Pith.

Robotics · arXiv:2611.13610 v1 · submitted 10 Nov 2026 · 216 references

From Egocentric Human Video to Robot Manipulation in the Era of Embodied Intelligence

Yi Wang, Jingqiu Wu, Lei Yao, Zhaoshuo Li, Haoyu Zhu, Yirui Zhou, Huaiyuan Xu, Ying Zheng

show 2 more authors

Chuang Yang, Lap-Pui Chau

The paper says

“Egocentric human video (EHV) records close-range hand-object interaction (HOI) and the temporal structure of everyday activities, offering a potentially scalable source of experience for robot manipulation.”

more of the abstract

Using this experience for robot control requires recovering useful supervision without recorded robot actions and accounting for differences in morphology, viewpoint, and action space. We define Ego2Robot learning as the process of learning or adapting robot manipulation policies from EHV, organized into four learning paradigms: explicit embodiment transfer, explicit action and task supervision, egocentric video representation pretraining, and latent action and dynamics modeling. The four paradigms differ in what they derive from human video: robot-format demonstrations, interpretable supervision, visual representations, or predictive models of actions and dynamics. For each paradigm, we trace what EHV information is extracted, how robot policies use it, and when the additional data is required. Besides, we review the benchmark datasets that cover EHV, robot demonstrations, and synthetic and simulated resources. This paper links EHV data's contribution to the task information preserved and the robot-specific grounding used during training or deployment. Finally, we identify challenges in physical feasibility, agent coordination, in-context adaptation, controlled evaluation, and predictive control.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 11 Nov 2026 · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

Holds up. A thorough, well-organized survey that delivers a useful taxonomy for a fast-moving area; the taxonomy is not airtight but the paper is honest about it, and the real value is in the structured comparison and the clear articulation of open challenges. This line is wrong

5 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the 216 references say.

5 minor objections

The paper says, at Section 2.4.3

Pith says: minor objection 1 of 5

The paper acknowledges that the two latent-action and world-action routes can be combined and that many methods blend paradigms, but it would help readers apply the taxonomy consistently if the authors stated explicitly that the four paradigms are not mutually exclusive and that a hybrid method is discussed under the paradigm corresponding to its primary EHV-derived output.

The paper says, at Section 2.1.1, Discussion

Pith says: minor objection 2 of 5

The sentence beginning 'Camera-frameposeaccuracyisinsufficientformotionretargeting' has missing spaces between words; please fix this and scan the manuscript for similar formatting errors.

show 3 more

The paper says, at Table 2 caption

Pith says: minor objection 3 of 5

The modality and annotation icon explanations appear garbled in the provided text, e.g., 'Modality icons denote♂layer-group depth, /adjus◎ monochrome video'; if this is an encoding artifact, it should be corrected in the published version.

The paper says, at Section 2.2.1

Pith says: minor objection 4 of 5

The cross-reference to Section 4.2 for deployment-time use of interaction history is helpful, but 'interaction history' could be defined at first use to avoid ambiguity with the robot's proprioceptive or observation history.

The paper says, at Table 4

Pith says: minor objection 5 of 5

The 'Validation' heading with subcolumns 'Use' and 'Eval.' is somewhat confusing; renaming 'Use' to something like 'Role' or 'Training/Planning/Benchmark use' would clarify the intended distinction.

What would settle it

Select 10 representative methods from the paper (e.g., R3M, LAPA, EgoMimic, Phantom, GR-2, DreamDojo, UniSkill, EgoVLA, MimicPlay, WARPED). For each, have two independent annotators assign it to one of the four paradigms, with the option to mark it as 'hybrid/unclear'. Compute the inter-annotator agreement (Cohen's kappa). If kappa < 0.6, the taxonomy is not reliably applicable, and the paper's main organizational contribution is weakened.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 11 Nov 2026

  1. Reader holds up confidence high
  2. Skeptic agrees 8 s · 46,166 tokens read, 600 written
  3. Editor wrote the verdict above 8 s · 47,008 tokens read, 425 written
  4. Referee minor revision: 5 minor 47 s · 46,511 tokens read, 6,238 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

The paper is a survey that organizes methods for learning robot manipulation from egocentric human video into four paradigms: explicit embodiment transfer, explicit action and task supervision, egocentric video representation pretraining, and latent action and dynamics modeling. The taxonomy is the main contribution, and it is genuinely useful for navigating a messy field. The paper does a good job of tracing what information each paradigm extracts from EHV, how it is grounded, and what additional data is required. The tables comparing datasets are comprehensive and well-structured. The authors are also unusually honest about limitations—they repeatedly note that paradigms overlap, that methods combine elements, and that the taxonomy is not mutually exclusive. They flag this in Section 2.4.3 and elsewhere. The stress-test concern about the taxonomy not being robust is real, but the paper already acknowledges it, and for a survey organizing a rapidly evolving field, a perfectly crisp taxonomy is probably impossible. The real soft spot is that the paper does not provide a systematic way to handle hybrid methods, which limits the taxonomy's utility as a prescriptive tool. But the authors are clear that this is a limitation, and the taxonomy still works well as a descriptive lens. The paper is well-written, the literature coverage is current (through mid-2026), and the open challenges section is thoughtful. It is not a methods paper, so novelty is in the organization and analysis, not in new results. That is fine for a survey. The paper deserves a serious referee and publication. I would cite it for the dataset comparison and the taxonomy framing. It is a solid reference for anyone working in this area.

The strongest objection

The paper's central claim is that the field can be organized into four distinct learning paradigms that differ in what information they extract from EHV and how they ground it in robot capabilities. However, the paper acknowledges in Section 2.4.3 that 'the two routes can be combined' and that 'many methods combine elements from multiple paradigms' (Section 2.4.3). The reader's weakest assumption correctly identifies this: the taxonomy is not robust if methods cannot be cleanly categorized. The paper does not provide a systematic way to handle hybrid methods, and the boundaries between paradigms are fuzzy. For example, latent action learning often uses explicit supervision (e.g., LAPA uses VQ-VAE with reconstruction loss, which is a form of explicit supervision), and representation pretraining is often combined with other paradigms (e.g., R3M uses temporal contrastive learning, which is a form of explicit supervision). If the taxonomy is not robust, the paper's main organizational contribution is weakened. The paper acknowledges this overlap in Section 2.4.3 but does not provide a systematic way to handle hybrid methods. This is a load-bearing concern because the taxonomy is the paper's primary contribution.

