The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 4 days ago • 387
RoboJev: An Open Vision-Language Judge for Robot Success Detection Paper • 2610.33718 • Published 6 days ago • 15
RealtimeWAM: One-Step Asynchronous World Action Models Paper • 2610.06617 • Published 25 days ago • 24
GTR: Gated Token Recurrence for Efficient Dense Prediction Paper • 2609.26590 • Published Sep 23 • 15
4Director: Controlling Video World Models with Rigid 3D Geometry Paper • 2610.02160 • Published 29 days ago • 39