Skip to main content

# Robotic In-Context Learning

2 related articles

Subscribe to updates

灵初智能 PsiBot Sep 28, 2026
PsiBot releases Psi-R2.5: reverse generation mass-produces strong Pair Data, and HIL+RL post-training lifts on-site success rate to 99%
PsiBot released the embodied-intelligence model Psi-R2.5, which uses a two-layer architecture of a high-level planner (QwenVL3.5-4B) and a low-level controller (Wan2.2-IT2V-5B), proposes and implements a "strong Pair Data" standard, reverse-invokes the Psi-W0 world model to generate human-hand demonstration videos from real-robot execution trajectories, distills an end-to-end human-to-robot data conversion model, and pairs it with a dexterous-hand HIL-in-the-loop plus RL post-training framework that the article says raises success rate to 99% in only 1-2 working days after a few iterations, while measuring compositional generalization with simulation evaluation embedded in pre-training and a 50-task real-robot multi-task benchmark.
PsiBot released the embodied-intelligence model Psi-R2.5, which uses a two-layer architecture of a high-level planner (QwenVL3.5-4B) and a low-level controller (Wan2.2-IT2V-5B), proposes and implements a "strong Pair Data" standard, reverse-invokes the Psi-W0 world model to generate human-hand demonstration videos from real-robot execution trajectories, distills an end-to-end human-to-robot data conversion model, and pairs it with a dexterous-hand HIL-in-the-loop plus RL post-training framework that the article says raises success rate to 99% in only 1-2 working days after a few iterations, while measuring compositional generalization with simulation evaluation embedded in pre-training and a 50-task real-robot multi-task benchmark.
Psi-R2.5 Strong Pair Data World Model Post-training Robotic In-Context Learning
arXiv Sep 17, 2026
In-Context Robot Learning with General-Purpose VLM Agents: The GPT-Policy Framework
This work introduces GPT-Policy, a framework that connects an off-the-shelf general-purpose vision-language model (VLM) to robot tools through a shared context-to-action closed loop, and evaluates its in-context learning on real robots across five context families (human videos, robot videos with actions, goal images, self-interaction history, and online human-robot interaction), finding that task-relevant context can improve success while reducing decisions and execution time, yet better task understanding does not ensure precise contact, reliable outcome verification, or physical safety.
This work introduces GPT-Policy, a framework that connects an off-the-shelf general-purpose vision-language model (VLM) to robot tools through a shared context-to-action closed loop, and evaluates its in-context learning on real robots across five context families (human videos, robot videos with actions, goal images, self-interaction history, and online human-robot interaction), finding that task-relevant context can improve success while reducing decisions and execution time, yet better task understanding does not ensure precise contact, reliable outcome verification, or physical safety.
Dongzhou Cheng（First author）
GPT-Policy Robotic In-Context Learning GPT-6 Astra Robot Manipulation Human-Robot Interaction

You’re all caught up