pith. sign in

arxiv: 2606.18092 · v1 · pith:NCHZTUJ5new · submitted 2026-06-16 · 💻 cs.RO · cs.AI

EAGG: Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning

Wanhao Niu , Qiyan Ke , Yuan Sun , Hao Sun , Jie Xu , Muyuan Ma , Ruiqi Hu , Fuchun Sun This is my paper

Pith reviewed 2026-06-27 00:33 UTC · model grok-4.3

classification 💻 cs.RO cs.AI
keywords grasp generationcross-end-effectorembodiment alignmentgraph conditioningrobot handsdexterous manipulationtransfer learning
0
0 comments X

The pith

A single grasp generator can match specialized models across six different robot hands by aligning each hand's structure.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tries to establish that cross-end-effector grasp generation benefits from explicitly modeling each embodiment's topology and geometry inside a shared model instead of using static descriptors. It proposes representing hands with graphs and refreshing geometry tokens during planning. A sympathetic reader would care because this could allow one system to work with many robot designs without retraining from scratch for each. The results on a benchmark with six end effectors support that performance stays close to dedicated models while enabling transfer.

Core claim

EAGG represents each embodiment with a topology-aware end-effector graph and an embodiment-specific low-dimensional end-effector control space. A frozen end-effector-cognition backbone converts the current articulated state into geometry-aware tokens that act as a reusable morphology prior, and iterative geometry injection refreshes these tokens throughout sampling so that conditioning remains synchronized with the evolving end-effector geometry.

What carries the argument

The topology-aware end-effector graph with iterative geometry injection, which produces reusable morphology priors from a frozen backbone and keeps them synchronized during grasp sampling.

If this is right

  • On the MultiGripperGrasp benchmark, EAGG reaches 56.17% average success across six training end effectors.
  • It remains within 1.10 percentage points of specialized training while preserving transfer to finetuning and zero-shot end effectors.
  • Iterative geometry injection reduces the pooled median contact distance from 0.239 cm to 0.189 cm.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This method implies that explicit embodiment alignment could apply to other robotics tasks like placement or assembly.
  • Testing the approach on hands with very different actuation couplings might reveal limits of the graph representation.
  • Zero-shot performance suggests potential for rapid adaptation to new end effectors without full retraining.

Load-bearing premise

That a frozen end-effector-cognition backbone can produce reusable geometry-aware tokens from the articulated state that stay useful when refreshed iteratively with new geometry.

What would settle it

A test showing that a version without iterative geometry injection achieves the same or lower median contact distance on the benchmark would indicate that synchronization is not necessary.

Figures

Figures reproduced from arXiv: 2606.18092 by Fuchun Sun, Hao Sun, Jie Xu, Muyuan Ma, Qiyan Ke, Ruiqi Hu, Wanhao Niu, Yuan Sun.

Figure 1
Figure 1. Figure 1: Cross-end-effector grasp generation setting. The figure highlights two coupled generalization axes. Top-left: diverse object inputs, including novel objects. Bottom-left: diverse end effectors, including unseen embodiments with different topology and closure types. Top-right: object generalization for a fixed embodiment, il￾lustrated with Allegro grasps across different objects. Bottom-right: embodiment ge… view at source ↗
Figure 2
Figure 2. Figure 2: EAGG pipeline. The upper branch encodes the object point cloud into object tokens, while the lower branch encodes the embodiment from a hand graph and a low-dimensional control representation into end-effector tokens. The transformer backbone predicts the grasp state iteratively from noise to the clean grasp. In the IGI loop, the intermediate grasp is decoded to the current articulated geometry, re-encoded… view at source ↗
Figure 4
Figure 4. Figure 4: Latent-space diagnostic. Projection of end-effector em￾beddings exported from the pre-trained end-effector-cognition model. The figure provides supporting evidence that the representation preserves morphology-relevant organization. D. Geometry Diagnostics and Component Analysis [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Cross-end-effector IGI diagnostic. Orange and blue boxplots compare Non-IGI and IGI on 10 end effectors. The three panels report initial overlap (%), final contact distance (CD, cm), and final penetration depth (PD, cm); lower values are better in all cases. Boxplots aggregate per-object summaries, so the figure measures whether IGI consistently shifts the geometry distribution toward cleaner states across… view at source ↗
Figure 6
Figure 6. Figure 6: Qualitative cross-end-effector grasp results. Each row shows representative generated grasps for one end effector. The top block contains the six training end effectors used in joint base training, the middle block contains the finetuning end effectors (Sawyer and Jaco) after 10-epoch adaptation with 5% data, and the bottom block contains the zero-shot end effectors (FreedomHand and DexHand) after lightwei… view at source ↗
Figure 7
Figure 7. Figure 7: Real-world hardware configurations. The hardware evaluation uses a UR-based workstation with interchangeable FreedomHand and DaHuan AG95 end effectors, an SOARM101 platform, RGB-D sensing, and the representative object set shown in the figure. References [1] J. Mahler, J. Liang, S. Niyaz et al., “Dex-net 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics,” in Ro… view at source ↗
Figure 8
Figure 8. Figure 8: Representative real-world execution results. Panel (a) shows generated grasps for FreedomHand, DaHuan AG95, and SOARM101. Panels (b)–(d) show representative successful executions on UR5 + FreedomHand, UR5 + DaHuan AG95, and SOARM101, respectively. [25] F. Zhao, D. Tsetserukou, and Q. Liu, “Graingrasp: Dexterous grasp generation with fine-grained contact guidance,” in 2024 IEEE International Conference on R… view at source ↗
read the original abstract

