mlsanityData to 14 Oct 2026

Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamics

arXiv 2604.13366 ↗First posted 15 Apr 2026cs.LG cs.RO cs.SYcited by 0

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate system identification as an in-context meta-learning problem and compare deterministic and generative sequence models for forward dynamics prediction. We take a Transformer-based meta-model, as a strong deterministic baseline, and introduce to this setting two complementary diffusion-based approaches: (i) inpainting diffusion (Diffuser), which learns the joint input-observation distribution, and (ii) conditioned diffusion models (CNN and Transformer), which generate future observations conditioned on control inputs. Through large-scale randomized simulations, we analyze performance across in-distribution and out-of-distribution regimes, as well as computational trade-offs relevant for control. We show that diffusion models significantly improve robustness under distribution shift, with inpainting diffusion achieving the best performance in our experiments. Finally, we demonstrate that warm-started sampling enables diffusion models to operate within real-time constraints, making them viable for control applications. These results highlight generative meta-models as a promising direction for robust system identification in robotics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 22 of its 29 references that are in the map. First posted on arXiv 15 Apr 2026.

Builds on

22 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  5. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  6. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  7. 2022Transformers learn in-context by gradient descentcited by 732
  8. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  9. 2018Meta-Learning: A Surveycited by 256
  10. 2022General-Purpose In-Context Learning by Meta-Learning Transformerscited by 105
  11. 2023In-Context Learning Unlocked for Diffusion Modelscited by 104
  12. 2020dynoNet: a neural network architecture for learning dynamical systemscited by 29
9 more
  1. 2022Physics-Informed Model-Based Reinforcement Learningcited by 18
  2. 2023From system models to class models: An in-context learning paradigmcited by 16
  3. 2024Enhanced Transformer architecture for in-context learning of dynamical systemscited by 7
  4. 2024The Duality of Generative AI and Reinforcement Learning in Robotics: A Reviewcited by 6
  5. 2024Synthetic data generation for system identification: leveraging knowledge transfer from similar systemscited by 5
  6. 2023A Black-Box Physics-Informed Estimator based on Gaussian Process Regression for Robot Inverse Dynamics Identificationcited by 4
  7. 2024RoboMorph: In-Context Meta-Learning for Robot Dynamics Modelingcited by 3
  8. 2025Distributionally robust minimization in meta-learning for system identificationcited by 3
  9. 2025Data-Driven Dynamic Parameter Learning of manipulator robotscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models
  2. 2025DDAT: Diffusion Policies Enforcing Dynamically Admissible Robot Trajectories
  3. 2025Diffusion Models for Robotic Manipulation: A Survey
  4. 2025Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making
  5. 2025Pixel Motion Diffusion is What We Need for Robot Control
  6. 2024Diffusion Transformer Policy
  7. 2025Real-Time Iteration Scheme for Diffusion Policy
  8. 2025Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation