PKU-Alignment Group @Pair-Lab (under construction)
PKU-Alignment Group @Pair-Lab (under construction)
News
People
Events
Publications
Contact
More Platforms
知乎
Bilibili
Email
小红书
PAIR-Lab
Copied
Copied to clipboard
Kaile Wang
Ph.D Student
Ph.D (2026), Peking University
Interests
Reinforcement Learning
Safety Alignment
LLMs Theory
Latest
AI Alignment: A Comprehensive Survey
Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
Reward Generalization in RLHF: A Topological Perspective
Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Language Models Resist Alignment: Evidence From Data Compression
Cite
×
