V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning Paper • 2603.14482 • Published Mar 15 • 30
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models Paper • 2603.17051 • Published 30 days ago • 109
Versatile Editing of Video Content, Actions, and Dynamics without Training Paper • 2603.17989 • Published 29 days ago • 17
LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation Paper • 2603.20192 • Published 27 days ago • 22
Beyond Language Modeling: An Exploration of Multimodal Pretraining Paper • 2603.03276 • Published Mar 3 • 103
From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors Paper • 2602.21778 • Published Feb 25 • 14