CoRL 2026 workshops ask what makes a pretrained robot policy adaptable
huihan_liu · x · 2026-11-11
Two workshops announced for CoRL 2026 (Nov 12, Austin): "Pretrain to Adapt" probes a gap in the standard pretrain-then-adapt paradigm — pretraining optimizes broad competence, not adaptability; the strongest pretrained policy isn't necessarily the easiest to adapt, and there's no reliable way to tell before adaptation. Topics include measuring adaptation readiness and pretraining beyond behavior cloning. Learn@Deploy covers fast adaptation, test-time optimization, failure recovery, and deployment evaluation. Speakers include Karl Pertsch, Sherry Yang, Siddharth Karamcheti; submissions due Oct 4, 2026.
Related event: CoRL 2026 to Host Twin Workshops on Adaptable Pretrained Robot Policies(2 posts)→
More from Embodied
- EEG can't match implanted BCIs: physics caps scalp signals at ~70Hz — EricMTrautmann · 2026-11-11
- Dyna Robotics' CoRL 2026 demo blends large-scale navigation with dexterous manipulation — JasonMa2020 · 2026-11-11
- MBZUAI releases PAN 2, an open-weights foundation world model for physical intelligence — Scobleizer · 2026-11-11
- SpaceX locks 100+ GW of solar cell equipment from SINGULUS for Starmind AI satellites — ns123abc · 2026-11-11
- SpaceX unveils Starlink Mini 2 with quick-swap battery: 4.5 hours of cordless internet — elonmusk · 2026-11-11
- $50 VL53L9 dToF LiDAR plugged into an iPhone enables quick open-source 3D scanning — kamathsblog · 2026-11-11