pith. sign in

arxiv: 2607.00678 · v1 · pith:R526GPKWnew · submitted 2026-07-01 · 💻 cs.CV · cs.RO

ABot-M0.5: Unified Mobility-and-Manipulation World Action Model

Ronghan Chen , Yandan Yang , Zuojin Tang , Dongjie Huo , Tong Lin , Haoning Wu , Haoyun Liu , Yuzhi Chen
show 13 more authors
Lulu Zheng Botai Yuan Tianlun Li Mingxin Wang Dekang Qi Bin Hu Wei Mei Yuze Xuan Haolong Yang Yanqing Zhu Mu Xu Zhiheng Ma Xinyuan Chang
This is my paper

Pith reviewed 2026-07-02 14:22 UTC · model grok-4.3

classification 💻 cs.CV cs.RO
keywords world action modelmobile manipulationlatent actionsmixture of transformersdream forcingembodied roboticsinverse dynamics
0
0 comments X

The pith

ABot-M0.5 aligns world action models on temporal granularity, action space, and train-test consistency to handle mobile manipulation.

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

The paper claims that prior world action models fail on mobile manipulation because they use coarse video chunks, entangle navigation and manipulation actions, and train under mismatched conditions. It proposes three targeted alignments to fix this: intermediate latent actions that bridge video and controls, a dual-level transformer architecture that separates modalities and action types, and a dream-forcing strategy that trains on the model's own predictions. These changes are presented as sufficient to capture fine contact dynamics, avoid action conflicts, and limit error buildup in long rollouts. The authors report that the resulting model reaches state-of-the-art success on long-horizon mobile tasks and fine-grained manipulation benchmarks.

Core claim

ABot-M0.5 is a world action model built on the principle that mobile manipulation requires explicit alignment at three levels: temporal granularity via intermediate latent actions that capture local state transitions, action space via a dual-level Mixture-of-Transformers that disentangles modalities and subspaces such as base movement and arm control, and inference consistency via progressive dream-forcing training on model-generated videos. This structure resolves missing contact dynamics, action-distribution conflicts, and error accumulation that arise in earlier coarse or misaligned models.

What carries the argument

The three-level alignment (latent actions for granularity, dual-level Mixture-of-Transformers for action disentanglement, and dream-forcing for train-test match) that bridges video latents to embodiment controls.

If this is right

  • Long-horizon mobile manipulation tasks become solvable with higher success rates than prior world action models.
  • Fine-grained control accuracy improves because latent actions capture contact-level transitions.
  • Autoregressive rollouts accumulate fewer errors once training matches inference conditions.
  • Navigation and manipulation actions can be modeled without distribution conflicts once subspaces are separated.

Where Pith is reading between the lines

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

  • The same alignment pattern could be tested on non-mobile manipulation domains to check whether the three levels remain load-bearing.
  • If dream-forcing reduces error accumulation, similar progressive self-prediction might help other autoregressive world models outside robotics.
  • The dual-level architecture suggests that future models could add more transformer levels for additional action types such as tool use.

Load-bearing premise

The three alignments are enough to fix the contact, conflict, and error problems in earlier world action models.

What would settle it

A controlled ablation that removes one of the three alignments and still matches or exceeds ABot-M0.5 performance on the same long-horizon and fine-grained benchmarks.

read the original abstract

Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typically reactive and lack explicit world modeling, while existing World Action Models (WAMs) are still poorly aligned with the structure of mobile manipulation: they operate on coarse video chunks, model entangled navigation-manipulation actions, and train inverse dynamics under supervision that does not match autoregressive inference. As a result, they often miss fine-grained contact dynamics, suffer from action-distribution conflicts, and accumulate errors over long-horizon rollouts. We propose ABot-M0.5, a new WAM built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency. To align temporal granularity, we introduce intermediate latent actions that capture local visual state transitions and serve as an bridging action space between video latents and embodiment-specific controls. To align action space, we design a dual-level Mixture-of-Transformers architecture that disentangles both modality representations and heterogeneous action subspaces such as base movement and arm manipulation. To align inference conditions, we propose the dream-forcing training strategy that progressively trains inverse dynamics on model-predicted videos, improving train-test alignment and robustness during autoregressive prediction. Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy. These results highlight the critical importance of granularity-aligned, action-disentangled, and inference-consistent world-action modeling.

