GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning Paper • 2602.12099 • Published 8 days ago • 55
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text Paper • 2601.22975 • Published 21 days ago • 100
Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation Paper • 2601.21406 • Published 22 days ago • 5
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation Paper • 2601.22153 • Published 22 days ago • 69
view article Article LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family Jan 19 • 81
LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR Paper • 2601.14251 • Published about 1 month ago • 24