Cross-end-effector grasp generation seeks a unified model that generalizes across objects and across embodiments ranging from parallel grippers to dexterous end effectors. Existing grasp generators are typically designed for a fixed embodiment or encode embodiment identity with a static descriptor, which weakens transfer when topology, actuation coupling, and contact geometry differ substantially. We present EAGG, an embodiment-aligned grasp generator that represents each embodiment with a topology-aware end-effector graph and an embodiment-specific low-dimensional end-effector control space. A frozen end-effector-cognition backbone converts the current articulated state into geometry-aware tokens that act as a reusable morphology prior, and iterative geometry injection refreshes these tokens throughout sampling so that conditioning remains synchronized with the evolving end-effector geometry. On the MultiGripperGrasp benchmark, EAGG reaches 56.17% average success across six training end effectors, remaining within 1.10 percentage points of specialized training while preserving transfer to finetuning and zero-shot end effectors. Iterative geometry injection further reduces the pooled median contact distance from 0.239 cm to 0.189 cm. These results show that cross-end-effector grasp generation is strengthened by aligning embodiment structure inside a shared generator rather than suppressing embodiment differences. Code is available at https://github.com/wanhaoniu/EAGG.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. The manuscript introduces EAGG, a unified grasp generator for cross-end-effector settings. It represents each embodiment via a topology-aware end-effector graph plus a low-dimensional control space, employs a frozen end-effector-cognition backbone to produce reusable geometry-aware tokens, and applies iterative geometry injection to keep conditioning synchronized with evolving geometry during sampling. On the MultiGripperGrasp benchmark the method reports 56.17% average success across six training end effectors (within 1.10 pp of per-embodiment specialized training), with preserved transfer to finetuning and zero-shot cases, and a reduction in pooled median contact distance from 0.239 cm to 0.189 cm when iterative injection is used. Code is released.

Significance. If the reported margins and transfer results hold under the stated experimental protocol, the work is significant for robotics: it demonstrates that explicit embodiment structure (graph topology plus iterative geometry refresh) can be retained inside a single generator without sacrificing performance relative to specialized models. The public code release and concrete benchmark numbers constitute reproducible evidence for the central architectural claim.

minor comments (3)
  1. The abstract and §4 report success rates and contact-distance reductions but do not state the precise definition of “success” (e.g., whether it requires force closure, a minimum number of contacts, or a simulation threshold); adding this definition would strengthen the results section.
  2. Table or figure captions for the MultiGripperGrasp results should explicitly list the six training end effectors, the finetuning set, and the zero-shot set so that the transfer claims can be verified without cross-referencing the text.
  3. The description of the frozen backbone (how its output tokens are produced from the articulated state) would benefit from a short pseudocode block or explicit input/output dimensions in the methods section.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive summary, significance assessment, and recommendation of minor revision. The report contains no major comments requiring point-by-point rebuttal.

