mlsanityData to 7 Oct 2026

Few-Shot In-Context Imitation Learning via Implicit Graph Alignment

arXiv 2310.12238 ↗First posted 18 Oct 2023cs.RO cs.AI cs.LGcited by 14

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

Consider the following problem: given a few demonstrations of a task across a few different objects, how can a robot learn to perform that same task on new, previously unseen objects? This is challenging because the large variety of objects within a class makes it difficult to infer the task-relevant relationship between the new objects and the objects in the demonstrations. We address this by formulating imitation learning as a conditional alignment problem between graph representations of objects. Consequently, we show that this conditioning allows for in-context learning, where a robot can perform a task on a set of new objects immediately after the demonstrations, without any prior knowledge about the object class or any further training. In our experiments, we explore and validate our design choices, and we show that our method is highly effective for few-shot learning of several real-world, everyday tasks, whilst outperforming baselines. Videos are available on our project webpage at https://www.robot-learning.uk/implicit-graph-alignment.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 29 of its 38 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

29 of 38 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Demonstrate Once, Imitate Immediately (DOME): Learning Visual Servoing for One-Shot Imitation Learning6 Apr
  2. 2021Towards More Generalizable One-shot Visual Imitation Learning26 Oct
  3. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration13 May
  4. 2019Self-Supervised Correspondence in Visuomotor Policy Learning16 Sep

Other references · 25

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  8. 2021Implicit Behavioral Cloningcited by 442
  9. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 342
  10. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  11. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 204
  12. 2019kPAM: KeyPoint Affordances for Category-Level Robotic Manipulationcited by 152
13 more
  1. 2018Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulationcited by 140
  2. 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
  3. 2020Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learningcited by 69
  4. 2019KETO: Learning Keypoint Representations for Tool Manipulationcited by 68
  5. 2022SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fieldscited by 51
  6. 2022TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulationcited by 47
  7. 2019Graph-Structured Visual Imitationcited by 43
  8. 2021kPAM 2.0: Feedback Control for Category-Level Robotic Manipulationcited by 38
  9. 2021Learning Models as Functionals of Signed-Distance Fields for Manipulation Planningcited by 29
  10. 2021My House, My Rules: Learning Tidying Preferences with Graph Neural Networkscited by 27
  11. 2022Offline-Online Learning of Deformation Model for Cable Manipulation with Graph Neural Networkscited by 17
  12. 2022Where To Start? Transferring Simple Skills to Complex Environmentscited by 9
  13. 2023DefGraspNets: Grasp Planning on 3D Fields with Graph Neural Netscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 6; 2025: 4; 2026: 3.

14 papers.

Sort:

By area:

  1. 2024Multimodal Alignment and Fusion: A Surveycited by 73
  2. 2024Keypoint Action Tokens Enable In-Context Imitation Learning in Roboticscited by 71
  3. 2024Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learningcited by 56
  4. 2024DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Modelscited by 43
  5. 2024Instant Policy: In-Context Imitation Learning via Graph Diffusioncited by 38
  6. 2024Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloningcited by 19
  7. 2023On the Effectiveness of Retrieval, Alignment, and Replay in Manipulationcited by 15
  8. 2025Action Tokenizer Matters in In-Context Imitation Learningcited by 12
  9. 2025One-Shot Dual-Arm Imitation Learningcited by 7
  10. 2025Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worldscited by 4
  11. 2025Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditionscited by 2
  12. 2026Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulationcited by 1
2 more
  1. 2026A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Roboticscited by 0
  2. 2026SynthICL: Scalable In-context Imitation Learning with Synthetic Datacited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs
  2. 2023One-Shot Imitation Learning: A Pose Estimation Perspective
  3. 2025Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through Planning
  4. 2026SparTa: Sparse Graphical Task Models from a Handful of Demonstrations
  5. 2026ICLR: In-Context Imitation Learning with Visual Reasoning
  6. 2024Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames
  7. 2024VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections
  8. 2020Scalable Multi-Task Imitation Learning with Autonomous Improvement