Anqi Liu
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces the Configurable Safety Reward Model (CSRM), a novel reward model that can be jointly optimized for calibrated safety compliance and reward modeling, significantly improving LLM safety alignment across diverse and unseen safety configurations.
The paper introduces the Configurable Safety Reward Model (CSRM), a novel reward model that can be jointly optimized for calibrated safety compliance and reward modeling, significantly improving LLM safety alignment across diverse and unseen safety configurations.
This paper studies the behavior of mixture-of-experts (MoE) models under distribution shift and proposes an adversarial reweighting method to improve their calibration.
The paper introduces RobustRLlib, a library and benchmark for robust reinforcement learning that improves reusability and provides an empirical capability map of current robust RL algorithms.
Papers
RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
Xi Chen, Fengqi Hu, Zeyu Shen, Jiaying Xu +4 more
The paper introduces RobustRLlib, a library and benchmark for robust reinforcement learning that improves reusability and provides an empirical capability map of current robust RL algorithms.