A Novel Ophthalmic Benchmark for Evaluating Multimodal Large Language Models with Fundus Photographs and OCT Images

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.

Multimodal Human-AI Synergy for Medical Imaging Quality Control: A Hybrid Intelligence Framework with Adaptive Dataset Curation and Closed-Loop Evaluation

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.

TCM-3CEval: A Triaxial Benchmark for Assessing Responses from Large Language Models in Traditional Chinese Medicine

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.

Benchmarking Chinese Medical LLMs: A Medbench-based Analysis of Performance Gaps and Hierarchical Optimization Strategies

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.

YOLOE: Real-Time Seeing Anything

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.

YOLO-UniOW: Efficient Universal Open-World Object Detection

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.

LAMBDA: Covering the Multimodal Critical Scenarios for Automated Driving Systems by Search Space Quantization

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.

EADReg: Probabilistic Correspondence Generation with Efficient Autoregressive Diffusion Model for Outdoor Point Cloud Registration

Diffusion models have shown the great potential in the point cloud registration (PCR) task, especially for enhancing the robustness to challenging cases. However, existing diffusion-based PCR methods primarily focus on instance-level scenarios and struggle with outdoor LiDAR points, where the sparsity, irregularity, and huge point scale inherent in LiDAR points pose challenges to establishing dense global point-to-point correspondences. To address this issue, we propose a novel framework named EADReg for efficient and robust registration of LiDAR point clouds based on autoregressive diffusion models. EADReg follows a coarse-to-fine registration paradigm. In the coarse stage, we employ a Bi-directional Gaussian Mixture Model (BGMM) to reject outlier points and obtain purified point cloud pairs. BGMM establishes correspondences between the Gaussian Mixture Models (GMMs) from the source and target frames, enabling reliable coarse registration based on filtered features and geometric information. In the fine stage, we treat diffusion-based PCR as an autoregressive process to generate robust point correspondences, which are then iteratively refined on upper layers. Despite common criticisms of diffusion-based methods regarding inference speed, EADReg achieves runtime comparable to convolutional-based methods. Extensive experiments on the KITTI and NuScenes benchmark datasets highlight the state-of-the-art performance of our proposed method. Codes will be released upon publication.

Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection

Unsupervised anomaly detection (AD) aims to train robust detection models using only normal samples, while can generalize well to unseen anomalies. Recent research focuses on a unified unsupervised AD setting in which only one model is trained for all classes, i.e., n-class-one-model paradigm. Feature-reconstruction-based methods achieve state-of-the-art performance in this scenario. However, existing methods often suffer from a lack of sufficient contextual awareness, thereby compromising the quality of the reconstruction. To address this issue, we introduce a novel Reconstruction as Sequence (RAS) method, which enhances the contextual correspondence during feature reconstruction from a sequence modeling perspective. In particular, based on the transformer technique, we integrate a specialized RASFormer block into RAS. This block enables the capture of spatial relationships among different image regions and enhances sequential dependencies throughout the reconstruction process. By incorporating the RASFormer block, our RAS method achieves superior contextual awareness capabilities, leading to remarkable performance. Experimental results show that our RAS significantly outperforms competing methods, well demonstrating the effectiveness and superiority of our method. Our code is available at https://github.com/Nothingtolose9979/RAS.

Optimised ProPainter for Video Diminished Reality Inpainting

In this paper, part of the DREAMING Challenge - Diminished Reality for Emerging Applications in Medicine through Inpainting, we introduce a refined video inpainting technique optimised from the ProPainter method to meet the specialised demands of medical imaging, specifically in the context of oral and maxillofacial surgery. Our enhanced algorithm employs the zero-shot ProPainter, featuring optimized parameters and pre-processing, to adeptly manage the complex task of inpainting surgical video sequences, without requiring any training process. It aims to produce temporally coherent and detail-rich reconstructions of occluded regions, facilitating clearer views of operative fields. The efficacy of our approach is evaluated using comprehensive metrics, positioning it as a significant advancement in the application of diminished reality for medical purposes.