The reader's weakest assumption is that the taxonomy is both complete and mutually exclusive, and that the reviewed methods can be cleanly categorized into one paradigm. The paper acknowledges this overlap in Section 2.4.3 but does not provide a systematic way to handle hybrid methods. This is a legitimate concern, but it does not invalidate the paper's contribution. The paper is a survey, and its taxonomy is a useful organizational tool even if it is not perfectly exclusive. The paper acknowledges the limitations and provides a clear discussion of the overlaps. The verdict should remain ACCEPT because the paper substantively advances its field by providing a structured reference that will aid researchers in navigating and comparing approaches. The concern is noted but does not change the overall positive assessment.

The referee's report

If the proposed taxonomy is accepted, this survey provides a genuinely useful organizing framework for a rapidly growing and fragmented literature. The paper's core criterion for the four paradigms—what information is derived from EHV, namely robot-format demonstrations, interpretable supervision, visual representations, or predictive models—is clear, and the paper consistently applies it throughout Sections 2.1-2.4. The survey is unusually careful about scope: it states that mixed-data methods are included only when their EHV use is documented, that inclusion does not imply attribution of gains to EHV, and that foundational or robot-only methods are discussed as context rather than evidence. The comparison with prior surveys in Table 1 and the dataset comparisons in Tables 2-4 are valuable resources. The paper also gives concrete, testable evaluation recommendations, particularly in Section 4.4, such as fixing architecture and training budgets when comparing EHV against non-egocentric video.

Pith's reading of the paper (a machine's summary, not the authors')

Egocentric human video (EHV) is video recorded from a camera worn on a person's head or body, showing their hands interacting with objects. This paper surveys the growing field of using such video to teach robots manipulation skills, without needing to record the robot performing the task first. The authors define Ego2Robot learning and organize existing methods into four paradigms: (1) explicit embodiment transfer, which converts human hand motion into robot action trajectories; (2) explicit action and task supervision, which extracts interpretable signals like affordances or progress estimates; (3) egocentric video representation pretraining, which learns visual features from EHV that can be transferred to robot policies; and (4) latent action and dynamics modeling, which learns hidden action representations or predictive world models from video. The paper also reviews the datasets used for training, including EHV datasets, robot demonstration datasets, and synthetic/simulated resources. It identifies five open challenges: physical feasibility of transferring human motion to robots, agent coordination, in-context adaptation, controlled evaluation, and predictive control. The survey is comprehensive and well-structured, but as a review it does not introduce new experimental results or a unified framework.

Core claim. The paper's central claim is that egocentric human video (EHV) can serve as a scalable source of experience for robot manipulation, and that the field can be organized into four distinct learning paradigms (explicit embodiment transfer, explicit action and task supervision, egocentric video representation pretraining, and latent action and dynamics modeling) that differ in what information they extract from EHV and how they ground it in robot capabilities. The paper asserts that this taxonomy clarifies the requirements and trade-offs of each approach.

The premise it rests on. The paper assumes that the four-paradigm taxonomy is both complete and mutually exclusive, and that the reviewed methods can be cleanly categorized into one paradigm. However, many methods combine elements from multiple paradigms (e.g., latent action learning often uses explicit supervision, and representation pretraining is often combined with other paradigms). The paper acknowledges this overlap in Section 2.4.3 but does not provide a systematic way to handle hybrid methods. If the taxonomy is not robust, the paper's main organizational contribution is weakened.

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Egocentric human video (EHV) records close-range hand-object interaction (HOI) and the temporal structure of everyday activities, offering a potentially scalable source of experience for robot manipulation. Using this experience for robot control requires recovering useful supervision without recorded robot actions and accounting for differences in morphology, viewpoint, and action space. We define Ego2Robot learning as the process of learning or adapting robot manipulation policies from EHV, organized into four learning paradigms: explicit embodiment transfer, explicit action and task supervision, egocentric video representation pretraining, and latent action and dynamics modeling. The four paradigms differ in what they derive from human video: robot-format demonstrations, interpretable supervision, visual representations, or predictive models of actions and dynamics. For each paradigm, we trace what EHV information is extracted, how robot policies use it, and when the additional data is required. Besides, we review the benchmark datasets that cover EHV, robot demonstrations, and synthetic and simulated resources. This paper links EHV data's contribution to the task information preserved and the robot-specific grounding used during training or deployment. Finally, we identify challenges in physical feasibility, agent coordination, in-context adaptation, controlled evaluation, and predictive control.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-11-11

The authors' main claim, as the classifier picked it out 0.76

“This paper links EHV data's contribution to the task information preserved and the robot-specific grounding used during training or deployment.”

How the main claim is stated: asserted 0.99

What the abstract itself states, as probabilities: claims first 0.04 · states limitation 0.52 · human participants 0.25 · controlled comparison 0.04 · randomized assignment 0.01 · states quantitative result 0.02 · compares with prior results 0.05 · mentions code or data availability 0.03

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Egocentric human video (EHV) records close-range hand-object interaction (HOI) and the temporal structure of everyday activities, offering a potentially scalable source of experience for robot manipulation. background 1.00 0.08 0.05 hedged possibility 0.83
Using this experience for robot control requires recovering useful supervision without recorded robot actions and accounting for differences in morphology, viewpoint, and action space. background 0.68 0.06 0.03 asserted 0.98
We define Ego2Robot learning as the process of learning or adapting robot manipulation policies from EHV, organized into four learning paradigms: explicit embodiment transfer, explicit action and task supervision, egocentric video representation pretraining, and latent action and dynamics modeling. contribution 0.95 0.76 0.12 asserted 1.00
The four paradigms differ in what they derive from human video: robot-format demonstrations, interpretable supervision, visual representations, or predictive models of actions and dynamics. contribution 0.55 0.44 0.06 asserted 1.00
For each paradigm, we trace what EHV information is extracted, how robot policies use it, and when the additional data is required. contribution 0.67 0.82 0.04 asserted 0.86
Besides, we review the benchmark datasets that cover EHV, robot demonstrations, and synthetic and simulated resources. contribution 0.88 0.67 0.02 asserted 0.98
This paper links EHV data's contribution to the task information preserved and the robot-specific grounding used during training or deployment. contribution 0.73 0.61 0.26 asserted 0.99
Finally, we identify challenges in physical feasibility, agent coordination, in-context adaptation, controlled evaluation, and predictive control. future work 0.71 0.81 0.16 asserted 0.99

What kind of paper the classifier reports this is: review 1.00 · evidence from literature 0.98

