EgoSim: Egocentric World Simulator for Embodied Interaction Generation Paper • 2604.01001 • Published 3 days ago • 30
VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification Paper • 2604.01569 • Published 2 days ago • 5
FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition Paper • 2604.02088 • Published 2 days ago • 3
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling Paper • 2603.25746 • Published 8 days ago • 151
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference Paper • 2603.25730 • Published 8 days ago • 48
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model Paper • 2603.21986 • Published 11 days ago • 120
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG Paper • 2603.23497 • Published 10 days ago • 90
RealMaster: Lifting Rendered Scenes into Photorealistic Video Paper • 2603.23462 • Published 10 days ago • 32
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation Paper • 2603.23500 • Published 10 days ago • 35
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models Paper • 2603.22212 • Published 11 days ago • 124