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper describes an architectural method (topology-aware graph, frozen backbone, iterative geometry injection) and reports independent benchmark results on MultiGripperGrasp (56.17% success, 1.10 pp gap, contact-distance reduction). No derivation chain reduces a claimed prediction or result to its own inputs by construction, no fitted parameters are renamed as predictions, and no load-bearing self-citations or uniqueness theorems are invoked. The evaluation metrics are external to the model's internal definitions, making the central claims self-contained against the benchmark.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Review based on abstract only; no explicit free parameters, invented entities, or detailed axioms are stated. The central method rests on the unverified assumption that the frozen backbone produces reusable tokens.

axioms (1)
  • domain assumption A frozen end-effector-cognition backbone converts the current articulated state into geometry-aware tokens that act as a reusable morphology prior.
    This premise is invoked to justify the shared generator design and is load-bearing for the claimed alignment benefit.

pith-pipeline@v0.9.1-grok · 5783 in / 1338 out tokens · 46772 ms · 2026-06-27T00:33:30.555395+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

58 extracted references · 1 linked inside Pith

  1. [1]

    Dex-net 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics,

    J. Mahler, J. Liang, S. Niyaz et al. , “Dex-net 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics,” in Robotics: Science and Systems (RSS) , 2017

    2017

  2. [2]

    Pointnetgpd: Detecting grasp configurations from point sets,

    H. Liang, X. Ma, S. Li, M. Görner, S. Tang, B. Fang, F. Sun, and J. Zhang, “Pointnetgpd: Detecting grasp configurations from point sets,” in 2019 IEEE International Conference on Robotics and Automation (ICRA) . IEEE, 2019, pp. 3629–3635

    2019

  3. [3]

    6-dof graspnet: Varia- tional grasp generation for object manipulation,

    A. Mousavian, C. Eppner, and D. Fox, “6-dof graspnet: Varia- tional grasp generation for object manipulation,” in Proceedings of the IEEE/CVF International Conference on Computer Vi- sion, 2019, pp. 2901–2910

    2019

  4. [4]

    S4g: Amodal single-view single- shot se(3) grasp detection in cluttered scenes,

    Y. Qin, R. Chen, H. Zhu et al., “S4g: Amodal single-view single- shot se(3) grasp detection in cluttered scenes,” in Conference on Robot Learning. PMLR, 2020, pp. 53–65

    2020

  5. [5]

    Contact- graspnet: Efficient 6-dof grasp generation in cluttered scenes,

    M. Sundermeyer, A. Mousavian, R. Tribelhorn et al. , “Contact- graspnet: Efficient 6-dof grasp generation in cluttered scenes,” in 2021 IEEE International Conference on Robotics and Au- tomation (ICRA) . IEEE, 2021, pp. 13 438–13 444

    2021

  6. [6]

    Dexgraspnet: A large-scale robotic dexterous grasp dataset for general objects based on simulation,

    R. Wang, J. Zhang, J. Chen, Y. Xu, P. Li, T. Liu, and H. Wang, “Dexgraspnet: A large-scale robotic dexterous grasp dataset for general objects based on simulation,” in 2023 IEEE Interna- tional Conference on Robotics and Automation (ICRA) . IEEE, 2023, pp. 11 359–11 366

    2023

  7. [7]

    Dexgraspnet 2.0: Learning generative dexterous grasping in large-scale synthetic cluttered scenes,

    J. Zhang, H. Liu, D. Li, X. Yu, H. Geng, Y. Ding, J. Chen, and H. Wang, “Dexgraspnet 2.0: Learning generative dexterous grasping in large-scale synthetic cluttered scenes,” in 8th Annual Conference on Robot Learning (CoRL) , 2024

    2024

  8. [8]

    Unidexgrasp: Universal robotic dexterous grasping via learning diverse proposal generation and goal-conditioned policy,

    Y. Xu, W. Wan, J. Zhang, H. Liu, Z. Shan, H. Shen, R. Wang, H. Geng, Y. Weng, J. Chen, T. Liu, L. Yi, and H. Wang, “Unidexgrasp: Universal robotic dexterous grasping via learning diverse proposal generation and goal-conditioned policy,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2023, pp. 4737–4747

    2023

  9. [9]

    Unidexgrasp++: Improving dexterous grasping policy learn- ing via geometry-aware curriculum and iterative generalist- specialist learning,

