VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published 10 days ago • 269
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training Paper • 2608.24845 • Published 11 days ago • 15
ReToken: One Token to Improve Vision-Language Models for Visual Retrieval Paper • 2607.28627 • Published Jul 30 • 9