collaborators

5 papers

cs.LG2026

Constitutional On-Policy Safe Distillation

Ming Wen, Yuxuan Liu, Kun Yang +9

On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense token-level supervis…

cs.AI2026

OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences

Ming Wen, Kun Yang, Jingyu Zhang +4

While safety alignment for Multimodal Large Language Models (MLLMs) has gained significant attention, current paradigms primarily target malicious intent or situational violations.…

cs.LG2026

Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs

Ming Wen, Kun Yang, Xin Chen +4

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently gen…

cs.CR2026

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment

Kun Wang, Zherui Li, Zhenhong Zhou +8

Omni-modal Large Language Models (OLLMs) greatly expand LLMs' multimodal capabilities but also introduce cross-modal safety risks. However, a systematic understanding of vulnerabil…

cs.AI2026

CSR-Bench: A Benchmark for Evaluating the Cross-modal Safety and Reliability of MLLMs

Yuxuan Liu, Yuntian Shi, Kun Wang +2

Multimodal large language models (MLLMs) enable interaction over both text and images, but their safety behavior can be driven by unimodal shortcuts instead of true joint intent un…