Chengsong Huang's picture

Chengsong Huang

ChengsongHuang

·

https://chengsong-huang.github.io/

hcscctv

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

upvoted a paper 2 days ago

The Unlearnability Phenomenon in RLVR for Language Models

upvoted a paper 4 days ago

Process Rewards with Learned Reliability

View all activity

Organizations

Papers 18

arxiv:2605.05566

arxiv:2603.09206

arxiv:2602.04145

arxiv:2602.03845

models 0

None public yet

datasets 1

ChengsongHuang/MATH_train

Viewer • Updated Sep 4, 2025 • 7.5k • 11