What was examined, and what was not

Sources read

  • arXiv listing abstract v1

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-11: 1 request, 6,284 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (10)
Figure 1 of the paper
Figure 1. Taxonomy of Ego2Robot learning of four learning paradigms with representative methods and supporting data resources. Example images from EgoDex [60], RoboMimic [110], and RoboTurk [109]. and visual representation pretraining [118]. Recently, latent action pretraining derives action-like targets from visual transitions without recorded action labels [189]. We use the term Ego2Robot learning for learning manipulation-relevant knowledge from EHV and grounding it in the capabilities of the target robot. Existing reviews address robot learning from robot demonstrations, general human…
Figure 2 of the paper
Figure 2. Hand pose and HOI reconstruction from EHV. It recovers hand meshes and joints, interaction trajectories, and contact locations for subsequent retargeting. Trajectory colors indicate temporal progression; yellow boxes and markers identify manipulated objects and contacts. Frames from EgoDex [60]; meshes and overlays are schematic. Hand pose reconstruction. Hand pose reconstruction estimates hand joint positions and meshes from monocular images or video frames. Rong et al. [136] introduced FrankMocap for whole-body reconstruction by integrating independently regressed body and hand…
Figure 3 of the paper
Figure 3. Motion retargeting transfers the human motion recovered from EHVs onto the target robot embodiment subject to its joint limits and workspace constraints. Additional contact and dynamics constraints are method-dependent. The mapping is schematic, illustrated with a human grasp frame from EgoDex [60]. The robot overlay is an illustrative composite. Kinematic retargeting. Kinematic methods establish correspondences between human motion and robot configurations through geometric objectives and embodiment-specific constraints. Bharadhwaj et al. [8] map predicted human hand trajectories…
Figure 4 of the paper
Figure 4. Two routes for Ego2Robot video translation: replacement-based editing replaces the human embodiment within the retained scene; rendering-based synthesis reconstructs and re-renders interactions from a target viewpoint. Both video translations produce robot observations with aligned actions for policy learning. Example images from WARPED [44]. Replacement-based video editing. These methods replace the human embodiment with a rendered robot and retain most of the original scene. Phantom [80] estimates hand poses, removes the human arm by inpainting, and overlays a rendered robot to…
Figure 5 of the paper
Figure 5. Human-derived affordances and their three complementary uses: action generation, learning supervision, and policy conditioning. Images from EgoDex [60] and so100_grasp_cup [153]. Affordance grounding for action generation. Predicted affordances can be treated as geometric targets or constraints for grasp synthesis, motion planning, and control. FSAG [55] extracts finger-specific contact regions from human demonstrations and combines them with depth-derived geometry to guide grasp refinement. RoboPCA [175] jointly predicts task-conditioned contact regions and poses, reducing…
Figure 6 of the paper
Figure 6. An illustrative progress estimate for picking up a spoon and holding it beside the tray. Progress ranges from 0 at task initiation to 1 when the spoon is held at the goal. Progress is useful information to support reward construction and execution monitoring. Video frames from EgoVerse [130]. Task-similarity and goal-conditioned rewards. EHV can define the desired behavior or goal against which robot execution is evaluated. In particular, DVD [16] combines human videos with a small amount of robot data to learn whether two videos depict the same task, using this similarity as a…
Figure 7 of the paper
Figure 7. Egocentric video representation pretraining through temporal contrastive learning, masked modeling, and language-conditioned objectives. The transferred encoder supplies features for robot policies and may be frozen or fine-tuned. Human and robot frames are from EgoDex [60] and RH20T [41], respectively. and incidental appearance. The resulting encoder supplies observation features for robot policies rather than explicit action targets. Foundational temporal objectives. Time-Contrastive Networks [143] use synchronized multi-view frames as positive pairs and temporally offset frames…
Figure 8 of the paper
Figure 8. Spatial masked pretraining on EHV frames [58; 133]. The encoder processes visible patches; encoded features and mask tokens enter the decoder to reconstruct masked content. Predictions are compared with ground-truth patches. The encoder transfers to Ego2Robot learning. The decoder is discarded. Video frames are from EgoDex [60]. Spatiotemporal masked prediction. Temporal prediction complements frame-wise reconstruction by making changes across observations part of the learning target. As methodological background, MotionMAE [184] jointly reconstructs masked video content and…
Figure 9 of the paper
Figure 9. Contrastive video-language alignment illustrated with drawer-opening and drawer-closing clips from EPIC￾KITCHENS [34]. Matched video-text pairs are aligned, and mismatched pairs are separated. Text descriptions, similarity scores, and embedding positions are illustrative. For robot control, LIV [104] pretrains on EPIC-KITCHENS using a joint objective that connects visual temporal structure with language and image goals. DecisionNCE [84] likewise uses EPIC-KITCHENS and learns instruction-grounded representations by treating matched video-language trajectories as implicitly preferred…
Figure 10 of the paper
Figure 10. A representative joint video-action architecture conditioned on visual observations and task instructions, with model-dependent robot state or past-action inputs. In the illustrated training setup, EHV supplies predictive supervision and robot demonstrations supply action supervision. Future-observation generation may be omitted at deployment. All video frames are from RH20T [41]. Predictive pretraining and policy learning. Future prediction can provide a learning objective that connects human interaction videos to robot action generation. Wu et al. [171] introduced GR-1, which…

Figures are the authors', reproduced from the paper.

References (216)
  1. [1] AgiBot-World-Contributors, Qingwen Bu, Jisong Cai, Li Chen, Xiuqi Cui, Yan Ding, Siyuan Feng, Shenyuan Gao, Xindong He, Xuan Hu, Xu Huang, Shu Jiang, Yuxin Jiang, Cheng Jing, Hongyang Li, Jialu Li, Chiming Liu, Yi Liu, Yuxiang Lu, Jianlan Luo, Ping Luo, Yao Mu, Yuehan Niu, Yix... on Pith
  2. [2] Arthur Allshire, Himanshu Gaurav Singh, Ritvik Singh, Adam Rashid, Hongsuk Choi, David McAllister, Justin Yu, Yiyuan Chen, Huang Huang, Pieter Abbeel, Xi Chen, Rocky Duan, Phillip Isola, Jitendra Malik, Fred Shentu, Guanya Shi, Philipp Wu, and Angjoo Kanazawa. Scalable Behavio... on PithPith's reviewarXiv
  3. [3] Mido Assran, Adrien Bardes, David Fan, Quentin Garrido, Russell Howes, Mojtaba, Komeili, Matthew Muck- ley, Ammar Rizvi, Claire Roberts, Koustuv Sinha, Artem Zholus, Sergio Arnaud, Abha Gejji, Ada Martin, Francois Robert Hogan, Daniel Dugas, Piotr Bojanowski, Vasil Khalidov, P... on PithPith's reviewarXiv
  4. [4] Jeongmin Bae, Seoha Kim, Marc Pollefeys, Mahdi Rad, Youngjung Uh, and Taein Kwon. Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos, June 2026.http: //arxiv.org/abs/2606.19156. arXiv:2606.19156 [cs.CV] on PithPith's reviewarXiv
  5. [5] Shikhar Bahl, Russell Mendonca, Lili Chen, Unnat Jain, and Deepak Pathak. Affordances from human videos as a versatile representation for robotics. In2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 01–13, 2023. doi: 10.1109/CVPR52729.2023.01324 on Pithdoi:10.1109/cvpr52729.2023.01324
  6. [6] Prithviraj Banerjee, Sindi Shkodrani, Pierre Moulon, Shreyas Hampali, Shangchen Han, Fan Zhang, Linguang Zhang, Jade Fountain, Edward Miller, Selen Basol, Richard Newcombe, Robert Wang, Jakob Julian Engel, and Tomas Hodan. Hot3d: Hand and object tracking in 3d from egocentric ... on Pith
  7. [7] Homanga Bharadhwaj, Abhinav Gupta, and Shubham Tulsiani. Visual affordance prediction for guiding robot exploration. In2023 IEEE International Conference on Robotics and Automation (ICRA), pages 3029–3036, on Pith
  8. [8] Homanga Bharadhwaj, Abhinav Gupta, Shubham Tulsiani, and Vikash Kumar. Zero-Shot Robot Manipulation from Passive Human Videos, February 2023.http://arxiv.org/abs/2302.02011. arXiv:2302.02011 [cs.RO] on PithPith's reviewarXiv
  9. [9] Homanga Bharadhwaj, Roozbeh Mottaghi, Abhinav Gupta, and Shubham Tulsiani. Track2act: Predicting point tracks from internet videos enables generalizable robot manipulation, 2024.https://arxiv.org/abs/2405.01527. 24 on PithPith's reviewarXiv
  10. [10] Jessica Borja-Diaz, Oier Mees, Gabriel Kalweit, Lukas Hermann, Joschka Boedecker, and Wolfram Burgard. Affordance learning from play for sample-efficient policy learning. In2022 International Conference on Robotics and Automation (ICRA), pages 6372–6378, 2022. doi: 10.1109/ICR... on Pithdoi:10.1109/icra46639.2022.9811889
  11. [11] Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Joseph Dabis, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alexander Herzog, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Tomas Jackson, Sally Jesmonth, Nikhil Joshi, Ryan Julian, Dmitry Kalashnik... on Pith
  12. [12] Jake Bruce, Michael Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, Yusuf Aytar, Sarah Bechtle, Feryal Behbahani, Stephanie Chan, Nicolas Heess, Lucy Gonzalez, Simon Osindero, Sherjil Ozair, Sc... on PithPith's reviewarXiv
  13. [13] Qingwen Bu, Yanting Yang, Jisong Cai, Shenyuan Gao, Guanghui Ren, Maoqing Yao, Ping Luo, and Hongyang Li. Univla: Learning to act anywhere with task-centric latent actions, 2025.https://arxiv.org/abs/2505.06111 on PithPith's reviewarXiv
  14. [14] Xiongyi Cai, Ri-Zhao Qiu, Geng Chen, Lai Wei, Isabella Liu, Tianshu Huang, Xuxin Cheng, and Xiaolong Wang. In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data, 2025.https://arxiv.org/abs/ 2511.15704. Version Number: 1 on PitharXiv
  15. [15] Chi-Lam Cheang, Guangzeng Chen, Ya Jing, Tao Kong, Hang Li, Yifeng Li, Yuxiao Liu, Hongtao Wu, Jiafeng Xu, Yichu Yang, Hanbo Zhang, and Minzhao Zhu. GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation, October 2024.http://arxiv.org/ab... on PithPith's reviewarXiv
  16. [17] Cong Chen, Haowen Wang, Zhixiang Zhang, Pei Ren, and Zhengping Che. CAPE: Contrastive Action-conditioned Parallel Encoding for Embodied Planning, June 2026. http://arxiv.org/abs/2606.07304. arXiv:2606.07304 [cs.RO] on PithPith's reviewarXiv
  17. [18] Hanzhi Chen, Boyang Sun, Anran Zhang, Marc Pollefeys, and Stefan Leutenegger. Vidbot: Learning generalizable 3d actions from in-the-wild 2d human videos for zero-shot robotic manipulation, 2025 on Pith
  18. [19] Hongyi Chen, Tony Dong, Tiancheng Wu, Liquan Wang, Yash Jangir, Yaru Niu, Yufei Ye, Homanga Bharadhwaj, Zackory Erickson, and Jeffrey Ichnowski. Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction, 2026.https://arxiv.org/abs/2602.... on PitharXiv
  19. [20] Jialei Chen, Kai Wang, Kang Chen, Shuaihang Chen, Feng Gao, Wenhao Tang, Zhiyuan Li, Weilin Liu, Zhuyu Yao, Boxun Li, Yuanbo Xu, and Chao Yu. Lawam: Latent world action models for efficient dynamics-aware robot policies, 2026.https://arxiv.org/abs/2606.15768 on PithPith's reviewarXiv
  20. [21] Mingjin Chen, Junhao Chen, Zhaoxin Fan, Yujian Lee, Zichen Dang, Lili Wang, Yawen Cui, Lap-Pui Chau, and Yi Wang. Hvg-3d: Bridging real and simulation domains for 3d-conditional hand-object interaction video synthesis. InProceedings of the IEEE/CVF Conference on Computer Visio... on Pith