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

1 major / 0 minor

Summary. The paper proposes ABot-M0.5, a World Action Model for mobile manipulation that addresses limitations in prior VLA policies and WAMs (coarse video chunks, entangled navigation-manipulation actions, and mismatched inverse-dynamics training). It introduces three alignments: temporal granularity via intermediate latent actions bridging video latents and controls; action space via a dual-level Mixture-of-Transformers that disentangles modalities and subspaces (base movement vs. arm manipulation); and train-test consistency via dream-forcing, which trains inverse dynamics on model-predicted videos. The central claim is that these yield state-of-the-art performance on challenging mobile and fine-grained manipulation benchmarks for both long-horizon task success and fine-grained control accuracy.

Significance. If the experimental results hold and the three alignments demonstrably resolve the stated problems of missing contact dynamics, action-distribution conflicts, and error accumulation, the work would represent a meaningful step toward unified world-action modeling for general-purpose robots, with potential impact on long-horizon embodied tasks.

major comments (1)
  1. [Abstract] Abstract: the central SOTA claim for long-horizon task success and fine-grained control accuracy is asserted without any quantitative results, benchmark names, metrics, baselines, error bars, or ablation outcomes visible in the provided text, rendering the claim unverifiable and preventing assessment of whether the three proposed alignments are sufficient.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the detailed review. We address the single major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central SOTA claim for long-horizon task success and fine-grained control accuracy is asserted without any quantitative results, benchmark names, metrics, baselines, error bars, or ablation outcomes visible in the provided text, rendering the claim unverifiable and preventing assessment of whether the three proposed alignments are sufficient.

    Authors: The referee correctly observes that the abstract states the SOTA claim without supporting numbers, benchmark names, or other specifics. While abstracts are conventionally concise, this omission does reduce immediate verifiability. We will revise the abstract to name the primary benchmarks, report the main metrics and improvements over baselines (with reference to the full experimental section for error bars and ablations), and briefly note how the three alignments contribute to the gains. This change will be incorporated in the next manuscript version. revision: yes

Circularity Check

0 steps flagged

No circularity detected; claims rest on empirical benchmarks

full rationale

The paper introduces ABot-M0.5 via three architectural/training alignments (latent actions, dual-level Mixture-of-Transformers, dream-forcing) presented as design choices to address prior WAM limitations. Performance claims are explicitly tied to external benchmark experiments rather than any internal derivation, equation, or self-referential fit. No self-definitional reductions, fitted inputs renamed as predictions, or load-bearing self-citations appear in the abstract or described structure. The chain is self-contained against external evaluation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available, so no concrete free parameters, axioms, or invented entities can be extracted or audited from the manuscript.

pith-pipeline@v0.9.1-grok · 5885 in / 1152 out tokens · 32883 ms · 2026-07-02T14:22:09.571250+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

81 extracted references · 68 canonical work pages · 54 internal anchors

  1. [1]

    AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

    AgiBot-World-Contributors, Qingwen Bu, Jisong Cai, Li Chen, Xiuqi Cui, Yan Ding, Siyuan Feng, Shenyuan Gao, Xindong He, Xuan Hu, et al. Agibot world colosseo: A large-scale manipulation platform for scalable and intelligent embodied systems.arXiv preprint arXiv:2503.06669, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  2. [2]

    Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

    Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. Scheduled sampling for sequence prediction with recurrent neural networks.arXiv preprint arXiv:1506.03099, 2015

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  3. [3]

