Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement Paper • 2610.40191 • Published 22 days ago • 77
Hy-Nomas: Towards Free-form Interactive World Generation Paper • 2610.36729 • Published 25 days ago • 109
Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance Paper • 2610.20220 • Published Oct 14 • 6
Video Generation Models are General-Purpose Vision Learners Paper • 2607.09024 • Published Jul 10 • 81
DataComp-VLM: Improved Open Datasets for Vision-Language Models Paper • 2606.28551 • Published Jun 26 • 52
DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation Paper • 2606.31537 • Published Jun 30 • 25
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning Paper • 2604.05404 • Published Apr 7 • 45
Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation? Paper • 2606.04811 • Published Jun 4 • 17
FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching Paper • 2604.06757 • Published Apr 8 • 10
EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models Paper • 2512.14666 • Published Dec 16, 2025 • 10
UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback Paper • 2511.01678 • Published Nov 3, 2025 • 37