collaborators

13 papers

cs.LG2026

SAF-OPD: Stable Advantage Fusion for On-Policy Distillation

Yifan Ding, Xincheng Wei, Yoshua Y. Li +7

Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stron…

cs.AI2026

Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification

Yunhao Feng, Ruixiao Lin, Ming Wen +12

LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed sa…

cs.CR2026

BraveGuard: From Open-World Threats to Safer Computer-Use Agents

Yunhao Feng, Xiaohu Du, Xinhao Deng +13

Computer-use agents extend language models from text generation to sustained interaction with files, terminals, browsers, and external tools. This shift creates safety risks that a…

cs.CR2026

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

Yunhao Feng, Yifan Ding, Yingshui Tan +6

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We…

cs.CL2026

ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking

Yutao Wu, Xiao Liu, Yinghui Li +5

Knowledge poisoning poses a critical threat to Retrieval-Augmented Generation (RAG) systems by injecting adversarial content into knowledge bases, tricking Large Language Models (L…

cs.CL2026

SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning

Run Zou, Jianhang Ding, Yifan Ding +3

Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge…