abhishekzkumar/notes-visual-question-answering Visual Question Answering • 16.6k • Updated Oct 2 • 15
abhishekzkumar/notes-visual-question-answering Visual Question Answering • 16.6k • Updated Oct 2 • 15
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published Sep 30 • 134
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience Paper • 2609.03241 • Published Sep 3 • 41