Jinghan Ke
JinghanKe
AI & ML interests
None yet
Recent Activity
upvoted a paper about 21 hours ago
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement authored a paper 5 months ago
T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning authored a paper 5 months ago
Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's
Own SignalsOrganizations
