NVIDIA introduces GR00T 2 robot world action model at CoRL
NVIDIA says GR00T 2 hit 71% average success across 50 tasks with one demonstration and 95% with five.
Stories per day · 30 days
2 RSS
4 stories, newest first · one card per story
Stories tagged #groot
The Low-Rank Structure of VLA Reinforcement Learning
RL post-training of flow-based VLA models produces low-rank updates concentrated in action-expert Timestep Modules.
Strategically Diverse Sampling for Self-Training
Strategically diverse sampling for LLM self-training beats IID data, and Qwen3-4B incorrect traces beat a 235B teacher.
GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies
GeoAAC adaptively sizes action chunking horizons in flow-based VLA policies using denoising trajectory geometry, raising real-world manipulation success from 53.3% to 74.4%.