Abstract:In ophthalmic surgery, developing an AI system capable of interpreting surgical videos and predicting subsequent operations requires numerous ophthalmic surgical videos with high-quality annotations, which are difficult to collect due to privacy concerns and labor consumption. Text-guided video generation (T2V) emerges as a promising solution to overcome this issue by generating ophthalmic surgical videos based on surgeon instructions. In this paper, we present Ophora, a pioneering model that can generate ophthalmic surgical videos following natural language instructions. To construct Ophora, we first propose a Comprehensive Data Curation pipeline to convert narrative ophthalmic surgical videos into a large-scale, high-quality dataset comprising over 160K video-instruction pairs, Ophora-160K. Then, we propose a Progressive Video-Instruction Tuning scheme to transfer rich spatial-temporal knowledge from a T2V model pre-trained on natural video-text datasets for privacy-preserved ophthalmic surgical video generation based on Ophora-160K. Experiments on video quality evaluation via quantitative analysis and ophthalmologist feedback demonstrate that Ophora can generate realistic and reliable ophthalmic surgical videos based on surgeon instructions. We also validate the capability of Ophora for empowering downstream tasks of ophthalmic surgical workflow understanding. Code is available at https://github.com/mar-cry/Ophora.
Abstract:Despite strong performance in medical question-answering, the clinical adoption of Large Language Models (LLMs) is critically hampered by their opaque 'black-box' reasoning, limiting clinician trust. This challenge is compounded by the predominant reliance of current medical LLMs on corpora from scientific literature or synthetic data, which often lack the granular expert validation and high clinical relevance essential for advancing their specialized medical capabilities. To address these critical gaps, we introduce a highly clinically relevant dataset with 31,247 medical question-answer pairs, each accompanied by expert-validated chain-of-thought (CoT) explanations. This resource, spanning multiple clinical domains, was curated via a scalable human-LLM hybrid pipeline: LLM-generated rationales were iteratively reviewed, scored, and refined by medical experts against a structured rubric, with substandard outputs revised through human effort or guided LLM regeneration until expert consensus. This publicly available dataset provides a vital source for the development of medical LLMs that capable of transparent and verifiable reasoning, thereby advancing safer and more interpretable AI in medicine.
Abstract:Recent advances in general medical AI have made significant strides, but existing models often lack the reasoning capabilities needed for complex medical decision-making. This paper presents GMAI-VL-R1, a multimodal medical reasoning model enhanced by reinforcement learning (RL) to improve its reasoning abilities. Through iterative training, GMAI-VL-R1 optimizes decision-making, significantly boosting diagnostic accuracy and clinical support. We also develop a reasoning data synthesis method, generating step-by-step reasoning data via rejection sampling, which further enhances the model's generalization. Experimental results show that after RL training, GMAI-VL-R1 excels in tasks such as medical image diagnosis and visual question answering. While the model demonstrates basic memorization with supervised fine-tuning, RL is crucial for true generalization. Our work establishes new evaluation benchmarks and paves the way for future advancements in medical reasoning models. Code, data, and model will be released at \href{https://github.com/uni-medical/GMAI-VL-R1}{this link}.
Abstract:Large language models (LLMs) excel in various NLP tasks and modern medicine, but their evaluation in traditional Chinese medicine (TCM) is underexplored. To address this, we introduce TCM3CEval, a benchmark assessing LLMs in TCM across three dimensions: core knowledge mastery, classical text understanding, and clinical decision-making. We evaluate diverse models, including international (e.g., GPT-4o), Chinese (e.g., InternLM), and medical-specific (e.g., PLUSE). Results show a performance hierarchy: all models have limitations in specialized subdomains like Meridian & Acupoint theory and Various TCM Schools, revealing gaps between current capabilities and clinical needs. Models with Chinese linguistic and cultural priors perform better in classical text interpretation and clinical reasoning. TCM-3CEval sets a standard for AI evaluation in TCM, offering insights for optimizing LLMs in culturally grounded medical domains. The benchmark is available on Medbench's TCM track, aiming to assess LLMs' TCM capabilities in basic knowledge, classic texts, and clinical decision-making through multidimensional questions and real cases.
Abstract:The evaluation and improvement of medical large language models (LLMs) are critical for their real-world deployment, particularly in ensuring accuracy, safety, and ethical alignment. Existing frameworks inadequately dissect domain-specific error patterns or address cross-modal challenges. This study introduces a granular error taxonomy through systematic analysis of top 10 models on MedBench, categorizing incorrect responses into eight types: Omissions, Hallucination, Format Mismatch, Causal Reasoning Deficiency, Contextual Inconsistency, Unanswered, Output Error, and Deficiency in Medical Language Generation. Evaluation of 10 leading models reveals vulnerabilities: despite achieving 0.86 accuracy in medical knowledge recall, critical reasoning tasks show 96.3% omission, while safety ethics evaluations expose alarming inconsistency (robustness score: 0.79) under option shuffled. Our analysis uncovers systemic weaknesses in knowledge boundary enforcement and multi-step reasoning. To address these, we propose a tiered optimization strategy spanning four levels, from prompt engineering and knowledge-augmented retrieval to hybrid neuro-symbolic architectures and causal reasoning frameworks. This work establishes an actionable roadmap for developing clinically robust LLMs while redefining evaluation paradigms through error-driven insights, ultimately advancing the safety and trustworthiness of AI in high-stakes medical environments.
Abstract:Object detection and segmentation are widely employed in computer vision applications, yet conventional models like YOLO series, while efficient and accurate, are limited by predefined categories, hindering adaptability in open scenarios. Recent open-set methods leverage text prompts, visual cues, or prompt-free paradigm to overcome this, but often compromise between performance and efficiency due to high computational demands or deployment complexity. In this work, we introduce YOLOE, which integrates detection and segmentation across diverse open prompt mechanisms within a single highly efficient model, achieving real-time seeing anything. For text prompts, we propose Re-parameterizable Region-Text Alignment (RepRTA) strategy. It refines pretrained textual embeddings via a re-parameterizable lightweight auxiliary network and enhances visual-textual alignment with zero inference and transferring overhead. For visual prompts, we present Semantic-Activated Visual Prompt Encoder (SAVPE). It employs decoupled semantic and activation branches to bring improved visual embedding and accuracy with minimal complexity. For prompt-free scenario, we introduce Lazy Region-Prompt Contrast (LRPC) strategy. It utilizes a built-in large vocabulary and specialized embedding to identify all objects, avoiding costly language model dependency. Extensive experiments show YOLOE's exceptional zero-shot performance and transferability with high inference efficiency and low training cost. Notably, on LVIS, with 3$\times$ less training cost and 1.4$\times$ inference speedup, YOLOE-v8-S surpasses YOLO-Worldv2-S by 3.5 AP. When transferring to COCO, YOLOE-v8-L achieves 0.6 AP$^b$ and 0.4 AP$^m$ gains over closed-set YOLOv8-L with nearly 4$\times$ less training time. Code and models are available at https://github.com/THU-MIG/yoloe.
Abstract:In recent years, large language models (LLMs) have demonstrated remarkable potential across various medical applications. Building on this foundation, multimodal large language models (MLLMs) integrate LLMs with visual models to process diverse inputs, including clinical data and medical images. In ophthalmology, LLMs have been explored for analyzing optical coherence tomography (OCT) reports, assisting in disease classification, and even predicting treatment outcomes. However, existing MLLM benchmarks often fail to capture the complexities of real-world clinical practice, particularly in the analysis of OCT images. Many suffer from limitations such as small sample sizes, a lack of diverse OCT datasets, and insufficient expert validation. These shortcomings hinder the accurate assessment of MLLMs' ability to interpret OCT scans and their broader applicability in ophthalmology. Our dataset, curated through rigorous quality control and expert annotation, consists of 439 fundus images and 75 OCT images. Using a standardized API-based framework, we assessed seven mainstream MLLMs and observed significant variability in diagnostic accuracy across different diseases. While some models performed well in diagnosing conditions such as diabetic retinopathy and age-related macular degeneration, they struggled with others, including choroidal neovascularization and myopia, highlighting inconsistencies in performance and the need for further refinement. Our findings emphasize the importance of developing clinically relevant benchmarks to provide a more accurate assessment of MLLMs' capabilities. By refining these models and expanding their scope, we can enhance their potential to transform ophthalmic diagnosis and treatment.
