mlsanityData to 7 Oct 2026

Denoising Hamiltonian Network for Physical Reasoning

arXiv 2503.07596 ↗First posted 10 Mar 2025cs.LG cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Machine learning frameworks for physical problems must capture and enforce physical constraints that preserve the structure of dynamical systems. Many existing approaches achieve this by integrating physical operators into neural networks. While these methods offer theoretical guarantees, they face two key limitations: (i) they primarily model local relations between adjacent time steps, overlooking longer-range or higher-level physical interactions, and (ii) they focus on forward simulation while neglecting broader physical reasoning tasks. We propose the Denoising Hamiltonian Network (DHN), a novel framework that generalizes Hamiltonian mechanics operators into more flexible neural operators. DHN captures non-local temporal relationships and mitigates numerical integration errors through a denoising mechanism. DHN also supports multi-system modeling with a global conditioning mechanism. We demonstrate its effectiveness and flexibility across three diverse physical reasoning tasks with distinct inputs and outputs.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

35 of 46 references.

References · 35

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2018Neural Ordinary Differential Equationscited by 3,733
  9. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  10. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  11. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  12. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
23 more
  1. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  2. 2016Group Equivariant Convolutional Networkscited by 1,154
  3. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  4. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  5. 2019Hamiltonian Neural Networkscited by 702
  6. 2019Augmented Neural ODEscited by 396
  7. 2020Lagrangian Neural Networkscited by 388
  8. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  9. 2018On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groupscited by 296
  10. 2019Revisiting Self-Supervised Visual Representation Learningcited by 250
  11. 2020Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Datacited by 248
  12. 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 225
  13. 2018A General Theory of Equivariant CNNs on Homogeneous Spacescited by 223
  14. 2019Symplectic ODE-Net: Learning Hamiltonian Dynamics with Controlcited by 183
  15. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  16. 2022e3nn: Euclidean Neural Networkscited by 171
  17. 2019Hamiltonian Generative Networkscited by 136
  18. 2020Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraintscited by 102
  19. 2020Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learningcited by 77
  20. 2021Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifoldscited by 72
  21. 2021Learning Partial Equivariances from Datacited by 44
  22. 2023Symmetry Breaking and Equivariant Neural Networkscited by 24
  23. 2024Improving Equivariant Model Training via Constraint Relaxationcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamicscited by 40
  2. 2025SuperFlow: Training Flow Matching Models with RL on the Flycited by 10
  3. 2025SeeU: Seeing the Unseen World via 4D Dynamics-aware Generationcited by 3
  4. 2025UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidancecited by 2
  5. 2025Floating-Body Hydrodynamic Neural Networkscited by 2
  6. 2026NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamicscited by 1
  7. 2026Physical Transformercited by 0
  8. 2026CHLU: The Causal Hamiltonian Learning Unit as a Symplectic Primitive for Deep Learningcited by 0
  9. 2026Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherencecited by 0
  10. 2026HamiFormer: Dual-Expert Diffusion Fields with Affine Symplectic Mapscited by 0