On-Policy Delta Distillation for Multilingual Math Reasoning Paper • 2608.05802 • Published 3 days ago • 24
PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs Paper • 2608.02218 • Published 6 days ago • 7
WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning Paper • 2607.29613 • Published 9 days ago • 27
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering Paper • 2607.28568 • Published 10 days ago • 181