3 citations · 10 across the 18 of their papers we have counts for
4 papers · 1 filter
MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models
Kevin Zhai, Utsav Singh, Anirudh Thatipelli +5
Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aes…
SAIL: Self-Improving Efficient Online Alignment of Large Language Models
Mucong Ding, Souradip Chakraborty, Vibhu Agrawal +5
Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches li…
Is poisoning a real threat to LLM alignment? Maybe more so than you think
Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu +2
Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement…
Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
Xiangyu Liu, Souradip Chakraborty, Yanchao Sun +1
Most existing works focus on direct perturbations to the victim's state/action or the underlying transition dynamics to demonstrate the vulnerability of reinforcement learning agen…