    W. Wan, H. Geng, Y. Liu, Z. Shan, Y. Yang, L. Yi, and H. Wang, “Unidexgrasp++: Improving dexterous grasping policy learn- ing via geometry-aware curriculum and iterative generalist- specialist learning,” in Proceedings of the IEEE/CVF Interna- tional Conference on Computer Vision (ICCV) , 2023

    2023

  10. [10]

    Multigrippergrasp: A dataset for robotic grasping from parallel jaw grippers to dexterous hands,

    L. F. Casas, A. Oveisi, B. Chen, P. Kulkarni, and K. Pereida, “Multigrippergrasp: A dataset for robotic grasping from parallel jaw grippers to dexterous hands,” in 2024 IEEE/RSJ Interna- tional Conference on Intelligent Robots and Systems (IROS) . IEEE, 2024

    2024

  11. [11]

    Cross-embodiment dex- terous grasping with reinforcement learning,

    H. Yuan, B. Zhou, Y. Fu, and Z. Lu, “Cross-embodiment dex- terous grasping with reinforcement learning,” in The Thirteenth International Conference on Learning Representations (ICLR) , 2025

    2025

  12. [12]

    Efficient residual learning with mixture-of-experts for universal dexterous grasping,

    Z. Huang, H. Yuan, Y. Fu, and Z. Lu, “Efficient residual learning with mixture-of-experts for universal dexterous grasping,” in The Thirteenth International Conference on Learning Repre- sentations (ICLR) , 2025

    2025

  13. [13]

    D(R,O) grasp: A unified representation of robot and object interaction for cross-embodiment dexterous grasping,

    Z. Wei, Z. Xu, J. Guo, Y. Hou, C. Gao, Z. Cai, J. Luo, and L. Shao, “D(R,O) grasp: A unified representation of robot and object interaction for cross-embodiment dexterous grasping,” in 2025 IEEE International Conference on Robotics and Automa- tion (ICRA) , 2025

    2025

  14. [14]

    UniFucGrasp: Human- hand-inspired unified functional grasp annotation strategy and dataset for diverse dexterous hands,

    H. Lin, W. Chen, X. Chen, F. Yang, Q. Diao, W. Xie, S. Wu, K. Yang, M. Li, and Y. Wang, “UniFucGrasp: Human- hand-inspired unified functional grasp annotation strategy and dataset for diverse dexterous hands,” arXiv preprint arXiv:2508.03339, 2025

    arXiv 2025

  15. [15]

    DexVLG: Dexterous vision-language-grasp model at scale,

    J. He, D. Li, X. Yu, Z. Qi, W. Zhang, J. Chen, Z. Zhang, Z. Zhang, L. Yi, and H. Wang, “DexVLG: Dexterous vision-language-grasp model at scale,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025

    2025

  16. [16]

    Postural hand synergies for tool use,

    M. Santello, M. Flanders, and J. F. Soechting, “Postural hand synergies for tool use,” Journal of neuroscience , vol. 18, no. 23, pp. 10 105–10 115, 1998

    1998

  17. [17]

    Dexterous grasping with low-dimensional hand models,

    M. T. Ciocarlie and P. K. Allen, “Dexterous grasping with low-dimensional hand models,” in 2007 IEEE International Conference on Robotics and Automation (ICRA) . IEEE, 2007

    2007

  18. [18]

    Hand posture subspaces for dexterous robotic grasping,

    M. T. Ciocarlie and P. K. Allen, “Hand posture subspaces for dexterous robotic grasping,” The International Journal of Robotics Research, vol. 28, no. 7, pp. 851–867, 2009

    2009

  19. [19]

    Mapping synergies from human to robotic hands with dis- similar kinematics: An approach in the object domain,

    G. Gioioso, G. Salvietti, M. Malvezzi, and D. Prattichizzo, “Mapping synergies from human to robotic hands with dis- similar kinematics: An approach in the object domain,” IEEE Transactions on Robotics, vol. 29, no. 4, pp. 825–837, 2013

    2013

  20. [20]

    Hand synergies: Integration of robotics and neuroscience for understanding the control of biological and artificial hands,

    M. Santello, M. Bianchi, M. Gabiccini, E. Ricciardi, G. Salvietti, D. Prattichizzo, M. Ernst, A. Moscatelli, H. Jorntell, A. M. L. Kappers et al. , “Hand synergies: Integration of robotics and neuroscience for understanding the control of biological and artificial hands,” Physics of Life Reviews, vol. 17, pp. 1–23, 2016

