view article Article autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training autotrust • 27 days ago • 44
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 29 days ago • 208
In-Context Learning for Robots: Methods and Applications Paper • 2609.36012 • Published 30 days ago • 240
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems Paper • 2609.33325 • Published about 1 month ago • 345
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 318
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published Aug 26 • 139