In-Context Learning for Robots: Methods and Applications
cs.RO, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Project page: https://human2robot.github.io/resources/paper.pdf
Terminology
Sources
- One-Shot Imitation Learning
- RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
- A Simple Neural Attentive Meta-Learner
- Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
- Prompting Decision Transformer for Few-Shot Policy Generalization
- In-context Reinforcement Learning with Algorithm Distillation
- One-Shot Visual Imitation Learning via Meta-Learning
- One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
- RoboTTT: Context Scaling for Robot Policies
- WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time
- Towards More Generalizable One-shot Visual Imitation Learning
- In-Context Imitation Learning via Next-Token Prediction
- Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers
- Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics
- Instant Policy: In-Context Imitation Learning via Graph Diffusion
- RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models
- Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning
- OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
- Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving