Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals
Paper
• 2506.02281 • Published
• 4 •
2
Wang
Qinsi1
AI & ML interests
None yet
Recent Activity
authored
a paper
about 18 hours ago
T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning updated
a dataset about 22 hours ago
T2SBench/T2S-Train-1.2k updated
a dataset about 22 hours ago
T2SBench/T2S-Bench-E2E Organizations
