GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published Sep 30 • 33
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems Paper • 2609.33325 • Published Sep 27 • 58
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 168
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem Paper • 2609.07064 • Published Sep 7 • 61