinforcement Learning (RL) have improved reasoning in Large Language Models (LLMs) and Multimodal LLMs (MLLMs), but their application to end-to-end TIMT is still underexplored. To bridge this gap, we introduce MT$^{3}$, the first framework to apply Multi-Task RL to MLLMs for end-to-end TIMT. MT$^{3}$ adopts a multi-task optimization paradigm targeting three key sub-skills: text recognition, context-aware reasoning, and translation. It is trained using a novel multi-mixed reward mechanism that adapts rule-based RL strategies to TIMT's intricacies, offering fine-grained, non-binary feedback across tasks. Furthermore, to facilitate the evaluation of TIMT in authentic cross-cultural and real-world social media contexts, we introduced XHSPost, the first social media TIMT benchmark. Our MT$^{3}$-7B-Zero achieves state-of-the-art results on the latest in-domain MIT-10M benchmark, outperforming strong baselines such as Qwen2.5-VL-72B and InternVL2.5-78B by notable margins across multiple metrics. Additionally, the model shows strong generalization to out-of-distribution language pairs and datasets. In-depth analyses reveal how multi-task synergy, reinforcement learning initialization, curriculum design, and reward formulation contribute to advancing MLLM-driven TIMT.

Towards Reliable Large Audio Language Model

Recent advancements in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound. However, these models still lack the ability to recognize their knowledge boundaries and refuse to answer questions they don't know proactively. While there have been successful attempts to enhance the reliability of LLMs, reliable LALMs remain largely unexplored. In this paper, we systematically investigate various approaches towards reliable LALMs, including training-free methods such as multi-modal chain-of-thought (MCoT), and training-based methods such as supervised fine-tuning (SFT). Besides, we identify the limitations of previous evaluation metrics and propose a new metric, the Reliability Gain Index (RGI), to assess the effectiveness of different reliable methods. Our findings suggest that both training-free and training-based methods enhance the reliability of LALMs to different extents. Moreover, we find that awareness of reliability is a "meta ability", which can be transferred across different audio modalities, although significant structural and content differences exist among sound, music, and speech.

Practical Equivalence Testing and Its Application in Synthetic Pre-Crash Scenario Validation

The use of representative pre-crash scenarios is critical for assessing the safety impact of driving automation systems through simulation. However, a gap remains in the robust evaluation of the similarity between synthetic and real-world pre-crash scenarios and their crash characteristics. Without proper validation, it cannot be ensured that the synthetic test scenarios adequately represent real-world driving behaviors and crash characteristics. One reason for this validation gap is the lack of focus on methods to confirm that the synthetic test scenarios are practically equivalent to real-world ones, given the assessment scope. Traditional statistical methods, like significance testing, focus on detecting differences rather than establishing equivalence; since failure to detect a difference does not imply equivalence, they are of limited applicability for validating synthetic pre-crash scenarios and crash characteristics. This study addresses this gap by proposing an equivalence testing method based on the Bayesian Region of Practical Equivalence (ROPE) framework. This method is designed to assess the practical equivalence of scenario characteristics that are most relevant for the intended assessment, making it particularly appropriate for the domain of virtual safety assessments. We first review existing equivalence testing methods. Then we propose and demonstrate the Bayesian ROPE-based method by testing the equivalence of two rear-end pre-crash datasets. Our approach focuses on the most relevant scenario characteristics. Our analysis provides insights into the practicalities and effectiveness of equivalence testing in synthetic test scenario validation and demonstrates the importance of testing for improving the credibility of synthetic data for automated vehicle safety assessment, as well as the credibility of subsequent safety impact assessments.

Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression

Ordinal regression bridges regression and classification by assigning objects to ordered classes. While human experts rely on discriminative patch-level features for decisions, current approaches are limited by the availability of only image-level ordinal labels, overlooking fine-grained patch-level characteristics. In this paper, we propose a Dual-level Fuzzy Learning with Patch Guidance framework, named DFPG that learns precise feature-based grading boundaries from ambiguous ordinal labels, with patch-level supervision. Specifically, we propose patch-labeling and filtering strategies to enable the model to focus on patch-level features exclusively with only image-level ordinal labels available. We further design a dual-level fuzzy learning module, which leverages fuzzy logic to quantitatively capture and handle label ambiguity from both patch-wise and channel-wise perspectives. Extensive experiments on various image ordinal regression datasets demonstrate the superiority of our proposed method, further confirming its ability in distinguishing samples from difficult-to-classify categories. The code is available at https://github.com/ZJUMAI/DFPG-ord.

Uncertainty-Aware Multi-Expert Knowledge Distillation for Imbalanced Disease Grading

Automatic disease image grading is a significant application of artificial intelligence for healthcare, enabling faster and more accurate patient assessments. However, domain shifts, which are exacerbated by data imbalance, introduce bias into the model, posing deployment difficulties in clinical applications. To address the problem, we propose a novel \textbf{U}ncertainty-aware \textbf{M}ulti-experts \textbf{K}nowledge \textbf{D}istillation (UMKD) framework to transfer knowledge from multiple expert models to a single student model. Specifically, to extract discriminative features, UMKD decouples task-agnostic and task-specific features with shallow and compact feature alignment in the feature space. At the output space, an uncertainty-aware decoupled distillation (UDD) mechanism dynamically adjusts knowledge transfer weights based on expert model uncertainties, ensuring robust and reliable distillation. Additionally, UMKD also tackles the problems of model architecture heterogeneity and distribution discrepancies between source and target domains, which are inadequately tackled by previous KD approaches. Extensive experiments on histology prostate grading (\textit{SICAPv2}) and fundus image grading (\textit{APTOS}) demonstrate that UMKD achieves a new state-of-the-art in both source-imbalanced and target-imbalanced scenarios, offering a robust and practical solution for real-world disease image grading.

Matrix Factorization with Dynamic Multi-view Clustering for Recommender System

Matrix factorization (MF), a cornerstone of recommender systems, decomposes user-item interaction matrices into latent representations. Traditional MF approaches, however, employ a two-stage, non-end-to-end paradigm, sequentially performing recommendation and clustering, resulting in prohibitive computational costs for large-scale applications like e-commerce and IoT, where billions of users interact with trillions of items. To address this, we propose Matrix Factorization with Dynamic Multi-view Clustering (MFDMC), a unified framework that balances efficient end-to-end training with comprehensive utilization of web-scale data and enhances interpretability. MFDMC leverages dynamic multi-view clustering to learn user and item representations, adaptively pruning poorly formed clusters. Each entity's representation is modeled as a weighted projection of robust clusters, capturing its diverse roles across views. This design maximizes representation space utilization, improves interpretability, and ensures resilience for downstream tasks. Extensive experiments demonstrate MFDMC's superior performance in recommender systems and other representation learning domains, such as computer vision, highlighting its scalability and versatility.