    2016

  21. [21]

    Synergy-based grasp synthesis for multi-fingered hands,

    H. Jiang, S. Liu, J. Wang et al. , “Synergy-based grasp synthesis for multi-fingered hands,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2021

    2021

  22. [22]

    Dexdiffuser: Gen- erating dexterous grasps with diffusion models,

    Z. Weng, H. Lu, D. Kragic, and J. Lundell, “Dexdiffuser: Gen- erating dexterous grasps with diffusion models,” arXiv preprint arXiv:2402.02989, 2024

    arXiv 2024

  23. [23]

    Learning diverse and physically feasible dexterous grasps with generative model and bilevel optimization,

    A. Wu, M. Guo, and C. K. Liu, “Learning diverse and physically feasible dexterous grasps with generative model and bilevel optimization,” in Proceedings of The 6th Conference on Robot Learning (CoRL), 2023, pp. 1938–1948

    2023

  24. [24]

    Fast-grasp’d: Dexter- ous multi-finger grasp generation through differentiable simula- tion,

    D. Turpin, T. Zhong, S. Zhang, G. Zhu, E. Heiden, M. Macklin, S. Tsogkas, S. Dickinson, and A. Garg, “Fast-grasp’d: Dexter- ous multi-finger grasp generation through differentiable simula- tion,” in 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2023, pp. 8082–8089. 15 Fig. 8. Representative real-world execution results. Panel...

    2023

  25. [25]

    Graingrasp: Dexterous grasp generation with fine-grained contact guidance,

    F. Zhao, D. Tsetserukou, and Q. Liu, “Graingrasp: Dexterous grasp generation with fine-grained contact guidance,” in 2024 IEEE International Conference on Robotics and Automation (ICRA), 2024, pp. 6470–6476

    2024

  26. [26]

    Springgrasp: Synthesizing compliant, dexterous grasps under shape uncertainty,

    S. Chen, J. Bohg, and C. K. Liu, “Springgrasp: Synthesizing compliant, dexterous grasps under shape uncertainty,” arXiv preprint arXiv:2404.13532, 2024

    arXiv 2024

  27. [27]

    FFHFlow: Diverse and uncertainty-aware dexterous grasp generation via flow variational inference,

    Q. Feng, J. Feng, Z. Chen, R. Triebel, and A. Knoll, “FFHFlow: Diverse and uncertainty-aware dexterous grasp generation via flow variational inference,” in Proceedings of The 9th Conference on Robot Learning (CoRL) , 2025, pp. 1352–1381

    2025

  28. [28]

    DexTOG: Learning task-oriented dexterous grasp with language condi- tion,

    J. Zhang, W. Xu, Z. Yu, P. Xie, T. Tang, and C. Lu, “DexTOG: Learning task-oriented dexterous grasp with language condi- tion,” IEEE Robotics and Automation Letters , vol. 10, no. 2, pp. 995–1002, 2025

    2025

  29. [29]

    AffordDexGrasp: Open-set language-guided dexterous grasp with generalizable-instructive affordance,

    Y.-L. Wei, M. Lin, Y. Lin, J.-J. Jiang, X.-M. Wu, L.-A. Zeng, and W.-S. Zheng, “AffordDexGrasp: Open-set language-guided dexterous grasp with generalizable-instructive affordance,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , 2025

    2025

  30. [30]

    G- DexGrasp: Generalizable dexterous grasping synthesis via part- aware prior retrieval and prior-assisted generation,

    J. Jian, X. Liu, Z. Chen, M. Li, J. Liu, and R. Hu, “G- DexGrasp: Generalizable dexterous grasping synthesis via part- aware prior retrieval and prior-assisted generation,” in Proceed- ings of the IEEE/CVF International Conference on Computer Vision (ICCV) , 2025

    2025

  31. [31]

    Graspit! a versatile simulator for robotic grasping,

    A. Miller and P. Allen, “Graspit! a versatile simulator for robotic grasping,” IEEE Robotics & Automation Magazine , vol. 11, no. 4, pp. 110–122, 2004

    2004

  32. [32]

    The columbia grasp database,

    C. Goldfeder, M. Ciocarlie, H. Dang et al., “The columbia grasp database,” in 2009 IEEE International Conference on Robotics and Automation. IEEE, 2009, pp. 1710–1716

