Efficient Foundation Models for Real-Time Embodied AI — CoRL 2026 Workshop
Description
Efficient Foundation Models for Real-Time Embodied AI - CoRL 2026 Workshop focuses on making robot foundation models fast, cheap, and safe enough to deploy. This workshop is about bridging the gap between embodied models' generality and their requirements for latency, memory, and power for actual deployment on hardware. Targeted towards compression, quantization, distillation, and more, it includes talks and live profiling sessions. It aims to explore architecture compression, edge-cloud co-design, and safety under latency.
Event location
Let your network know you`re going
Share this event to start conversations, invite colleagues, and connect before it begins.
Meet the speakers
Jiajun Wu
Theme:Stanford University - World models for embodied AI: efficient learned models for online planning.
Yecheng “Jason” Ma
Theme:Dyna Robotics - Embodied foundation models on a commercial duty cycle, from DYNA-1 to the DYNA-2 world-action model.
Dhruv Shah
Theme:Princeton University and Google DeepMind - Post-training as the stage where most deployable-efficiency decisions are made.
Ouais Alsharif
Theme:Google DeepMind - Engineering robot foundation models for production deployment.
Related events
Small Business AI Clinic: Prompting & Automation Lab (Virtual)
Colorado Applied Machine Learning Mini Conference
Builder's Day 2026 by Prisma
SUSTAINABLE BY DESIGN: HOW CAN WE BUILD AI FOR A CLIMATE-FORWARD FUTURE
Boston Amazon Quick User Group
AI Co-working with Launch by Lunch
Beyond the AI Pilot: CIO Dinner
Ditch the Deck: AI Show Not Tell
Discovery Series: Cool Talks in Cool Places
AI & Fintech XRPL Hackathon in New York
PEF DC: Inside the U.S. Department of State
