AI
AI Digest
EN RU
Home Archive About RSS

#training-dynamics

2 items

  • 9 июн On the Geometry of On-Policy Distillation: A Training Paradigm Distinct from SFT and RLVR Hong Kong University of Science and Technology research
  • 26 июн Dense Supervision Is Not Enough: The Readout Blind Spot in Looped Language Models research

ai-digest.kerby.pro

© 2026 Alexei Lukin · CC BY 4.0

RSS · JSON Feed · About