We present Perception-R1, a scalable RL framework using Group Relative Policy Optimization (GRPO) during MLLM post-training. Key innovations: 🎯 Perceptual Perplexity Analysis: We introduce a novel ...

RynnVLA-001 is a VLA model based on pretrained video generation model. The key insight is to implicitly transfer manipulation skills learned from human demonstrations in ego-centric videos to the ...