show 80 more
  1. [22] Siyi Chen, Hugo Hadfield, Alex Zook, Mikaela Angelina Uy, Chan Hee Song, Erwin Coumans, Xuning Yang, Faisal Ladhak, Qing Qu, Stan Birchfield, Jonathan Tremblay, and Valts Blukis. Volo: A physical orchestrator for open-vocabulary long-horizon manipulation, 2026.https://arxiv.or... on PithPith's reviewarXiv
  2. [23] Xiaoyang Chen, Shengcheng Luo, Haoran Guo, Jiaming Jiang, Wanlin Li, Ziyuan Jiao, and Chenxi Xiao. DexMani: Human-DerivedManipulabilityGuidanceforDexterousRotation, August2026. http://arxiv.org/abs/2608.00554. arXiv:2608.00554 [cs.RO] on PithPith's reviewarXiv
  3. [24] Xiaoyu Chen, Junliang Guo, Tianyu He, Chuheng Zhang, Pushi Zhang, Derek Cathera Yang, Li Zhao, and Jiang Bian. IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI, October 2024.http://arxiv.org/abs/2411.00785. arXiv:2411.00785 [cs.RO]. 25 on PithPith's reviewarXiv
  4. [25] Xiaoyu Chen, Hangxing Wei, Pushi Zhang, Chuheng Zhang, Kaixin Wang, Yanjiang Guo, Rushuai Yang, Yucen Wang, Xinquan Xiao, Li Zhao, Jianyu Chen, and Jiang Bian. villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models, September 2025.http://arxiv.org/abs/2507.... on PithPith's reviewarXiv
  5. [26] Yi Chen, Yuying Ge, Weiliang Tang, Yizhuo Li, Yixiao Ge, Mingyu Ding, Ying Shan, and Xihui Liu. Moto: Latent motion token as the bridging language for learning robot manipulation from videos, 2025. https: //arxiv.org/abs/2412.04445 on PitharXiv
  6. [27] Zerui Chen, Shizhe Chen, Etienne Arlaud, Ivan Laptev, and Cordelia Schmid. Vividex: Learning vision-based dexterous manipulation from human videos, 2025 on Pith
  7. [28] Dongzhou Cheng, Taoran Yi, Ye Fang, Xingwu Zhang, Fan Feng, Yixuan Li, Gengxiong Zhuang, Rongze Wang, Shuai Yang, Wei Song, Weizhi Xue, Minyan Wu, Jie Gui, Jiaqi Wang, and Tong Wu. In-context robot learning with vlm agents, 2026.https://arxiv.org/abs/2609.19138 on PithPith's reviewarXiv
  8. [29] Shuo Cheng, Chuye Zhang, Alfred Cueva, Caelan Garrett, Ajay Mandlekar, and Danfei Xu. Human2Any: Human- to-Robot Transfer via Constraint-Aware Compositional Planning, June 2026.http://arxiv.org/abs/2606.28813. arXiv:2606.28813 [cs.RO] on PithPith's reviewarXiv
  9. [30] Jeremy A. Collins, Loránd Cheng, Kunal Aneja, Albert Wilcox, Benjamin Joffe, and Animesh Garg. AM- PLIFY: Actionless Motion Priors for Robot Learning from Videos, June 2025.http://arxiv.org/abs/2506.14198. arXiv:2506.14198 [cs.RO] on PithPith's reviewarXiv
  10. [31] André Correia and Luís A. Alexandre. A survey of demonstration learning, 2024. ISSN 0921-8890.https: //www.sciencedirect.com/science/article/pii/S0921889024001969 on Pith
  11. [32] Weisheng Dai, Kai Lan, Jianyi Zhou, Bo Zhao, Xiu Su, Junwen Tong, Weili Guan, and Shuo Yang. ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation, January 2026. http: //arxiv.org/abs/2602.00557. arXiv:2602.00557 [cs.RO] on PitharXiv
  12. [33] Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michael Wray. The EPIC-KITCHENS Dataset: Collection, ChallengesandBaselines.IEEE Transactions on Pattern Ana... on Pithdoi:10.1109/tpami.2020.2991965.https://doi.ieeecomputersociety
  13. [34] Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Antonino Furnari, Evangelos Kazakos, Jian Ma, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michael Wray. Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100.Internationa... on Pithdoi:10.1007/s11263-021-01531-2
  14. [35] Prithwish Dan, Kushal Kedia, Angela Chao, Edward Weiyi Duan, Maximus Adrian Pace, Wei-Chiu Ma, and Sanjiban Choudhury. X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real, 2025.https://arxiv.org/ abs/2505.07096. Version Number: 5 on PitharXiv
  15. [36] Zibin Dong, Fei Ni, Yifu Yuan, Yinchuan Li, and Jianye Hao. EmbodiedMAE: A Unified 3D Multi-Modal Representation for Robot Manipulation, May 2025.http://arxiv.org/abs/2505.10105. arXiv:2505.10105 [cs.RO] on PithPith's reviewarXiv
  16. [37] Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, and Andrew Zisserman. Temporal cycle-consistency learning. In2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1801–1810, 2019. doi: 10.1109/CVPR.2019.00190 on Pithdoi:10.1109/cvpr.2019.00190
  17. [38] Chrisantus Eze and Christopher Crick. Learning by watching: A review of video-based learning approaches for robot manipulation.IEEE Access, 13:184071–184109, 2025. doi: 10.1109/ACCESS.2025.3624723 on Pithdoi:10.1109/access.2025.3624723
  18. [39] Jiacheng Fan, Zhiyue Zhao, Yiqian Zhang, Chao Chen, Peide Wang, Hengdi Zhang, and Zhengxue Cheng. RoboPaint: From Human Demonstration to Any Robot and Any View, February 2026.http://arxiv.org/abs/ 2602.05325. arXiv:2602.05325 [cs.RO] on PitharXiv
  19. [40] Zicong Fan, Omid Taheri, Dimitrios Tzionas, Muhammed Kocabas, Manuel Kaufmann, Michael J. Black, and Otmar Hilliges. Arctic: A dataset for dexterous bimanual hand-object manipulation. In2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 12943–129... on Pith
  20. [41] Hao-Shu Fang, Hongjie Fang, Zhenyu Tang, Jirong Liu, Chenxi Wang, Junbo Wang, Haoyi Zhu, and Cewu Lu. Rh20t: A comprehensive robotic dataset for learning diverse skills in one-shot. In2024 IEEE International Conference on Robotics and Automation (ICRA), pages 653–660, 2024. do... on Pithdoi:10.1109/icra57147.2024.10611615
  21. [42] Youhe Feng, Hansen Shi, Haoyang Li, Xinlei Guo, Yang Wang, Chengyang Zhang, Jinkai Zhang, Xiaohan Zhang, Jie Tang, and Jing Zhang. ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation, May 2026.http://arxiv.org/abs/2605.08774. arXiv:2605.08774 [cs.RO] on PithPith's reviewarXiv
