mlsanityData to 14 Oct 2026

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

arXiv 2507.13097 ↗First posted 17 Jul 2025cs.RO cs.AIcited by 32

Not on the map. Why?

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.

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

64 of 78 references.

References · 64

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  6. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  8. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  9. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  11. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  12. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
38 more
  1. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  2. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  3. 2024One Step Diffusion via Shortcut Modelscited by 391
  4. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  5. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 325
  6. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 315
  7. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 282
  8. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 242
  9. 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 218
  10. 2022AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domainscited by 208
  11. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  12. 2022DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulationcited by 137
  13. 2022SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusioncited by 127
  14. 2020ACRONYM: A Large-Scale Grasp Dataset Based on Simulationcited by 117
  15. 2024URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Imagescited by 111
  16. 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representationscited by 108
  17. 2018More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touchcited by 102
  18. 2019Self-supervised 6D Object Pose Estimation for Robot Manipulationcited by 101
  19. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 95
  20. 2018PointNetGPD: Detecting Grasp Configurations from Point Setscited by 80
  21. 2022Deep Learning Approaches to Grasp Synthesis: A Reviewcited by 72
  22. 2024Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulationcited by 71
  23. 20196-DOF Grasping for Target-driven Object Manipulation in Cluttercited by 70
  24. 2020EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulationcited by 61
  25. 2024RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulationcited by 58
  26. 2022GenDexGrasp: Generalizable Dexterous Graspingcited by 56
  27. 2018Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervisioncited by 52
  28. 2023cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generationcited by 52
  29. 2022Learning Generalizable Dexterous Manipulation from Human Grasp Affordancecited by 51
  30. 2022StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objectscited by 50
  31. 2024DexDiffuser: Generating Dexterous Grasps with Diffusion Modelscited by 48
  32. 2023M2T2: Multi-Task Masked Transformer for Object-centric Pick and Placecited by 41
  33. 2023GraspGPT: Leveraging Semantic Knowledge from a Large Language Model for Task-Oriented Graspingcited by 40
  34. 2020Deep Differentiable Grasp Planner for High-DOF Gripperscited by 39
  35. 2017Domain Randomization and Generative Models for Robotic Graspingcited by 36
  36. 2023Fast-Grasp'D: Dexterous Multi-finger Grasp Generation Through Differentiable Simulationcited by 35
  37. 2020Same Object, Different Grasps: Data and Semantic Knowledge for Task-Oriented Graspingcited by 27
  38. 2023nvblox: GPU-Accelerated Incremental Signed Distance Field Mappingcited by 24

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 25.

32 papers.

Sort:

By area:

  1. 2025NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videoscited by 40
  2. 2025SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RLcited by 21
  3. 2026Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulationcited by 14
  4. 2026Any3D-VLA: Enhancing VLA Robustness via Diverse Point Cloudscited by 13
  5. 2025Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robotscited by 9
  6. 2026NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planningcited by 8
  7. 2026GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulationcited by 8
  8. 2026EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AIcited by 6
  9. 2026ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100Kcited by 5
  10. 2026A Few Words Go a Long Way: Language Guided Robot Policy Synthesiscited by 3
  11. 2026Robo-Harness K1: Harnessing Robot-Use Agents via Perception Augmentationcited by 3
  12. 2025OmniDexVLG: Learning Dexterous Grasp Generation from Vision Language Model-Guided Grasp Semantics, Taxonomy and Functional Affordancecited by 2
20 more
  1. 2026Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learningcited by 2
  2. 2026DREAM: Deployment-Time Demonstration Generation via Real-to-Sim for Scalable Policy Adaptationcited by 2
  3. 2025Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Controlcited by 1
  4. 2025IGen: Scalable Data Generation for Robot Learning from Open-World Imagescited by 1
  5. 2026Replanning Human-Robot Collaborative Tasks with Vision-Language Models via Semantic and Physical Dual-Correctioncited by 1
  6. 2026Relation-Centric Open-Vocabulary 3D Gaussian Segmentationcited by 1
  7. 2026PROBE: Manipulation-Grounded Visual Question Answering with VLM Agentscited by 1
  8. 2025GraspFactory: A Large Object-Centric Grasping Datasetcited by 0
  9. 2026Show, Don't Tell: Detecting Novel Objects by Watching Human Videoscited by 0
  10. 2026Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planningcited by 0
  11. 2026DCGrasp: Distance-aware Controllable Grasp Generationcited by 0
  12. 2026Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observationscited by 0
  13. 2026Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Executioncited by 0
  14. 2026GraRe: Grasp Candidate Re-Ranking for Frozen 6-DoF Grasp Detectorscited by 0
  15. 2026Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraintscited by 0
  16. 2026Gripper-aware Vision Language Action Modelscited by 0
  17. 2026SynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrationscited by 0
  18. 2026Steer2Grasp: Inference-Time Embodiment-Aware Steering for Diverse Physically Feasible Grasp Diffusioncited by 0
  19. 2026SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generationcited by 0
  20. 2026Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrationscited by 0