Linfeng Song's picture

4 18

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

upvoted a paper 5 days ago

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values

upvoted a paper 26 days ago

VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning

upvoted a paper 26 days ago

CLUE: Non-parametric Verification from Experience via Hidden-State Clustering

View all activity

Organizations

commented a paper 5 months ago

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation

Paper • 2505.10962 • Published May 16 • 8 •

commented a paper 10 months ago

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

Paper • 2412.20735 • Published Dec 30, 2024 • 12 •

commented a paper about 1 year ago

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

Paper • 2410.06508 • Published Oct 9, 2024 • 11 •

commented a paper over 1 year ago

LiteSearch: Efficacious Tree Search for LLM

Paper • 2407.00320 • Published Jun 29, 2024 • 40 •