相关论文: MedVLThinker: Simple Baselines for Multimodal Medi…

Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning through iterative visual interaction. Medical VLMs often rely…

Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models (LLMs) can be substantially improved using outcome-level verification signals, such as unit tests for code or exact-match checks for…

Large language models (LLMs) excel on many NLP benchmarks, but their behavior on real-world, semi-structured prediction remains underexplored. We present LlaMADRS, a benchmark for structured clinical assessment from dialogue built on the…

Clinical reasoning in medicine is a hypothesis-driven process where physicians refine diagnoses from limited information through targeted history, physical examination, and diagnostic investigations. In contrast, current medical benchmarks…

Recent advances in image reasoning methods, particularly "Thinking with Images", have demonstrated remarkable success in Multimodal Large Language Models (MLLMs); however, this dynamic reasoning paradigm has not yet been extended to video…

Medical image analysis is essential in modern healthcare. Deep learning has redirected research focus toward complex medical multimodal tasks, including report generation and visual question answering. Traditional task-specific models often…

As multimodal large language models (MLLMs) frequently exhibit errors in complex video reasoning scenarios, correcting these errors is critical for uncovering their weaknesses and improving performance. However, existing benchmarks lack…

Despite notable advancements in multimodal reasoning, leading Multimodal Large Language Models (MLLMs) still underperform on vision-centric multimodal reasoning tasks in general scenarios. This shortfall stems from their predominant…

The rapid advancement of Large Vision Language Models (LVLMs) has demonstrated excellent abilities in various visual tasks. Building upon these developments, the thinking with images paradigm has emerged, enabling models to dynamically edit…

Reinforcement learning with verifiable rewards (RLVR) succeeds in reasoning tasks (e.g., math and code) by checking the final verifiable answer (i.e., a verifiable dot signal). However, extending this paradigm to open-ended generation is…

With the continuous expansion of Large Language Models (LLMs) and advances in reinforcement learning, LLMs have demonstrated exceptional reasoning capabilities, enabling them to address a wide range of complex problems. Inspired by these…

Multimodal Large Language Models (MLLMs) show promise for image-based regression tasks, but current approaches face key limitations. Recent methods fine-tune MLLMs using preset output vocabularies and generic task-level prompts (e.g., "How…

Despite significant advancements, current large language models (LLMs) and vision-language models (LVLMs) continue to struggle with complex, multi-step, cross-modal common sense reasoning tasks, often exhibiting a lack of "deliberative…

Large language models (LLMs) have demonstrated impressive reasoning capabilities, particularly in textual mathematical problem-solving. However, existing open-source image instruction fine-tuning datasets, containing limited question-answer…

Multimodal large language models (MLLMs) have emerged as powerful tools for computational pathology, offering unprecedented opportunities to integrate pathological images with language context for comprehensive diagnostic analysis. These…

Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their…

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced reasoning capabilities in Large Language Models. However, adapting RLVR to multimodal domains suffers from a critical \textit{perception-reasoning decoupling}.…

The main challenges limiting the adoption of deep learning-based solutions in medical workflows are the availability of annotated data and the lack of interpretability of such systems. Concept Bottleneck Models (CBMs) tackle the latter by…

The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning, a cornerstone of clinical practice.…

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For…