  22. [43] Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, and Baining Guo. From human videos to robot manipulation: A survey on scalable vision-language-action ... on Pith
  23. [44] Harry Freeman, Chung Hee Kim, and George Kantor. WARPED: Wrist-Aligned Rendering for Robot Policy Learn- ing from Egocentric Human Demonstrations, April 2026.http://arxiv.org/abs/2604.10809. arXiv:2604.10809 [cs.RO] on PithPith's reviewarXiv
  24. [45] Hongming Fu, Wenjia Wang, Xiaozhen Qiao, Rolandos Alexandros Potamias, Taku Komura, Shuo Yang, Zheng Liu, and Bo Zhao. EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos, 2026. https://arxiv.org/abs/2601.01050. Version Number: 2 on PitharXiv
  25. [46] Shenyuan Gao, William Liang, Kaiyuan Zheng, Ayaan Malik, Seonghyeon Ye, Sihyun Yu, Wei-Cheng Tseng, Yuzhu Dong, Kaichun Mo, Chen-Hsuan Lin, Qianli Ma, Seungjun Nah, Loic Magne, Jiannan Xiang, Yuqi Xie, Ruijie Zheng, Dantong Niu, You Liang Tan, K. R. Zentner, George Kurian, Sun... on PithPith's reviewarXiv
  26. [47] Caelan Garrett, Ajay Mandlekar, Bowen Wen, and Dieter Fox. SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment, October 2024. http://arxiv.org/abs/2410.18907. arXiv:2410.18907 [cs.RO] on PithPith's reviewarXiv
  27. [48] Manish Kumar Govind, Dominick Reilly, Pu Wang, and Srijan Das. UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models, April 2026.http://arxiv.org/abs/2602.20231. arXiv:2602.20231 [cs.RO] on PithPith's reviewarXiv
  28. [49] Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski, Joanna Materzynska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag, Florian Hoppe, Christian Thurau, Ingo Bax, and Roland Memisevic. The "something something" video datab... on Pith
  29. [50] Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, San- thosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Meng... on Pith
  30. [51] Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, Triantafyllos Afouras, Kumar Ashutosh, Vijay Baiyya, Siddhant Bansal, Bikram Boote, Eugene Byrne, Zach Chavis, Joya Chen, Feng Cheng, Fu-Jen Chu, Sean Crane, Avijit Dasgupta, Jing Dong, Maria Esc... on Pith
  31. [52] Lingxiao Guo, Huanyu Li, and Guanya Shi. Worlds in One Demo: A Synthetic Data Engine for Learning Open-World Mobile Manipulation, July 2026.http://arxiv.org/abs/2607.13154. arXiv:2607.13154 [cs.RO] on PithPith's reviewarXiv
  32. [53] Songhao Han, Boxiang Qiu, Yue Liao, Siyuan Huang, Chen Gao, Shuicheng Yan, and Si Liu. RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation, October 2025.http://arxiv.org/ abs/2506.06677. arXiv:2506.06677 [cs.RO] on PitharXiv
  33. [54] Yifan Han, Jianxiang Liu, Haoyu Zhang, Yuqi Gu, Yunhan Guo, and Wenzhao Lian. BridgeACT: Bridging Human Demonstrations to Robot Actions via Unified Tool-Target Affordances, May 2026.http://arxiv.org/ abs/2604.23249. arXiv:2604.23249 [cs.RO] on PithPith's reviewarXiv
  34. [55] Yifan Han, Yichuan Peng, Pengfei Yi, Junyan Li, Hanqing Wang, Gaojing Zhang, Qi Peng Liu, and Wenzhao Lian. FSAG: Enhancing Human-to-Dexterous-Hand Finger-Specific Affordance Grounding via Diffusion Models, March 2026.http://arxiv.org/abs/2601.08246. arXiv:2601.08246 [cs.RO] on PitharXiv
  35. [56] Jinkun Hao, Mingda Jia, Ruiyan Wang, Hongrui Zhu, Jiafei Cao, Xihui Liu, Ran Yi, Lizhuang Ma, Jiangmiao Pang, and Xudong Xu. EgoSim: Egocentric World Simulator for Embodied Interaction Generation, July 2026. http://arxiv.org/abs/2604.01001. arXiv:2604.01001 [cs.CV] on PithPith's reviewarXiv
  36. [57] Ryosei Hara, Wataru Ikeda, Masashi Hatano, and Mariko Isogawa. Eventegohands: Event-based egocentric 3d hand mesh reconstruction, 2025 on Pith
  37. [58] Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, and Ross Girshick. Masked autoencoders are scalable vision learners. In2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 15979–15988, 2022. doi: 10.1109/CVPR52688.2022.01553 on Pithdoi:10.1109/cvpr52688.2022.01553
  38. [59] Zeyu He, Yuchang Zhang, Yuanzhen Zhou, Miao Tao, Hengjie Li, Hui Wang, Yang Tian, Jia Zeng, Tai Wang, Wenzhe Cai, Yilun Chen, Ning Gao, and Jiangmiao Pang. Nimbus: A Unified Embodied Synthetic Data Generation Framework, February 2026.http://arxiv.org/abs/2601.21449. arXiv:2601... on PitharXiv
  39. [60] Ryan Hoque, Peide Huang, David J. Yoon, Mouli Sivapurapu, and Jian Zhang. EgoDex: Learning Dexterous Ma- nipulation from Large-Scale Egocentric Video, March 2026.http://arxiv.org/abs/2505.11709. arXiv:2505.11709 [cs.CV] on PithPith's reviewarXiv
  40. [61] Chengkai Hou, Kun Wu, Jiaming Liu, Zhengping Che, Di Wu, Fei Liao, Guangrun Li, Jingyang He, Qiuxuan Feng, Zhao Jin, Chenyang Gu, Zhuoyang Liu, Nuowei Han, Xiangju Mi, Yaoxu Lv, Yankai Fu, Gaole Dai, Langzhe Gu, Tao Li, Yuheng Zhang, Yixue Zhang, Xinhua Wang, Shichao Fan, Meng... on PitharXiv
  41. [62] Qianxi Hua, Xinyue Li, Zheng Yan, Yang Li, Chi Zhang, Yongyao Li, and Yufei Liu. VTouch++: A Multimodal Dataset with Vision-Based Tactile Enhancement for Bimanual Manipulation, April 2026.http://arxiv.org/abs/ 2604.20444. arXiv:2604.20444 [cs.RO] on PithPith's reviewarXiv
  42. [63] Bingjia Huang, Xin Ding, Fu Chen, Kun Li, Wei Sun, Hao Wu, Yunxin Liu, and Ting Cao. Zeva-ego: Egocentric mid-training with in-context causal learning for robot manipulation, 2026.https://arxiv.org/abs/2609.24411 on PithPith's reviewarXiv
