IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation Paper • 2610.38425 • Published 6 days ago • 22
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published Jul 29 • 57
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design Paper • 2608.13560 • Published Aug 13 • 60
ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling Paper • 2610.15166 • Published 24 days ago • 63
WorldCast: Exploring Intelligent Visual Generation in World State Prediction Paper • 2610.20731 • Published 20 days ago • 40
WorldCast: Exploring Intelligent Visual Generation in World State Prediction Paper • 2610.20731 • Published 20 days ago • 40
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness Paper • 2610.08621 • Published 28 days ago • 76
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design Paper • 2608.13560 • Published Aug 13 • 60
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception Paper • 2606.28322 • Published Jun 26 • 42
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception Paper • 2606.28322 • Published Jun 26 • 42