wovepaper — the arXiv observatory

papers

Publications (2)

cs.LG2026

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy

Eric Hanchen Jiang, Weixuan Ou, Run Liu +8

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense…

cs.AI2025

ME $^{3}$ -BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception

Siyi Lu, Run Liu, Dongsheng Yang +1

Autonomous driving systems face significant challenges in perceiving complex environments and making real-time decisions. Traditional modular approaches, while offering interpretab…

Publications (2)

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy

ME3-BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception

ME $^{3}$ -BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception