The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation8 min audioPaper published Sep 29, 2026#3 on Hugging Face · Sep 28–Oct 4ListenRead paper ↗View visual summary
Scaling Properties of Same-Family On-Policy DistillationEpisode released Oct 11, 20268 min audioPaper published Sep 26, 2026#7 on Hugging Face · Sep 28–Oct 4ListenRead paper ↗View visual summary
Raven: The Harness of Harnesses for Composable Agentic IntelligenceEpisode released Oct 10, 20269 min audioPaper published Sep 27, 2026#1 on Hugging Face · Sep 28–Oct 4ListenRead paper ↗View visual summary
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search AgentsEpisode released Oct 9, 20268 min audioPaper published Sep 30, 2026#2 on Hugging Face · Sep 28–Oct 4ListenRead paper ↗View visual summary
In-Context Learning for Robots: Methods and ApplicationsEpisode released Oct 9, 20268 min audioPaper published Sep 28, 2026#8 on Hugging Face · Sep 28–Oct 4ListenRead paper ↗View visual summary
MaLiang-Harness: A Programmable Path to Image and Video GenerationEpisode released Oct 9, 20268 min audioPaper published Sep 28, 2026#6 on Hugging Face · Sep 28–Oct 4ListenRead paper ↗View visual summary