9 papers
RareLens: Towards End-to-End Rare Disease Care via Aligning Divergent Large Language Model Reasoning
Xi Chen, Hongru Zhou, Shiyu Feng +24
Rare diseases represent one of the most challenging settings for clinical decision-making, where heterogeneous presentations, sparse evidence and limited expertise create persisten…
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…
Large Vision-Language Models Get Lost in Attention
Gongli Xi, Ye Tian, Mengyu Yang +5
Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer…
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…
ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning
Gongli Xi, Kun Wang, Zeming Gao +4
Large multimodal reasoning models solve challenging visual problems via explicit long-chain inference: they gather visual clues from images and decode clues into textual tokens. Ye…
RareAlert: Aligning heterogeneous large language model reasoning for early rare disease risk screening
Xi Chen, Hongru Zhou, Huahui Yi +10
Missed and delayed diagnosis remains a major challenge in rare disease care. At the initial clinical encounters, physicians assess rare disease risk using only limited information…
SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models
Huahui Yi, Kun Wang, Qiankun Li +7
Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the…
OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
Liang Lin, Zhihao Xu, Junhao Dong +10
Large language model (LLM) alignment faces a critical dilemma when addressing multiple human preferences: improvements in one dimension frequently come at the expense of others, cr…
Advanced Long-term Earth System Forecasting
Hao Wu, Yuan Gao, Ruijian Gou +30
Reliable long-term forecasting of Earth system dynamics is fundamentally limited by instabilities in current artificial intelligence (AI) models during extended autoregressive simu…