UniWeaver: Harnessing Unified Multimodal Models for Interleaved Text-Image Generation Paper • 2611.13530 • Published 11 days ago
G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Paper • 2611.13004 • Published 13 days ago • 48
dNaViT: Discrete Codes are General-Purpose Visual Representations Paper • 2611.12426 • Published 12 days ago • 37
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 26 days ago • 52
Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals? Paper • 2610.37662 • Published 25 days ago • 37
IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation Paper • 2610.38425 • Published 24 days ago • 18
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published Jul 29 • 55
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 Oct 10 • 44
WorldCast: Exploring Intelligent Visual Generation in World State Prediction Paper • 2610.20731 • Published Oct 14 • 35
WorldCast: Exploring Intelligent Visual Generation in World State Prediction Paper • 2610.20731 • Published Oct 14 • 35
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness Paper • 2610.08621 • Published Oct 6 • 70