Deepak Pathak Demonstrates In-Context Learning for Robotics with One-Shot Video Prompts
deepakpathak · x · 2026-08-26
Deepak Pathak demonstrated in-context learning capabilities for robotics. The method allows robots to perform long-horizon tasks exceeding 10 minutes using just a single video prompt, without fine-tuning and without seeing the tasks during pre-training. This approach aims to build intelligence from the foundations up.
More from Embodied
- Skild AI unveils S1: robot foundation model that learns 10-minute novel tasks from one video — deepakpathak · 2026-08-26
- KUKA Robot Demo: Keeping Tool Center Point Still — Olivier__OG · 2026-08-26
- Dreame pivots to embodied AI among 4 core businesses; XPeng's He says humanoid robots may beat cars on margin — 创业邦 · 2026-08-26
- LimX gathers global robotics voices at WRC 2026 to discuss life beyond demos — broodsugar · 2026-08-26
- Tesla upgrades in-car Grok to world's #1 speech-to-speech AI — XFreeze · 2026-08-26
- Seeking AI tools for generating 3D printable minis with watertight meshes — Minus8058 · 2026-08-26