collaborators

9 papers

cs.CV2026

Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents

XiuYu Zhang, Junfeng Fang, Zhenkai Liang

Latent visual reasoning (LVR) inserts supervised latent tokens between perception and answer generation in vision-language models (VLMs). The field uses alignment between these lat…

cs.CL2026

Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data

XiuYu Zhang, Yi Shan, Junfeng Fang +1

Large language models are increasingly evaluated by other models, raising a natural question: can a model predict how a judge will score its own output? We find that the ability is…

cs.CL2026

Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer

Chenhang Cui, An Zhang, Yuxin Chen +5

Large vision-language models (LVLMs) have rapidly advanced across various domains, yet they still lag behind strong text-only large language models (LLMs) on tasks that require mul…

cs.LG2026

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint

Leheng Sheng, Changshuo Shen, Weixiang Zhao +6

As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable u…

cs.AI2026

Self-Guard: Defending Large Reasoning Models via enhanced self-reflection

Jingnan Zheng, Jingjun Xu, Yanzhen Luo +6

The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation…

cs.AI2025

RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards

Jingnan Zheng, Xiangtian Ji, Yijun Lu +6

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against th…