Linfeng Song's picture

3 6

Linfeng Song

freesunshine0316

https://freesunshine0316.github.io/

AI & ML interests

Researcher @Tencent AI Lab working on reasoning and RLAIF with LLM, especially search + RL. Working on NLP since 2010.

Recent Activity

commented a paper 5 days ago

HUNYUANPROVER: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving

upvoted a paper 5 days ago

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

View all activity

Organizations

freesunshine0316's activity

upvoted a paper 5 days ago

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Paper • 2412.21187 • Published 8 days ago • 27

upvoted a paper 3 months ago

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning

Paper • 2410.06508 • Published Oct 9, 2024 • 10

upvoted 2 papers 6 months ago

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Paper • 2407.00617 • Published Jun 30, 2024 • 7

LiteSearch: Efficacious Tree Search for LLM

Paper • 2407.00320 • Published Jun 29, 2024 • 37

upvoted 2 papers 7 months ago

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

Paper • 2404.12253 • Published Apr 18, 2024 • 54

Stabilizing RLHF through Advantage Model and Selective Rehearsal

Paper • 2309.10202 • Published Sep 18, 2023 • 9