G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Paper • 2611.13004 • Published 8 days ago • 45
dNaViT: Discrete Codes are General-Purpose Visual Representations Paper • 2611.12426 • Published 7 days ago • 36
Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals? Paper • 2610.37662 • Published 20 days ago • 37
WorldCast: Exploring Intelligent Visual Generation in World State Prediction Paper • 2610.20731 • Published Oct 14 • 34
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design Paper • 2608.13560 • Published Aug 13 • 60
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published Jul 29 • 55
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture Paper • 2605.12500 • Published May 12 • 153
view article Article NEO-unify: Building Native Multimodal Unified Models End to End sensenova • Mar 5 • 183
Scaling Embeddings Outperforms Scaling Experts in Language Models Paper • 2601.21204 • Published Jan 29 • 104