VideoNexus: Video Perception Beyond the Reasoning Context Paper • 2611.21392 • Published 4 days ago • 21
BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model Paper • 2611.14815 • Published 10 days ago • 57
Duo: A Reciprocal World Model for Full-Duplex Interaction Paper • 2611.15131 • Published 9 days ago • 48
PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models Paper • 2611.16748 • Published 8 days ago • 43
EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models Paper • 2611.06748 • Published 15 days ago • 27
LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis Paper • 2611.06856 • Published 15 days ago • 33
P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors Paper • 2611.03953 • Published 17 days ago • 72
AgentBaton: Efficient Model Collaboration in Agentic Tasks Paper • 2610.35959 • Published 26 days ago • 25
WorldFoundry: Towards Unified Infrastructure for World Intelligence Paper • 2611.10771 • Published 12 days ago • 56
Running Featured 38 Human-1M Exploration and Search 🤖 38 Human-1M: 100K hours of sensorized human demonstrations
VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding Paper • 2611.08449 • Published 15 days ago • 121
FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation Paper • 2610.36545 • Published 24 days ago • 35
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation Paper • 2610.20571 • Published Oct 14 • 61
VideoJev: System One Model for Video Understanding and Interaction Paper • 2610.18615 • Published Oct 13 • 85
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published Oct 8 • 55
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents Paper • 2609.40325 • Published Sep 30 • 43
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents Paper • 2609.39982 • Published Sep 30 • 96
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 146