Representation & Optimization Collection Understanding about representation sheds light on optimization • 139 items • Updated 6 days ago • 7
Self Gradient Forcing: Native Long Video Extrapolation Paper • 2607.20368 • Published 7 days ago • 34
Representation & Optimization Collection Understanding about representation sheds light on optimization • 139 items • Updated 6 days ago • 7
Distilled Reinforcement Learning for LLM Post-training Paper • 2607.17247 • Published 10 days ago • 9
Representation & Optimization Collection Understanding about representation sheds light on optimization • 139 items • Updated 6 days ago • 7
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Paper • 2607.11886 • Published 16 days ago • 84
Cognition Collection Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 201 items • Updated 9 days ago • 6
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation Paper • 2607.13124 • Published 15 days ago • 19
Representation & Optimization Collection Understanding about representation sheds light on optimization • 139 items • Updated 6 days ago • 7
Weak-to-Strong Generalization via Direct On-Policy Distillation Paper • 2607.05394 • Published 21 days ago • 138
Representation & Optimization Collection Understanding about representation sheds light on optimization • 139 items • Updated 6 days ago • 7
Representation & Optimization Collection Understanding about representation sheds light on optimization • 139 items • Updated 6 days ago • 7
Representation & Optimization Collection Understanding about representation sheds light on optimization • 139 items • Updated 6 days ago • 7
Representation & Optimization Collection Understanding about representation sheds light on optimization • 139 items • Updated 6 days ago • 7
Less is More: Early Stopping Rollout for On-Policy Distillation Paper • 2605.27028 • Published May 26 • 15
Representation & Optimization Collection Understanding about representation sheds light on optimization • 139 items • Updated 6 days ago • 7
DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes Paper • 2605.28421 • Published May 27 • 48