  43. [64] Dongchi Huang, Hongyin Zhang, Bohan Hou, Siteng Huang, Zhian Su, Hang Guo, Tong Lu, Zhaofeng Xu, Jiahao Tang, Jianfei Yang, Donglin Wang, Peixi Peng, Mingxiu Chen, Deli Zhao, and Xin Li. RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance, August 2026.htt... on PithPith's reviewarXiv
  44. [65] Tao Huang, Guangqi Jiang, Yanjie Ze, and Huazhe Xu. Diffusion reward: Learning rewards via conditional video diffusion. In Aleš Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and Gül Varol, editors,Computer Vision – ECCV 2024, pages 478–495. Springer N... on Pith
  45. [66] Yifei Huang, Guo Chen, Jilan Xu, Mingfang Zhang, Lijin Yang, Baoqi Pei, Hongjie Zhang, Lu Dong, Yali Wang, Limin Wang, and Yu Qiao. Egoexolearn: A dataset for bridging asynchronous ego- and exo-centric view of procedural activities in real world, 2025.https://arxiv.org/abs/2403.16182 on PithPith's reviewarXiv
  46. [67] Ahad Jawaid and Yu Xiang. OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation, September 2025.http://arxiv.org/abs/2509.05513. arXiv:2509.05513 [cs.CV] on PithPith's reviewarXiv
  47. [68] Tao Jiang, Tianyuan Yuan, Yicheng Liu, Chenhao Lu, Jianning Cui, Xiao Liu, Shuiqi Cheng, Jiyang Gao, Huazhe Xu, and Hang Zhao. Galaxea Open-World Dataset and G0 Dual-System VLA Model, August 2025. http://arxiv.org/abs/2509.00576. arXiv:2509.00576 [cs.RO] on PithPith's reviewarXiv
  48. [69] Yuming Jiang, Siteng Huang, Shengke Xue, Yaxi Zhao, Jun Cen, Sicong Leng, Kehan Li, Jiayan Guo, Kexiang Wang, Mingxiu Chen, Fan Wang, Deli Zhao, and Xin Li. RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation, September 2025.http://arxiv.org/abs/2509.15212. a... on PitharXiv
  49. [70] Siddharth Karamcheti, Suraj Nair, Annie S Chen, Thomas Kollar, Chelsea Finn, Dorsa Sadigh, and Percy Liang. Language-Driven Representation Learning for Robotics. InProceedings of Robotics: Science and Systems, Daegu, Republic of Korea, July 2023. doi: 10.15607/RSS.2023.XIX.032 on Pithdoi:10.15607/rss.2023.xix.032
  50. [71] Simar Kareer, Dhruv Patel, Ryan Punamiya, Pranay Mathur, Shuo Cheng, Chen Wang, Judy Hoffman, and Danfei Xu. Egomimic: Scaling imitation learning via egocentric video, 2025 on Pith
  51. [72] Justin Kerr, Chung Min Kim, Mingxuan Wu, Brent Yi, Qianqian Wang, Ken Goldberg, and Angjoo Kanazawa. Robot see robot do: Imitating articulated object manipulation with monocular 4d reconstruction. 270:587–603, 06–09 Nov 2025.https://proceedings.mlr.press/v270/kerr25a.html on Pith
  52. [73] Alexander Khazatsky, Karl Pertsch, Suraj Nair, Ashwin Balakrishna, Sudeep Dasari, Siddharth Karamcheti, Soroush Nasiriany, Mohan Kumar Srirama, Lawrence Yunliang Chen, Kirsty Ellis, Peter David Fagan, Joey Hejna, Masha Itkina, Marion Lepert, Yecheng Jason Ma, Patrick Tree Mill... on Pith
  53. [74] Hanjung Kim, Jaehyun Kang, Hyolim Kang, Meedeum Cho, Seon Joo Kim, and Youngwoon Lee. UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations, September 2025.http://arxiv.org/abs/ 2505.08787. arXiv:2505.08787 [cs.RO] on PitharXiv
  54. [75] Iaroslav Kolomiets, Miguel Altamirano Cabrera, Artem Lykov, Jeffrin Sam, Dmitrii Iarchuk, Yara Mahmoud, Daniia Zinniatullina, Mikhail Konenkov, and Dzmitry Tsetserukou. AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning... on PithPith's reviewarXiv
  55. [76] Taein Kwon, Bugra Tekin, Jan Stühmer, Federica Bogo, and Marc Pollefeys. H2o: Two hands manipulating objects for first person interaction recognition. In2021 IEEE/CVF International Conference on Computer Vision (ICCV), pages 10118–10128, 2021. doi: 10.1109/ICCV48922.2021.00998 on Pithdoi:10.1109/iccv48922.2021.00998
  56. [77] Yuanchuan Lai, Qing Gao, Ziyan Liang, Junjie Hu, and Zhaojie Ju. ObjRetarget: An Object-Aware Motion Retargeting Framework with Anthropomorphic Arm Constraints and Polyhedral Hand Modeling, July 2026. https://arxiv.org/abs/2607.03828. Version Number: 1. 29 on PithPith's reviewarXiv
  57. [78] Jung Min Lee, Dohyeok Lee, Seokhun Ju, Taehyun Cho, Jin Woo Koo, Li Zhao, Sangwoo Hong, and Jungwoo Lee. MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction, 2026.https: //arxiv.org/abs/2602.03668. Version Number: 3 on PithPith's reviewarXiv
  58. [79] Marion Lepert, Jiaying Fang, and Jeannette Bohg. Masquerade: Learning from In-the-wild Human Videos using Data-Editing, August 2025.http://arxiv.org/abs/2508.09976. arXiv:2508.09976 [cs.RO] on PithPith's reviewarXiv
  59. [80] Marion Lepert, Jiaying Fang, and Jeannette Bohg. Phantom: Training Robots Without Robots Using Only Human Videos, May 2026.http://arxiv.org/abs/2503.00779. arXiv:2503.00779 [cs.RO] on PithPith's reviewarXiv
  60. [81] Dayou Li, Lulin Liu, Bangya Liu, Shijie Zhou, Jiu Feng, Ziqi Lu, Minghui Zheng, Chenyu You, and Zhiwen Fan. Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis, March 2026.http://arxiv.org/ abs/2603.13615. arXiv:2603.13615 [cs.CV] on PitharXiv
  61. [82] Hao Li, Ganlong Zhao, Yufei Liu, Haotian Hou, Guoquan Ye, Tongyan Fang, Chunxiao Liu, Siyuan Huang, Jianbo Liu, Xiaogang Wang, and Hongsheng Li. ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining, June 2026.http://arxiv.org/abs/2606.17200. arXiv:2606.172... on PithPith's reviewarXiv
  62. [83] Hongyu Li, Lingfeng Sun, Yafei Hu, Duy Ta, Jennifer Barry, George Konidaris, and Jiahui Fu. NovaFlow: Zero- Shot Manipulation via Actionable Flow from Generated Videos, October 2025.http://arxiv.org/abs/2510.08568. arXiv:2510.08568 [cs.RO] on PitharXiv