    2009

  33. [33]

    The ycb object and model set: Towards common benchmarks for manipulation research,

    B. Calli, A. Singh, A. Walsman, S. S. Srinivasa, P. Abbeel, and A. M. Dollar, “The ycb object and model set: Towards common benchmarks for manipulation research,” in 2015 International Conference on Advanced Robotics (ICAR) . IEEE, 2015, pp. 510–517

    2015

  34. [34]

    Egad! an evolved grasp- ing analysis dataset for diversity and reproducibility in robotic manipulation,

    D. Morrison, P. Corke, and J. Leitner, “Egad! an evolved grasp- ing analysis dataset for diversity and reproducibility in robotic manipulation,” IEEE Robotics and Automation Letters , vol. 5, no. 3, pp. 4368–4375, 2020

    2020

  35. [35]

    Deep learning approaches to grasp synthesis: A review,

    R. Newbury, S. Sun, M. A. Roa et al., “Deep learning approaches to grasp synthesis: A review,” IEEE Transactions on Robotics , vol. 39, no. 5, pp. 3994–4015, 2023

    2023

  36. [36]

    An overview of learning-based dexterous grasping: Recent advances and future directions,

    X. Song, Y. Li, Y. Zhang, Y. Liu, and L. Jiang, “An overview of learning-based dexterous grasping: Recent advances and future directions,” Artificial Intelligence Review , vol. 58, p. 300, 2025

    2025

  37. [37]

    Customizable 6 degrees of freedom grasping dataset and an interactive training method for graph convolutional network,

    W. Niu, Z. Zhu, H. Wang et al. , “Customizable 6 degrees of freedom grasping dataset and an interactive training method for graph convolutional network,” Engineering Applications of Artificial Intelligence, vol. 138, p. 109320, 2024

    2024

  38. [38]

    Visual-tactile grasp dataset and grasp margin matrix analysis for stability evaluation,

    W. Niu, Z. Zhu, J. Zheng et al. , “Visual-tactile grasp dataset and grasp margin matrix analysis for stability evaluation,” IEEE Transactions on Robotics, 2026

    2026

  39. [39]

    Unigrasp: Learning a unified model to grasp with multifingered robotic hands,

    L. Shao, F. Ferreira, M. Jorda, V. Nambiar, J. Luo, K. Solovey, P. Agrawal, S. Savarese, M. Müller, R. Shome et al. , “Unigrasp: Learning a unified model to grasp with multifingered robotic hands,” IEEE Robotics and Automation Letters , vol. 5, no. 4, pp. 2286–2293, 2020

    2020

  40. [40]

    Gendexgrasp: Generalizable dexterous grasping,

    P. Li, T. Liu, Y. Li, Y. Geng, Y. Zhu, Y. Yang, and S. Huang, “Gendexgrasp: Generalizable dexterous grasping,” in 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2023

    2023

  41. [41]

    Transferring grasping across grippers: Learning-optimization hybrid framework for generalized planar grasp generation,

    X. Wang and Q. Xu, “Transferring grasping across grippers: Learning-optimization hybrid framework for generalized planar grasp generation,” IEEE Transactions on Robotics , vol. 40, pp. 3388–3405, 2024

    2024

  42. [42]

    T(R,O) grasp: Efficient graph diffusion of robot-object spatial transforma- tion for cross-embodiment dexterous grasping,

    X. Fei, Z. Xu, H. Fang, T. Zhang, and L. Shao, “T(R,O) grasp: Efficient graph diffusion of robot-object spatial transforma- tion for cross-embodiment dexterous grasping,” arXiv preprint arXiv:2510.12724, 2025

    arXiv 2025

  43. [43]

    De- moGrasp: Universal dexterous grasping from a single demon- stration,

    H. Yuan, Z. Huang, Y. Wang, C. Mao, C. Xu, and Z. Lu, “De- moGrasp: Universal dexterous grasping from a single demon- stration,” arXiv preprint arXiv:2509.22149 , 2025

    arXiv 2025

  44. [44]

    Grasp2grasp: 16 Vision-based dexterous grasp translation via schrödinger bridges,

    T. Zhong, J. Buchanan, and C. Allen-Blanchette, “Grasp2grasp: 16 Vision-based dexterous grasp translation via schrödinger bridges,” in The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS) , 2025

