Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Paper • 2608.05000 • Published 1 day ago • 37
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion Paper • 2608.03974 • Published 3 days ago • 81
Evaluation-Verification Reward for Consistent Multi-Reference Image Editing Paper • 2607.29025 • Published 7 days ago • 15
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering Paper • 2607.28568 • Published 8 days ago • 180