9 papers
Synergistic Perception-Reasoning Governance: Grounding Medical MLLMs with Verifiable Anatomical Evidence
Rui Hao, Qiankun Li, Junyuan Mao +4
Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report generation, yet inference-time hallucinations still undermine trustworthy use: mo…
SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics
Haolong Hu, Hanyu Li, Tiancheng He +6
MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploit long-context safety decay. Y…
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
ShiYing Huang, Liang Lin, Yuer Li +6
In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tensi…
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
Kaiwen Luo, Zhenhong Zhou, Leyan Wang +32
Advances in Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs). Among these, Large Audio Language Models (LALMs) are essential for realizi…
SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety
Zixuan Xu, Tiancheng He, Huahui Yi +7
Vision-language models remain susceptible to multimodal jailbreaks and over-refusal because safety hinges on both visual evidence and user intent, while many alignment pipelines su…
PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs
Jinyue Li, Yuci Liang, Qiankun Li +7
Computational pathology demands both visual pattern recognition and dynamic integration of structured domain knowledge, including taxonomy, grading criteria, and clinical evidence.…
Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning
Jing Tang, Kun Wang, Haolang Lu +7
Multimodal large language models (MLLMs) in long chain-of-thought reasoning often fail when different knowledge sources provide conflicting signals. We formalize these failures und…
CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns
Zhenhong Zhou, Shilinlu Yan, Chuanpu Liu +3
Large language models (LLMs) are increasingly deployed in cost-sensitive and on-device scenarios, and safety guardrails have advanced mainly in English. However, real-world Chinese…
Multi-scale Cascaded Foundation Model for Whole-body Organs-at-risk Segmentation
Rui Hao, Dayu Tan, Qiankun Li +3
Accurate segmentation of organs-at-risk (OARs) is vital for safe and precise radiotherapy and surgery. Most existing studies segment only a limited set of organs or regions, lackin…