WorldDraft: If Code Builds the World, Can Video Models Just Render It? Paper • 2611.16217 • Published 5 days ago • 17
World-in-Context: Interactive Video World Modeling with In-Context Conditioning Paper • 2610.33169 • Published 25 days ago • 23
The Past Frames the Future: Memory for Autoregressive Video Generation Paper • 2609.28466 • Published Sep 23 • 44
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout Paper • 2609.09123 • Published Sep 8 • 27
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models Paper • 2609.02886 • Published Sep 2 • 114
GenRouter: Unified Workflow Routing for Agentic Image Generation Paper • 2608.16721 • Published Aug 17 • 29
RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data Paper • 2605.13775 • Published May 13 • 7
V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators Paper • 2604.03307 • Published Mar 31 • 16
Show, Don't Tell: Morphing Latent Reasoning into Image Generation Paper • 2602.02227 • Published Feb 2 • 10
DVD: Deterministic Video Depth Estimation with Generative Priors Paper • 2603.12250 • Published Mar 12 • 26
DVD: Deterministic Video Depth Estimation with Generative Priors Paper • 2603.12250 • Published Mar 12 • 26
Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance Paper • 2603.02175 • Published Mar 2 • 24
Show, Don't Tell: Morphing Latent Reasoning into Image Generation Paper • 2602.02227 • Published Feb 2 • 10