CARE certifies VLA inference speedups up to 10.8x with statistical guarantees
UMCP · hf · 2026-10-09
CARE introduces certified accelerator selection for vision-language-action models: paired rollouts provide finite-sample guarantees that acceleration-induced failure stays below a user-set budget. On LIBERO with OpenVLA-OFT it certifies 9.0–10.8x speedups while preserving ≥85.8% of reference-solved episodes, generalizes to π₀.₅ flow-step reduction and LLM agents in Crafter.
More from Embodied
- LLMs play Connect 4 via robot arms in MuJoCo; fable 5.1 wins at $17.40 in API calls — eigenron · 2026-10-09
- Prediction: frontier models as real-time robot policies at 10k-100k tok/s within 1-2 years — ATTlKA · 2026-10-09
- Hugging Face launches Robotic Episodes Viewer for 24k+ LeRobot datasets — mishig25 · 2026-10-09
- Blind humanoid walks, plays soccer and lifts suitcases with joint encoders only — accepted at Humanoids 2026 — Jan_R_Peters · 2026-10-09
- Delete object info from observations and PPO learns to search anyway — TU Darmstadt on its Humanoids 2026 paper — Jan_R_Peters · 2026-10-09
- Corporate robot bets graded: only one binding order with unit counts found — lukas_m_ziegler · 2026-10-09