RLWRLD Lands 5 CoRL 2026 Papers; Human-Video Pretraining Lifts VLA Success to 80.3%

chris_j_paxton · x · 2026-09-12

Robotics startup RLWRLD announced 5 papers accepted to CoRL 2026, headlined by HuRo:

• HuRo builds a "robotization" pipeline converting heterogeneous human videos into robot-aligned observations and action trajectories, yielding 630K episodes and 142M frames for VLA pretraining
• Scaling this pretraining lifts overall task completion from 51.5% to 80.3% across four real-world manipulation tasks, and OOD completion under spatial/visual shifts from 34.9% to 72.2%
• Ablations show visual robotization improves OOD robustness, and end-to-end pretraining with retargeted actions beats visual-only transfer; code and data are released
• Other accepted papers cover folding tactile/torque feedback into VLA action streams via cross-modal self-attention, and learning invertible latent decompositions of collision-free configuration space for path planning

Original post →

More from Embodied

• Dev builds real 'sidequest' device that dances only to music it likes — wavefnx · 2026-10-31
• Indie dev prototypes custom secure hardware in a day with Rust firmware and root-key isolation — wavefnx · 2026-10-31
• UCLA's ChairNav teaches autonomous wheelchairs to learn each rider's preferences — zhoubolei · 2026-10-31
• Amazon Echo kills local voice storage: everything goes to the cloud from March 28 — alex_verem · 2026-10-31
• HP paid $116M for Humane, then bricked every $699 AI Pin 10 days later — alex_verem · 2026-10-31
• Moxie, the $800 AI robot friend for kids, went silent overnight after shutdown — alex_verem · 2026-10-31

Embodied channel →