Related papers: Patho-R1: A Multimodal Reinforcement Learning-Base…
We explore multi-step reasoning in vision-language models (VLMs). The problem is challenging, as reasoning data consisting of multiple steps of visual and language processing are barely available. To overcome the challenge, we first…
Large language models (LLMs) constitute a breakthrough state-of-the-art Artificial Intelligence technology which is rapidly evolving and promises to aid in medical diagnosis. However, the correctness and the accuracy of their returns has…
Large annotated datasets are essential for training robust Computer-Aided Diagnosis (CAD) models for breast cancer detection or risk prediction. However, acquiring such datasets with fine-detailed annotation is both costly and…
Vision-language models have demonstrated impressive capabilities in general medical visual question answering, yet due to limited interpretability, it remains unclear whether their predictions reflect evidence-grounded clinical reasoning or…
Recent advances in reasoning with large language models (LLMs)has shown remarkable reasoning capabilities in domains such as mathematics and coding, yet their application to clinical diagnosis remains underexplored. Here, we introduce…
Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness.…
Vision-Language Models (VLMs) excel in many direct multimodal tasks but struggle to translate this prowess into effective decision-making within interactive, visually rich environments like games. This ``knowing-doing'' gap significantly…
Recently, improving the reasoning ability of large multimodal models (LMMs) through reinforcement learning has made great progress. However, most existing works are based on highly reasoning-intensive datasets such as mathematics and code,…
Multimodal large language models (MLLMs) are well suited to image aesthetic assessment, as they can capture high-level aesthetic features leveraging their cross-modal understanding capacity. However, the scarcity of multimodal aesthetic…
Medical vision-language models (VLMs) achieve strong performance in diagnostic reporting and image-text alignment, yet their underlying reasoning mechanisms remain fundamentally correlational, exhibiting reliance on superficial statistical…
Robotic foundation models require reasoning over complex visual scenes to execute adaptive actions in dynamic environments. While recent studies on latent-reasoning Vision-Language-Action (VLA) models have demonstrated the capability to…
Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-enabled autonomous systems. However, such fine-tuning relies…
Vision-Language Models (VLMs), exemplified by CLIP, have emerged as foundational for multimodal intelligence. However, their capacity for logical understanding remains significantly underexplored, resulting in critical ''logical…
Reasoning-focused large language models (LLMs) are rapidly evolving across various domains, yet their capabilities in handling complex legal problems remains underexplored. In this paper, we introduce Unilaw-R1, a large language model…
What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks? The strongest vision-language models (VLMs) show such broad visual reasoning is within reach, but the recipe behind…
The widespread use of chest X-rays (CXRs), coupled with a shortage of radiologists, has driven growing interest in automated CXR analysis and AI-assisted reporting. While existing vision-language models (VLMs) show promise in specific tasks…
Pre-trained on extensive text and image corpora, current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks. However, their performance is still lacking in physical domains that require…
Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of…
MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental…
Medical image understanding plays a crucial role in enabling automated diagnosis and data-driven clinical decision support. However, its progress is impeded by two primary challenges: the limited availability of high-quality annotated…