arxiv:2507.06804
Linfeng Song
freesunshine0316
ยท
AI & ML interests
Researcher @Tencent AI Lab working on reasoning and RLAIF with LLM, especially search + RL. Working on NLP since 2010.
Recent Activity
authored
a paper
1 day ago
The Trickle-down Impact of Reward (In-)consistency on RLHF
authored
a paper
1 day ago
Iterative Nash Policy Optimization: Aligning LLMs with General
Preferences via No-Regret Learning
authored
a paper
1 day ago
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
Organizations
models
0
None public yet
datasets
0
None public yet