# GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training

arXiv: https://arxiv.org/abs/2507.13097 · HTML: https://mlsanity.com/paper/2507.13097/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 78 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Builds on (most cited first, 30 of 64)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [One Step Diffusion via Shortcut Models](https://mlsanity.com/paper/2410.12557/) (2024)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes](https://mlsanity.com/paper/2103.14127/) (2021)
- [AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains](https://mlsanity.com/paper/2212.08333/) (2022)
- [FoundationStereo: Zero-Shot Stereo Matching](https://mlsanity.com/paper/2501.09898/) (2025)
- [DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation](https://mlsanity.com/paper/2210.02697/) (2022)
- [SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion](https://mlsanity.com/paper/2209.03855/) (2022)
- [ACRONYM: A Large-Scale Grasp Dataset Based on Simulation](https://mlsanity.com/paper/2011.09584/) (2020)
- [URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images](https://mlsanity.com/paper/2405.11656/) (2024)
- [Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations](https://mlsanity.com/paper/2104.01542/) (2021)
- [More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch](https://mlsanity.com/paper/1805.11085/) (2018)
- [Self-supervised 6D Object Pose Estimation for Robot Manipulation](https://mlsanity.com/paper/1909.10159/) (2019)

## Built on by (most cited first, 30 of 32)

- [NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos](https://mlsanity.com/paper/2510.08568/) (2025)
- [SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL](https://mlsanity.com/paper/2512.04069/) (2025)
- [Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation](https://mlsanity.com/paper/2602.15828/) (2026)
- [Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds](https://mlsanity.com/paper/2602.00807/) (2026)
- [Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots](https://mlsanity.com/paper/2511.00917/) (2025)
- [NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning](https://mlsanity.com/paper/2602.20119/) (2026)
- [GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation](https://mlsanity.com/paper/2605.22882/) (2026)
- [EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI](https://mlsanity.com/paper/2607.07459/) (2026)
- [ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K](https://mlsanity.com/paper/2603.16866/) (2026)
- [A Few Words Go a Long Way: Language Guided Robot Policy Synthesis](https://mlsanity.com/paper/2607.23784/) (2026)
- [Robo-Harness K1: Harnessing Robot-Use Agents via Perception Augmentation](https://mlsanity.com/paper/2609.29389/) (2026)
- [OmniDexVLG: Learning Dexterous Grasp Generation from Vision Language Model-Guided Grasp Semantics, Taxonomy and Functional Affordance](https://mlsanity.com/paper/2512.03874/) (2025)
- [Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning](https://mlsanity.com/paper/2603.09882/) (2026)
- [DREAM: Deployment-Time Demonstration Generation via Real-to-Sim for Scalable Policy Adaptation](https://mlsanity.com/paper/2608.29078/) (2026)
- [Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Control](https://mlsanity.com/paper/2509.06201/) (2025)
- [IGen: Scalable Data Generation for Robot Learning from Open-World Images](https://mlsanity.com/paper/2512.01773/) (2025)
- [Replanning Human-Robot Collaborative Tasks with Vision-Language Models via Semantic and Physical Dual-Correction](https://mlsanity.com/paper/2602.14551/) (2026)
- [Relation-Centric Open-Vocabulary 3D Gaussian Segmentation](https://mlsanity.com/paper/2607.01140/) (2026)
- [PROBE: Manipulation-Grounded Visual Question Answering with VLM Agents](https://mlsanity.com/paper/2608.17129/) (2026)
- [GraspFactory: A Large Object-Centric Grasping Dataset](https://mlsanity.com/paper/2509.20550/) (2025)
- [Show, Don't Tell: Detecting Novel Objects by Watching Human Videos](https://mlsanity.com/paper/2603.12751/) (2026)
- [Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning](https://mlsanity.com/paper/2606.28813/) (2026)
- [DCGrasp: Distance-aware Controllable Grasp Generation](https://mlsanity.com/paper/2606.29924/) (2026)
- [Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observations](https://mlsanity.com/paper/2607.00498/) (2026)
- [Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Execution](https://mlsanity.com/paper/2607.14341/) (2026)
- [GraRe: Grasp Candidate Re-Ranking for Frozen 6-DoF Grasp Detectors](https://mlsanity.com/paper/2608.00946/) (2026)
- [Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints](https://mlsanity.com/paper/2608.22149/) (2026)
- [Gripper-aware Vision Language Action Models](https://mlsanity.com/paper/2608.24603/) (2026)
- [SynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrations](https://mlsanity.com/paper/2609.21650/) (2026)
- [Steer2Grasp: Inference-Time Embodiment-Aware Steering for Diverse Physically Feasible Grasp Diffusion](https://mlsanity.com/paper/2609.33546/) (2026)

## Abstract (arXiv)

Grasping is a fundamental robot skill, yet despite significant research advancements, learning-based 6-DOF grasping approaches are still not turnkey and struggle to generalize across different embodiments and in-the-wild settings. We build upon the recent success on modeling the object-centric grasp generation process as an iterative diffusion process. Our proposed framework, GraspGen, consists of a DiffusionTransformer architecture that enhances grasp generation, paired with an efficient discriminator to score and filter sampled grasps. We introduce a novel and performant on-generator training recipe for the discriminator. To scale GraspGen to both objects and grippers, we release a new simulated dataset consisting of over 53 million grasps. We demonstrate that GraspGen outperforms prior methods in simulations with singulated objects across different grippers, achieves state-of-the-art performance on the FetchBench grasping benchmark, and performs well on a real robot with noisy visual observations.