    2025

  45. [45]

    Toward dexterous manipulation with augmented adaptive synergies: The pisa/iit softhand 2,

    C. Della Santina, C. Piazza, G. Grioli, M. G. Catalano, and A. Bicchi, “Toward dexterous manipulation with augmented adaptive synergies: The pisa/iit softhand 2,” IEEE Transactions on Robotics, vol. 34, no. 5, pp. 1141–1156, 2018

    2018

  46. [46]

    Nervenet: Learning structured policy with graph neural networks,

    T. Wang, R. Liao, J. Ba et al. , “Nervenet: Learning structured policy with graph neural networks,” in International Conference on Learning Representations (ICLR) , 2018

    2018

  47. [47]

    Graph-based policy for robot control,

    W. Huang, I. Mordatch, and D. Pathak, “Graph-based policy for robot control,” in 2019 IEEE International Conference on Robotics and Automation (ICRA) . IEEE, 2019

    2019

  48. [48]

    Denoising diffusion probabilistic models,

    J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” in Advances in Neural Information Processing Sys- tems, vol. 33, 2020, pp. 6840–6851

    2020

  49. [49]

    Score- based generative modeling through stochastic differential equa- tions,

    Y. Song, J. Sohl-Dickstein, D. P. Kingma et al. , “Score- based generative modeling through stochastic differential equa- tions,” in International Conference on Learning Representa- tions (ICLR) , 2021

    2021

  50. [50]

    Flow matching for generative modeling,

    Y. Lipman, R. T. Chen, H. Ben-Hamu et al. , “Flow matching for generative modeling,” International Conference on Learning Representations (ICLR), 2023

    2023

  51. [51]

    Flow straight and fast: Learning to generate and transfer data with rectified flow,

    X. Liu, C. Gong, and Q. Liu, “Flow straight and fast: Learning to generate and transfer data with rectified flow,” International Conference on Learning Representations (ICLR) , 2022

    2022

  52. [52]

    Building normal- izing flows with stochastic interpolants,

    M. S. Albergo and E. Vanden-Eijnden, “Building normal- izing flows with stochastic interpolants,” arXiv preprint arXiv:2209.15571, 2023

    Pith/arXiv arXiv 2023

  53. [53]

    Frog- ger: Fast robust grasp generation via the min-weight metric,

    A. H. Li, P. Culbertson, J. W. Burdick, and A. D. Ames, “Frog- ger: Fast robust grasp generation via the min-weight metric,” in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2023, pp. 6809–6816

    2023

  54. [54]

    Grasp as you say: Language- guided dexterous grasp generation,

    Y.-L. Wei, J.-J. Jiang, C. Xing, X.-T. Tan, X.-M. Wu, H. Li, M. Cutkosky, and W.-S. Zheng, “Grasp as you say: Language- guided dexterous grasp generation,” in Advances in Neural In- formation Processing Systems , vol. 37, 2024, pp. 46 881–46 907

    2024

  55. [55]

    HGDiffuser: Efficient task-oriented grasp generation via human-guided grasp diffusion models,

    D. Huang, W. Dong, C. Tang, and H. Zhang, “HGDiffuser: Efficient task-oriented grasp generation via human-guided grasp diffusion models,” arXiv preprint arXiv:2503.00508 , 2025

    arXiv 2025

  56. [56]

    Pointnet++: Deep hierarchical feature learning on point sets in a metric space,

    C. R. Qi, L. Yi, H. Su, and L. J. Guibas, “Pointnet++: Deep hierarchical feature learning on point sets in a metric space,” in Advances in Neural Information Processing Systems , 2017

    2017

  57. [57]

    Synergygrasp: A structure-aware synergy frame- work for multi-hand grasp generation,

    W. Niu, H. Sun, Y. Rong, Z. Zhu, Y. Xie, H. Zhou, C. Zhuang, and F. Sun, “Synergygrasp: A structure-aware synergy frame- work for multi-hand grasp generation,” 2026, under review

    2026

  58. [58]

    Grasp pose detection in point clouds,

    A. ten Pas, M. Gualtieri, K. Saenko, and R. Platt, “Grasp pose detection in point clouds,” The International Journal of Robotics Research, vol. 36, no. 13-14, pp. 1455–1473, 2017

    2017