ChenShawn's picture

2 2 14

ChenShawn

ChenShawn

·

ChenShawn

AI & ML interests

Reinforcement learning

Recent Activity

upvoted a paper about 16 hours ago

VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training

upvoted a paper about 17 hours ago

DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

liked a dataset about 2 months ago

R2E-Gym/R2E-Gym-Subset

View all activity

Organizations

None yet

models 2

ChenShawn/DeepEyes-rebuttal-model

8B • Updated Sep 19, 2025 • 7 • 1

ChenShawn/DeepEyes-7B

Image-Text-to-Text • 8B • Updated May 22, 2025 • 423 • 15

datasets 1

ChenShawn/DeepEyes-Datasets-47k

Preview • Updated May 22, 2025 • 221 • 18