This paper introduces MedReCo and MedReCo-VLM, a framework that enables entity-aware cross-image reasoning for medical imaging, allowing AI to compare current scans with prior studies and analogous ca…

The paper addresses 'Template Collapse' in 3D CT report generation—where models generate generic reports—by proposing CLarGen, a decoupled framework that significantly improves clinical accuracy and d…

The paper introduces a simple, token-efficient vision-language model for generating comprehensive pathology synoptic reports from multiple whole-slide images (WSIs), achieving high performance while s…

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

The paper introduces Text-Conditioned Layer-wise Internal Alignment (TC-LIA), a model-agnostic method that significantly improves the detection of 'mirage'—when Vision-Language Models confidently answ…

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reali…

The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensiti…

The paper analyzes that while multimodal large language models (MLLMs) offer superior semantic understanding for image generation, this enhanced capability significantly increases safety risks, partic…

The paper introduces Set-Distance Rewards (SDR), a permutation-invariant reward signal that effectively guides the generation of unordered radiology reports, significantly outperforming standard train…

This paper evaluates multiple LLMs (DeepSeek-R1, OpenBioLLM-Llama3, Qwen 3.5) for generating privacy-safe, high-quality synthetic mental health reports, demonstrating their effectiveness in expanding…

This paper introduces the concept of Safety Geometry Collapse, demonstrating that multimodal inputs degrade the safety separation of LLMs, and proposes ReGap, a training-free method that adaptively co…

The paper introduces PMC-InterCPT, a refined biomedical interleaved corpus that enhances multimodal continued pretraining by integrating figure-referencing body text alongside captions, leading to imp…

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

The paper introduces SafeMed-R1, a clinically audited LLM that significantly improves safety and ethical alignment for medical applications, matching or exceeding resident performance on safety-critic…

The paper proposes MMGuard, a proactive defense mechanism that injects unlearnable, human-imperceptible perturbations into multimodal data to prevent unauthorized fine-tuning of Large Vision-Language…

The authors demonstrate that fine-tuning a two-stage retrieval system using synthetic data generated by large language models can significantly improve the performance of medical semantic search for c…

肖代替了视觉令牌的永久删除，通过可恢复的路由来改进视觉语言模型的性能

The paper introduces CERA, a novel contrastive retrieval framework that improves RAG factuality and interpretability by using subjectivity-based hard negative selection and an auxiliary attention alig…

The paper explains the 'table-chart gap' in scientific claim verification by showing that multimodal LLMs successfully encode information from charts but fail to route it to the final prediction layer…

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and im…