Kaixiang Lin

Applied Scientist@Amazon·美国·OpenReview

研究方向

Reinforcement Learning · Off-policy learning · Reinforcement learning applications · Reinforcement learning from human feedback · Alignment · Multimodal Agent

4.5

Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach

ICLR 2026Rejected

7.5

Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

ICLR 2025Oral

通讯

5.8

Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

ICLR 2025Rejected

三作

4.8

Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

ICML 2025Poster

三作

3.5

Policy optimization can be memory-efficient: LLM Alignment Through Successive Policy Re-weighting (SPR)

合作者 (18)