Three CMU robot papers spotlighted at CoRL 2026: memory, vision-touch steering, world models
pabbeel · x · 2026-11-09
A CMU Intent Robotics Lab researcher (with Amazon FAR) will present three workshop-spotlighted works at CoRL 2026 in Austin:
- IMPRINT (RoboMem): multi-stream latent memory for robot policies without manual curation.
- ViTaL (main conference + Learn@Deploy spotlight): inference-time policy steering via vision and touch — "vision selects behavior, touch refines contact."
- WEAVER (CSIR spotlight): a faster, more faithful and consistent world model for robotic manipulation.
Also: a joint keynote with Andrea Bajcsy at the "Oopsie Data" workshop (training embodied reward models from imperfect data, ICML spotlight), and co-organizing the Pretrain to Adapt workshop on what makes a pretrained policy adaptable to new tasks, embodiments, and environments.
More from Embodied
- iPad mini 8 hands-on: 1g heavier and a third the price of iPhone Air, 60Hz capped — oran_ge · 2026-11-09
- Dooder puts an AI with on-device hearing and voice entirely on the Apple Watch — breagz · 2026-11-09
- Stanford team teaches an AI agent a pool table's physics by letting it take real shots (CoRL) — drmapavone · 2026-11-09
- Furong Huang Lab brings six human-video-to-robot works to CoRL 2026 — furongh · 2026-11-09
- 3D animated teardown explains how the open-source local-AI microduck robot works — Individual-Dot5488 · 2026-11-09
- CoRL 2026 balloons to 5,000+ attendees; Princeton PRISM brings 6 robotics papers including oral MolmoB0T — shahdhruv_ · 2026-11-09