Jinghan Ke

JinghanKe's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 4 days ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published 12 days ago • 100

authored 3 papers 5 months ago

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Paper • 2603.03790 • Published Mar 4 • 122

Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals

Paper • 2506.02281 • Published Jun 2, 2025 • 4

Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives

Paper • 2502.02723 • Published Feb 4, 2025 • 1

upvoted 2 papers 5 months ago

Reconstructing Humans with a Biomechanically Accurate Skeleton

Paper • 2503.21751 • Published Mar 27, 2025 • 11

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Paper • 2603.03790 • Published Mar 4 • 122

upvoted a paper 10 months ago

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play

Paper • 2509.25541 • Published Sep 29, 2025 • 142