Abstract:Medical imaging quality control (QC) is essential for accurate diagnosis, yet traditional QC methods remain labor-intensive and subjective. To address this challenge, in this study, we establish a standardized dataset and evaluation framework for medical imaging QC, systematically assessing large language models (LLMs) in image quality assessment and report standardization. Specifically, we first constructed and anonymized a dataset of 161 chest X-ray (CXR) radiographs and 219 CT reports for evaluation. Then, multiple LLMs, including Gemini 2.0-Flash, GPT-4o, and DeepSeek-R1, were evaluated based on recall, precision, and F1 score to detect technical errors and inconsistencies. Experimental results show that Gemini 2.0-Flash achieved a Macro F1 score of 90 in CXR tasks, demonstrating strong generalization but limited fine-grained performance. DeepSeek-R1 excelled in CT report auditing with a 62.23\% recall rate, outperforming other models. However, its distilled variants performed poorly, while InternLM2.5-7B-chat exhibited the highest additional discovery rate, indicating broader but less precise error detection. These findings highlight the potential of LLMs in medical imaging QC, with DeepSeek-R1 and Gemini 2.0-Flash demonstrating superior performance.
Abstract:Traditional object detection models are constrained by the limitations of closed-set datasets, detecting only categories encountered during training. While multimodal models have extended category recognition by aligning text and image modalities, they introduce significant inference overhead due to cross-modality fusion and still remain restricted by predefined vocabulary, leaving them ineffective at handling unknown objects in open-world scenarios. In this work, we introduce Universal Open-World Object Detection (Uni-OWD), a new paradigm that unifies open-vocabulary and open-world object detection tasks. To address the challenges of this setting, we propose YOLO-UniOW, a novel model that advances the boundaries of efficiency, versatility, and performance. YOLO-UniOW incorporates Adaptive Decision Learning to replace computationally expensive cross-modality fusion with lightweight alignment in the CLIP latent space, achieving efficient detection without compromising generalization. Additionally, we design a Wildcard Learning strategy that detects out-of-distribution objects as "unknown" while enabling dynamic vocabulary expansion without the need for incremental learning. This design empowers YOLO-UniOW to seamlessly adapt to new categories in open-world environments. Extensive experiments validate the superiority of YOLO-UniOW, achieving achieving 34.6 AP and 30.0 APr on LVIS with an inference speed of 69.6 FPS. The model also sets benchmarks on M-OWODB, S-OWODB, and nuScenes datasets, showcasing its unmatched performance in open-world object detection. Code and models are available at https://github.com/THU-MIG/YOLO-UniOW.
Abstract:Scenario-based virtual testing is one of the most significant methods to test and evaluate the safety of automated driving systems (ADSs). However, it is impractical to enumerate all concrete scenarios in a logical scenario space and test them exhaustively. Recently, Black-Box Optimization (BBO) was introduced to accelerate the scenario-based test of ADSs by utilizing the historical test information to generate new test cases. However, a single optimum found by the BBO algorithm is insufficient for the purpose of a comprehensive safety evaluation of ADSs in a logical scenario. In fact, all the subspaces representing danger in the logical scenario space, rather than only the most critical concrete scenario, play a more significant role for the safety evaluation. Covering as many of the critical concrete scenarios in a logical scenario space through a limited number of tests is defined as the Black-Box Coverage (BBC) problem in this paper. We formalized this problem in a sample-based search paradigm and constructed a coverage criterion with Confusion Matrix Analysis. Furthermore, we propose LAMBDA (Latent-Action Monte-Carlo Beam Search with Density Adaption) to solve BBC problems. LAMBDA can quickly focus on critical subspaces by recursively partitioning the logical scenario space into accepted and rejected parts. Compared with its predecessor LaMCTS, LAMBDA introduces sampling density to overcome the sampling bias from optimization and Beam Search to obtain more parallelizability. Experimental results show that LAMBDA achieves state-of-the-art performance among all baselines and can reach at most 33 and 6000 times faster than Random Search to get 95% coverage of the critical areas in 2- and 5-dimensional synthetic functions, respectively. Experiments also demonstrate that LAMBDA has a promising future in the safety evaluation of ADSs in virtual tests.