mlsanityData to 7 Oct 2026

DiffTaichi: Differentiable Programming for Physical Simulation

arXiv 1910.00935 ↗First posted 1 Oct 2019cs.LG cs.GR physics.comp-phcited by 248

Not on the map. Why?

Abstract (arXiv)

We present DiffTaichi, a new differentiable programming language tailored for building high-performance differentiable physical simulators. Based on an imperative programming language, DiffTaichi generates gradients of simulation steps using source code transformations that preserve arithmetic intensity and parallelism. A light-weight tape is used to record the whole simulation program structure and replay the gradient kernels in a reversed order, for end-to-end backpropagation. We demonstrate the performance and productivity of our language in gradient-based learning and optimization tasks on 10 different physical simulators. For example, a differentiable elastic object simulator written in our language is 4.2x shorter than the hand-engineered CUDA version yet runs as fast, and is 188x faster than the TensorFlow implementation. Using our differentiable programs, neural network controllers are typically optimized within only tens of iterations.

Key facts. Cited by 248 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 30; 2022: 46; 2023: 38; 2024: 34; 2025: 45; 2026: 54.

248 papers.

Sort:

By area:

  1. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 375
  2. 2021Advances in Neural Renderingcited by 365
  3. 2024PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generationcited by 169
  4. 2023PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identificationcited by 145
  5. 2023Flexible Isosurface Extraction for Gradient-Based Mesh Optimizationcited by 138
  6. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  7. 2021PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physicscited by 100
  8. 2024DiffusionPDE: Generative PDE-Solving Under Partial Observationcited by 100
  9. 2022Accelerated Policy Learning with Parallel Differentiable Simulationcited by 92
  10. 2024Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulationcited by 92
  11. 2022Do Differentiable Simulators Give Better Policy Gradients?cited by 83
  12. 2022SNUG: Self-Supervised Neural Dynamic Garmentscited by 83
38 more
  1. 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulationcited by 74
  2. 2022RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networkscited by 69
  3. 2025PhysGen3D: Crafting a Miniature Interactive World from a Single Imagecited by 65
  4. 2021DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contactcited by 64
  5. 2021DiffPD: Differentiable Projective Dynamicscited by 62
  6. 2023Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamicscited by 56
  7. 2021Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Languagecited by 55
  8. 2021An End-to-End Differentiable Framework for Contact-Aware Robot Designcited by 53
  9. 2021Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contactcited by 50
  10. 2022NeuPhysics: Editable Neural Geometry and Physics from Monocular Videoscited by 50
  11. 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Toolscited by 44
  12. 2024Feature Splatting: Language-Driven Physics-Based Scene Synthesis and Editingcited by 44
  13. 2024PhyRecon: Physically Plausible Neural Scene Reconstructioncited by 44
  14. 2021NTopo: Mesh-free Topology Optimization using Implicit Neural Representationscited by 41
  15. 2022Differentiable Simulation of Soft Multi-body Systemscited by 39
  16. 2021Efficient Differentiable Simulation of Articulated Bodiescited by 38
  17. 2022Differentiable Dynamics for Articulated 3d Human Motion Reconstructioncited by 38
  18. 2022Physical Design using Differentiable Learned Simulatorscited by 37
  19. 2023FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulationcited by 37
  20. 2022NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fieldscited by 36
  21. 2022Virtual Elastic Objectscited by 35
  22. 2021Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Modelscited by 33
  23. 2025Exploring the Evolution of Physics Cognition in Video Generation: A Surveycited by 31
  24. 2022Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamicscited by 30
  25. 2022DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objectscited by 29
  26. 2022RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimationcited by 29
  27. 2020Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learningcited by 27
  28. 2024AutoVFX: Physically Realistic Video Editing from Natural Language Instructionscited by 27
  29. 2021Learning neural network potentials from experimental data via Differentiable Trajectory Reweightingcited by 26
  30. 2024Differentiability in Unrolled Training of Neural Physics Simulators on Transient Dynamicscited by 25
  31. 2022ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulationcited by 24
  32. 2025DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundnesscited by 24
  33. 2023DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physicscited by 23
  34. 2022SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Renderingcited by 22
  35. 2023ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environmentcited by 22
  36. 2024Learning Quadruped Locomotion Using Differentiable Simulationcited by 22
  37. 2025Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videoscited by 22
  38. 2025The Reality Gap in Robotics: Challenges, Solutions, and Best Practicescited by 22

50 most cited of 248 All 248 (JSON)