蔡正舟

conctsai

9

·

AI & ML interests

None yet

Recent Activity

authored a paper 3 days ago

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

upvoted a paper 7 days ago

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

authored a paper 2 months ago

Learning to Self-Verify Makes Language Models Better Reasoners

View all activity

Organizations

None yet

Papers 4

arxiv:2607.26784

arxiv:2605.27141

arxiv:2605.16143

arxiv:2602.07594

models 0

None public yet

datasets 1

conctsai/video-r1-image

Updated Apr 11, 2025 • 14