← Search

Xingyuan Dai

2 accepted papers

2024

RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences

ICML 2024spotlight

Preference-based Reinforcement Learning (PbRL) circumvents the need for reward engineering by harnessing human preferences as the reward signal. However, current PbRL methods excessively depend on high-quality feedback from domain experts, which results in a lack of robustness. In this paper, we pre…

2024

SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models

CVPR 2024poster

Recent trends in Large Vision Language Models (LVLMs) research have been increasingly focusing on advancing beyond general image understanding towards more nuanced object-level referential comprehension. In this paper we present and delve into the self-consistency capability of LVLMs a crucial aspec…