◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Yu Bai

3 papers hereh-index 5682 citations10 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author2
  • last author1

Across the 3 of 3 papers where every author was matched, so the position is known.

fields
  • cs.LG3
same name
  • Yu Bai — 16 papers, h 15
  • Yu Bai — 11 papers, h 9
  • Yu Bai — 5 papers, h 3
  • Yu Bai — 5 papers, h 2
  • Yu Bai — 4 papers, h 3
  • Yu Bai — 3 papers, h 2

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

collaborators

3 papers

cs.LG2024

Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond

Fan Chen, Song Mei, Yu Bai

Modern Reinforcement Learning (RL) is more than just learning the optimal policy; Alternative learning goals such as exploring the environment, estimating the underlying model, and…

cs.LG2024

Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Tianyu Guo, Druv Pai, Yu Bai +3

Practitioners have consistently observed three puzzling phenomena in transformer-based large language models (LLMs): attention sinks, value-state drains, and residual-state peaks,…

cs.LG2024

Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning

Ruiqi Zhang, Licong Lin, Yu Bai +1

Large Language Models (LLMs) often memorize sensitive, private, or copyrighted data during pre-training. LLM unlearning aims to eliminate the influence of undesirable data from the…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.