# DaXBench: Benchmarking Deformable Object Manipulation with Differentiable Physics

arXiv: https://arxiv.org/abs/2210.13066 · HTML: https://mlsanity.com/paper/2210.13066/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2022.

## Built on by (most cited first, 24 of 24)

- [Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2403.03890/) (2024)
- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark](https://mlsanity.com/paper/2407.07788/) (2024)
- [RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization](https://mlsanity.com/paper/2307.10224/) (2023)
- [Benchmarking the Sim-to-Real Gap in Cloth Manipulation](https://mlsanity.com/paper/2310.09543/) (2023)
- [Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks](https://mlsanity.com/paper/2507.23172/) (2025)
- [Closing the Train-Test Gap in World Models for Gradient-Based Planning](https://mlsanity.com/paper/2512.09929/) (2025)
- [Data Pyramid for Embodied Manipulation: A Survey](https://mlsanity.com/paper/2607.24744/) (2026)
- [General-purpose Clothes Manipulation with Semantic Keypoints](https://mlsanity.com/paper/2408.08160/) (2024)
- [JAX-MPM: A Learning-Augmented Differentiable Meshfree Framework for GPU-Accelerated Lagrangian Simulation and Geophysical Inverse Modeling](https://mlsanity.com/paper/2507.04192/) (2025)
- [D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulation](https://mlsanity.com/paper/2403.12861/) (2024)
- [GenDOM: Generalizable One-shot Deformable Object Manipulation with Parameter-Aware Policy](https://mlsanity.com/paper/2309.09051/) (2023)
- [Differentiable Information Enhanced Model-Based Reinforcement Learning](https://mlsanity.com/paper/2503.01178/) (2025)
- [Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation](https://mlsanity.com/paper/2606.14188/) (2026)
- [ClothPPO: A Proximal Policy Optimization Enhancing Framework for Robotic Cloth Manipulation with Observation-Aligned Action Spaces](https://mlsanity.com/paper/2405.04549/) (2024)
- [Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation](https://mlsanity.com/paper/2606.04269/) (2026)
- [SoftVTBench: A Safety-Aware Visuo-Tactile Benchmark for Physically Constrained Robotic Manipulation of Deformable Objects (Early Version)](https://mlsanity.com/paper/2607.04234/) (2026)
- [GenORM: Generalizable One-shot Rope Manipulation with Parameter-Aware Policy](https://mlsanity.com/paper/2306.09872/) (2023)
- [CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints](https://mlsanity.com/paper/2507.19983/) (2025)
- [MoDeSuite: Robot Learning Task Suite for Benchmarking Mobile Manipulation with Deformable Objects](https://mlsanity.com/paper/2507.21796/) (2025)
- [SCOOP'D: Learning Mixed-Liquid-Solid Scooping via Sim2Real Generative Policy](https://mlsanity.com/paper/2510.11566/) (2025)
- [Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions](https://mlsanity.com/paper/2605.02699/) (2026)
- [Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming](https://mlsanity.com/paper/2606.06094/) (2026)
- [DexNinja: Learning Robust Dexterous Cutting Policy with a Real-to-Sim-to-Real Data Engine](https://mlsanity.com/paper/2610.17208/) (2026)

## Abstract (arXiv)

Deformable Object Manipulation (DOM) is of significant importance to both daily and industrial applications. Recent successes in differentiable physics simulators allow learning algorithms to train a policy with analytic gradients through environment dynamics, which significantly facilitates the development of DOM algorithms. However, existing DOM benchmarks are either single-object-based or non-differentiable. This leaves the questions of 1) how a task-specific algorithm performs on other tasks and 2) how a differentiable-physics-based algorithm compares with the non-differentiable ones in general. In this work, we present DaXBench, a differentiable DOM benchmark with a wide object and task coverage. DaXBench includes 9 challenging high-fidelity simulated tasks, covering rope, cloth, and liquid manipulation with various difficulty levels. To better understand the performance of general algorithms on different DOM tasks, we conduct comprehensive experiments over representative DOM methods, ranging from planning to imitation learning and reinforcement learning. In addition, we provide careful empirical studies of existing decision-making algorithms based on differentiable physics, and discuss their limitations, as well as potential future directions.