paper_other OTTER:A Vision-Language-Action Model with Text-Aware Visual Feature Extraction Improving Vision-Language-Action Model with Online Reinforcement Learning Fine-Tuning Vision-Language-Action Models:Optimizing Speed and Success

Mastering Diverse Domains through World Models Paper Reading:Generalist World Model Pre-Training for Efficient Reinforcement Learning

NOPROP:TRAINING NEURAL NETWORKS WITHOUT BACK-PROPAGATION OR FORWARD-PROPAGATION