CoRL 2026 workshop charts the path to continually self-improving robots
abhishekunique7 · x · 2026-11-12
The Continually Self-Improving Robots workshop at CoRL 2026 (Nov 12, Austin) argues imitation alone can't close the long-tail reliability gap: robots must autonomously collect data, discover failures, and refine skills through interaction — an "era of experiences." Organized by Abhishek Gupta (UW & Amazon FAR) with invited speakers from Physical Intelligence, UBC, Dyna, and Generalist; accepted papers include test-time gradient guidance for flow policies and the WEAVER world model for manipulation.
Related event: CoRL 2026 to Host Workshop on Continually Self-Improving Robots(3 posts)→
More from Embodied
- Mila brings its robotics research to CoRL 2026 in Austin — Mila_Quebec · 2026-11-13
- Fable 5.2 robot evals: overall success rate jumps from 34% to 50% across 456 tasks — GuanyaShi · 2026-11-13
- Day 8 of building a robot arm: maker ditches off-the-shelf gripper and builds his own — _Stocko_ · 2026-11-13
- Google and Samsung's AI eyewear gets lineup, Gemini and privacy right — the test is the second pair — BenBajarin · 2026-11-13
- Mantle Launches AI-Native Maintenance Service for Robots and Industrial Machines With 250+ Technicians — ycombinator · 2026-11-13
- GEM-4D: geometry-enhanced video world models lift robot sim success 22.7% to 75.1% — pliang279 · 2026-11-13