G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Paper • 2611.13004 • Published 5 days ago • 37
Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals? Paper • 2610.37662 • Published 17 days ago • 37
WorldCast: Exploring Intelligent Visual Generation in World State Prediction Paper • 2610.20731 • Published about 1 month ago • 34
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design Paper • 2608.13560 • Published Aug 13 • 60
SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training Paper • 2605.08738 • Published May 9 • 12