Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling Paper • 2604.28185 • Published 8 days ago • 86
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published 11 days ago • 68
ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 29 days ago • 261
Watch Before You Answer: Learning from Visually Grounded Post-Training Paper • 2604.05117 • Published Apr 6 • 35
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks Paper • 2603.27862 • Published Mar 29 • 31
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published Mar 17 • 96