Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedback Paper • 2606.14368 • Published Jun 12 • 3
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 390 items • Updated about 12 hours ago • 86
1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation Paper • 2609.24432 • Published 2 days ago • 12
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence Paper • 2609.05571 • Published 19 days ago • 97
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself Paper • 2609.22068 • Published 5 days ago • 116
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 390 items • Updated about 12 hours ago • 86
MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup Paper • 2609.15126 • Published 9 days ago • 11
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 390 items • Updated about 12 hours ago • 86
Calibrating Teacher--Student Discrepancy for On-Policy Distillation Paper • 2609.21619 • Published 5 days ago • 10
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling Paper • 2609.19499 • Published 7 days ago • 37 • 4
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 390 items • Updated about 12 hours ago • 86
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling Paper • 2609.19499 • Published 7 days ago • 37
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL Paper • 2609.20715 • Published 6 days ago • 42
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 390 items • Updated about 12 hours ago • 86
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published 6 days ago • 128
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 390 items • Updated about 12 hours ago • 86
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation Paper • 2609.20511 • Published 6 days ago • 108
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 390 items • Updated about 12 hours ago • 86