VideoJev: System One Model for Video Understanding and Interaction
Paper • 2610.18615 • Published • 341
Video Understanding
-
-
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
Paper • 2609.39600 • Published • 57 -
Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding
Paper • 2610.16118 • Published • 20 -
DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding
Paper • 2610.19849 • Published • 42 -
Gen4P: Video Generators are 4D Perceivers
Paper • 2610.22371 • Published • 7