view article Article autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training autotrust • 10 days ago • 121
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis Paper • 2609.38923 • Published 10 days ago • 123
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience Paper • 2609.03241 • Published Sep 3 • 51