RoboDawn: VLM closed-loop robot control hits 73.6% one-shot, beating π0.5 zero-shot
Meng-Hao Guo · hf · 2026-09-22
RoboDawn exposes robot control to an agentic VLM via a compact set of discrete translation/rotation/gripper commands, enabling closed-loop observe-reason-act control, plus an in-context learning scheme grounded on a few demonstrations. On RoboTwin 2.0 C2R it reaches 53.2% zero-shot and 73.6% one-shot success, beating the strong trained baseline π0.5 (46.0%) and setting SOTA; RoboDojo improves from 35.67% to 47.17%. No task-specific robot training needed, and the same framework transfers to real Franka arms for block-in-basket and stacking tasks.
More from Embodied
- NUS's Grounded Action Model Tops Robot Manipulation Benchmarks with 3D Grounding — NationalUniversityofSingapore · 2026-09-22
- Distilling World-Model Features into VLAs: 0.8B Policy Hits 97.9% on LIBERO — Trung Dao · 2026-09-22
- Stealth team unveils new robot Origin; Scobleizer bets it would sell at Home Depot — Scobleizer · 2026-09-22
- Figure's Helix 2.5 robots tested on household tasks across 30 unseen homes — FinanceYF5 · 2026-09-22
- PrimeBOT T1 starts at $2,960 as line outputs a humanoid every 2.5 minutes — davidpattersonx · 2026-09-22
- HuRo: 630K robotized human-video episodes lift VLA completion from 51.5% to 80.3% — RLWRLD · 2026-09-22