JGC's picture

JGC

Nothing2Say

·

jiangguochaoGG

AI & ML interests

None yet

Recent Activity

liked a model 5 days ago

deepseek-ai/DeepSeek-V4-Pro

upvoted a paper 16 days ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

authored a paper 19 days ago

Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search

View all activity

Organizations

None yet

commented a paper 7 months ago

VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models

Paper • 2509.19803 • Published Sep 24, 2025 • 122 •

commented a paper 8 months ago

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

Paper • 2508.21104 • Published Aug 28, 2025 • 37 •

commented a paper 10 months ago

FlashThink: An Early Exit Method For Efficient Reasoning

Paper • 2505.13949 • Published May 20, 2025 • 1 •