  63. [84] Jianxiong Li, Jinliang Zheng, Yinan Zheng, Liyuan Mao, Xiao Hu, Sijie Cheng, Haoyi Niu, Jihao Liu, Yu Liu, Jingjing Liu, Ya-Qin Zhang, and Xianyuan Zhan. Decisionnce: embodied multimodal representations via implicit preference learning. InProceedings of the 41st International ... on Pith
  64. [85] Junlong Li, Junxi Li, Yuxiang Yang, Wenbin Zou, Lap-Pui Chau, and Yi Wang. Egoprocevqa: A novel egocentric procedural understanding task with self-skill-exploration agent, 2026.https://arxiv.org/abs/2607.13792 on PithPith's reviewarXiv
  65. [86] Qixiu Li, Yu Deng, Yaobo Liang, Lin Luo, Lei Zhou, Chengtang Yao, Lingqi Zeng, Zhiyuan Feng, Huizhi Liang, Sicheng Xu, Yizhong Zhang, Xi Chen, Hao Chen, Lily Sun, Dong Chen, Jiaolong Yang, and Baining Guo. Scalable Vision-Language-Action Model Pretraining for Robotic Manipulat... on PitharXiv
  66. [87] Ruiying Li, Yunlang Zhou, YuYao Zhu, Kylin Chen, Jingyuan Wang, Sukai Wang, Kongtao Hu, Minhui Yu, Bowen Jiang, Zhan Su, Jiayao Ma, Xin He, Yongjian Shen, Yang Yang, Guanghui Ren, Maoqing Yao, Wenhao Wang, and Yao Mu. Roboclaw: An agentic framework for scalable long-horizon ro... on PitharXiv
  67. [88] Yihang Li, Xuelong Wei, Jingzhou Luo, Yingjing Xiao, Yibo Bai, Guangyuan Zhou, Teng Zou, Chenguang Gui, Jiajun Wen, He Zhang, Kangliang Chen, Xing Pan, Shuaiyan Liu, Daming Wang, Tao An, Jiayi Li, Shibo Jin, Wanwan Zhang, Tianyu Wang, Boren Wei, Zhixuan Huang, Fangsheng Liu, R... on PithPith's reviewarXiv
  68. [89] Zishuo Li, Bowen Yang, Changtao Miao, Kai Zhu, Hao Chen, Qingze Guan, Zhengxing Wu, Wanke Zhan, Yang Sun, Zhiyi Huang, Zitong Shan, Zhenchao Jin, Jiadong Hong, Taowen Wang, Yushi Feng, You Liu, Yibo Wang, Yifan Yang, Zhaowen Zhou, Man Luo, Hao Cheng, Bo Zhang, Jianshu Li, Jian... on PithPith's reviewarXiv
  69. [90] Anthony Liang, Yigit Korkmaz, Jiahui Zhang, Minyoung Hwang, Abrar Anwar, Sidhant Kaushik, Aditya Shah, Alex S. Huang, Luke Zettlemoyer, Dieter Fox, Yu Xiang, Anqi Li, Andreea Bobu, Abhishek Gupta, Stephen Tu, Erdem Biyik, and Jesse Zhang. Robometer: Scaling General-Purpose Rob... on Pith
  70. [91] Jongbin Lim, Taeyun Ha, Seongho Cha, Kanghyeon Cho, Mingi Choi, Subin Jeon, Jisoo Kim, Byungjun Kim, and Hanbyul Joo. Hrdexdb: A 4d dexterous grasping dataset across human and multiple robot embodiments, 2026.https://arxiv.org/abs/2604.14944 on PithPith's reviewarXiv
  71. [92] Kevin Qinghong Lin, Alex Jinpeng Wang, Mattia Soldan, Michael Wray, Rui Yan, Eric Zhongcong Xu, Difei Gao, Rongcheng Tu, Wenzhe Zhao, Weijie Kong, Chengfei Cai, Hongfa Wang, Dima Damen, Bernard Ghanem, Wei Liu, and Mike Zheng Shou. Egocentric Video-Language Pretraining, Octobe... on PithPith's reviewarXiv
  72. [93] Litao Liu, Yifan Han, Pengfei Yi, Wenbo Yu, Hanqing Wang, Haoran Du, Enze Yuan, Zilin Yuan, Ruiding Feng, Michael Liu, Qi Zhang, and Jingjin Yu. Affordance2Action: Task-Conditioned Scene-level Affordance Grounding for Real-Time Manipulation, June 2026.http://arxiv.org/abs/2606... on PithPith's reviewarXiv
  73. [94] Yangcen Liu, Shuo Cheng, Xinchen Yin, Woo Chul Shin, Alfred Cueva, Yiran Yang, Zhenyang Chen, Chuye Zhang, and Danfei Xu. EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations, 2026.https://arxiv.org/abs/2606.12604. Version Number: 1 on PithPith's reviewarXiv
  74. [95] Yunze Liu, Yun Liu, Che Jiang, Kangbo Lyu, Weikang Wan, Hao Shen, Boqiang Liang, Zhoujie Fu, He Wang, and Li Yi. Hoi4d: A 4d egocentric dataset for category-level human-object interaction. In2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2098... on Pith
  75. [96] Yunze Liu, Jing Wang, Shenrui Wu, Wenkun He, Guanqi Zhan, Xianzheng Ma, Junyu Chen, Wenhang Ge, Haozhan Tang, Yuchao Gu, Zhuoyang Zhang, Zekai Wang, Dantong Niu, Zhen Dong, Yuke Zhu, Trevor Darrell, Linxi "Jim" Fan, Song Han, and Han Cai. Robota-embed: Unified vla embeddings f... on PithPith's reviewarXiv
  76. [97] Hao Luo, Yicheng Feng, Wanpeng Zhang, Sipeng Zheng, Ye Wang, Haoqi Yuan, Jiazheng Liu, Chaoyi Xu, Qin Jin, and Zongqing Lu. Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos, July 2025.http://arxiv.org/abs/2507.15597. arXiv:2507.15597 [cs.CV] on PithPith's reviewarXiv
  77. [98] Hao Luo, Ye Wang, Wanpeng Zhang, Sipeng Zheng, Ziheng Xi, Chaoyi Xu, Haiweng Xu, Haoqi Yuan, Chi Zhang, Yiqing Wang, Yicheng Feng, and Zongqing Lu. Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization, January 2026.http://arxiv.org/abs/2601.1299... on PitharXiv
  78. [99] Juncheng Ma, Jianxin Bi, Yufan Deng, Xuanran Zhai, Kewei Zhang, Ye Huang, Bo Liang, Shukai Gong, Jiankai Tu, Xiaotian Tang, Jiaxin Li, Kaiqi Chen, Duomin Wang, Yuqi Wang, Bingyi Kang, Eric Huang, Zhiyang Dou, Zhen Dong, Enze Xie, Wojciech Matusik, Tat-Seng Chua, and Daquan Zho... on PithPith's reviewarXiv
  79. [100] Junyi Ma, Wentao Bao, Jingyi Xu, Guanzhong Sun, Yu Zheng, Erhang Zhang, Xieyuanli Chen, and Hesheng Wang. Uni-hand: Universal hand motion forecasting in egocentric views.IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(10):11758–11775, 2026. doi: 10.1109/TPAM... on Pithdoi:10.1109/tpami.2026.3692504
  80. [101] Junyi Ma, Erhang Zhang, Haoran Yang, Ditao Li, Chenyang Xu, Guangming Wang, and Hesheng Wang. Robot Learning from Human Videos: A Survey, 2026.https://arxiv.org/abs/2604.27621. Version Number: 1 on PithPith's reviewarXiv

The first 100 of 216 references are listed here. All of them are in this paper's citation record.

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment