GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning Paper • 2602.12099 • Published 4 days ago • 52
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text Paper • 2601.22975 • Published 18 days ago • 99
Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation Paper • 2601.21406 • Published 19 days ago • 5
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation Paper • 2601.22153 • Published 18 days ago • 68
view article Article LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family 28 days ago • 81
LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR Paper • 2601.14251 • Published 27 days ago • 24