Survey Maps Four Families of In-Context Learning for Robots, Toward Physical Recursive Self-Improvement
Knowin · hf · 2026-09-30
This literature review organizes in-context learning (ICL) for robots by the interfaces connecting contextual evidence to execution: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill/agent-based execution. It compares transfer assumptions and the roles of training, correspondence, and memory across manipulation and navigation, links method design to evaluation practices, and outlines an agenda toward physical recursive self-improvement.
More from Embodied
- WorldLine: 10k-hour video-trained action simulator lifts robot policy success up to 21.4 pts — hongkongust · 2026-09-30
- EVO-WAM self-verifies video-action rollouts, real-world long-horizon success 20%→76.7% — hitsz123 · 2026-09-30
- PanoVLN beats VLN SOTA by 11.9% success rate using panoramic views, tested on a quadruped robot — ZhejiangUniversity · 2026-09-30
- Agile Robots ships humanoid robots daily from German factory, partners with DeepMind — CyberRobooo · 2026-09-30
- Real2Gym Turns Videos Into Interactive Robot Gyms, Beating GPT-6 Direct Mode by 33% on Real Robots — Shanghai-AI-Laboratory · 2026-09-30
- CrossBFM Distills a Shared Behavior Space Across Humanoid Robots in Under One GPU-Hour — Tan-Dzung Do · 2026-09-30