    Motus: A Unified Latent Action World Model

    Hongzhe Bi, Hengkai Tan, Shenghao Xie, Zeyuan Wang, Shuhe Huang, Haitian Liu, Ruowen Zhao, Yao Feng, Chendong Xiang, Yinze Rong, et al. Motus: A unified latent action world model.arXiv preprint arXiv:2512.13030, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  4. [4]

    $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

    Kevin Black, Noah Brown, Danny Driess, Adnan Esmail, Michael Equi, Chelsea Finn, Niccolo Fusai, Lachy Groom, Karol Hausman, Brian Ichter, et al.π0: A vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  5. [5]

    RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

    Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Xi Chen, Krzysztof Choromanski, Tianli Ding, Danny Driess, Avinava Dubey, Chelsea Finn, et al. Rt-2: Vision-language-action models transfer web knowledge to robotic control.arXiv preprint arXiv:2307.15818, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  6. [6]

    RT-1: Robotics Transformer for Real-World Control at Scale

    Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Joseph Dabis, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, Jasmine Hsu, et al. Rt-1: Robotics transformer for real-world control at scale.arXiv preprint arXiv:2212.06817, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  7. [7]

    Univla: Learning to act anywhere with task-centric latent actions.RSS, 2025

    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.RSS, 2025

    2025

  8. [8]

    WorldVLA: Towards Autoregressive Action World Model

    Jun Cen, Chaohui Yu, Hangjie Yuan, Yuming Jiang, Siteng Huang, Jiayan Guo, Xin Li, Yibing Song, Hao Luo, Fan Wang, et al. Worldvla: Towards autoregressive action world model.arXiv preprint arXiv:2506.21539, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  9. [9]

    RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

    Tianxing Chen, Zanxin Chen, Baijun Chen, Zijian Cai, Yibin Liu, Zixuan Li, Qiwei Liang, Xianliang Lin, Yiheng Ge, Zhenyu Gu, et al. Robotwin 2.0: A scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation.arXiv preprint arXiv:2506.18088, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  10. [10]

    Diffusion policy: Visuomotor policy learning via action diffusion.The International Journal of Robotics Research, 44(10-11):1684–1704, 2025

    Cheng Chi, Zhenjia Xu, Siyuan Feng, Eric Cousineau, Yilun Du, Benjamin Burchfiel, Russ Tedrake, and Shuran Song. Diffusion policy: Visuomotor policy learning via action diffusion.The International Journal of Robotics Research, 44(10-11):1684–1704, 2025

    2025

  11. [11]

    Open X-Embodiment: Robotic Learning Datasets and RT-X Models

    Open X-Embodiment Collaboration. Open x-embodiment: Robotic learning datasets and rt-x models.arXiv preprint arXiv:2310.08864, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  12. [12]

    InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

    InternVLA-M1 Contributors. Internvla-m1: A spatially guided vision-language-action framework for generalist robot policy.arXiv preprint arXiv:2510.13778, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  13. [13]

    Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

    Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, and Cho-Jui Hsieh. Self-forcing++: Towards minute-scale high-quality video generation.arXiv preprint arXiv:2510.02283, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  14. [14]

    FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

    Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, and Christopher Re. Flashattention: Fast and memory-efficient exact attention with io-awareness.arXiv preprint arXiv:2205.14135, 2022

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  15. [15]

    RoboNet: Large-Scale Multi-Robot Learning

    Sudeep Dasari, Frederik Ebert, Stephen Tian, Suraj Nair, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Sergey Levine, and Chelsea Finn. Robonet: Large-scale multi-robot learning.arXiv preprint arXiv:1910.11215, 2020

    work page internal anchor Pith review Pith/arXiv arXiv 1910

  16. [16]

    LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

    Senyu Fei, Siyin Wang, Junhao Shi, Zihao Dai, Jikun Cai, Pengfang Qian, Li Ji, Xinzhe He, Shiduo Zhang, Zhaoye Fei, Jinlan Fu, Jingjing Gong, and Xipeng Qiu. Libero-plus: In-depth robustness analysis of vision-language-action models. arXiv preprint arXiv:2510.13626, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  17. [17]

    Vidar: Embodied Video Diffusion Model for Generalist Manipulation

    Yao Feng, Hengkai Tan, Xinyi Mao, Chendong Xiang, Guodong Liu, Shuhe Huang, Hang Su, and Jun Zhu. Vidar: Embodied video diffusion model for generalist manipulation.arXiv preprint arXiv:2507.12898, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  18. [18]

    Galaxea g0.5 technical report

    Galaxea Team. Galaxea g0.5 technical report. 2026. URLhttps://opengalaxea.github.io/G05/

    2026

  19. [19]

    PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models

    Xinyu Guo, Bin Xie, Wei Chai, Xianchi Deng, Tiancai Wang, Zhengxing Wu, and Xingyu Chen. Priorvla: Prior-preserving adaptation for vision-language-action models.arXiv preprint arXiv:2605.10925, 2026. 29

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  20. [20]

    World Models

    David Ha and Jürgen Schmidhuber. World models.arXiv preprint arXiv:1803.10122, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  21. [21]

    Mastering Diverse Domains through World Models

    Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, and Timothy Lillicrap. Mastering diverse domains through world models. arXiv preprint arXiv:2301.04104, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  22. [22]

    Self forcing: Bridging the train-test gap in autoregressive video diffusion.Advancesin Neural Information Processing Systems, 38:167283–167308, 2026

    Xun Huang, Zhengqi Li, Guande He, Mingyuan Zhou, and Eli Shechtman. Self forcing: Bridging the train-test gap in autoregressive video diffusion.Advancesin Neural Information Processing Systems, 38:167283–167308, 2026

    2026

  23. [23]

    NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks

    Chia-Yu Hung, Qi Sun, Pengfei Hong, Amir Zadeh, Chuan Li, U Tan, Navonil Majumder, Soujanya Poria, et al. Nora: A small open-sourced generalist vision language action model for embodied tasks.arXiv preprint arXiv:2504.19854, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  24. [24]

    ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents

    Dongjie Huo, Haoyun Liu, Guoqing Liu, Dekang Qi, Zhiming Sun, Maoguo Gao, Jianxin He, Yandan Yang, Xinyuan Chang, Feng Xiong, et al. ABot-Claw: A foundation for persistent, cooperative, and self-evolving robotic agents. arXiv preprint arXiv:2604.10096, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  25. [25]

    Oxe-auge: A large-scale robot augmentation of oxe for scaling cross-embodiment policy learning

    Guanhua Ji, Harsha Polavaram, Lawrence Yunliang Chen, Sandeep Bajamahal, Zehan Ma, Simeon Adebola, Chenfeng Xu, and Ken Goldberg. Oxe-auge: A large-scale robot augmentation of oxe for scaling cross-embodiment policy learning. arXiv preprint arXiv:2512.13100, 2025

    work page arXiv 2025

  26. [26]

    Galaxea open-world dataset and g0 dual-system vla model.arXiv preprint arXiv:2509.00576, 2025

    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.arXiv preprint arXiv:2509.00576, 2025

    work page arXiv 2025

  27. [27]

    DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

    Alexander Khazatsky, Karl Pertsch, Suraj Nair, Ashwin Balakrishna, Sudeep Dasari, Siddharth Karamcheti, Soroush Nasiriany, Mohan Kumar Srirama, Lawrence Yunliang Chen, Kirsty Ellis, et al. Droid: A large-scale in-the-wild robot manipulation dataset.arXiv preprint arXiv:2403.12945, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  28. [28]

    RLDX-1 Technical Report

    Dongyoung Kim, Huiwon Jang, Myungkyu Koo, Suhyeok Jang, Taeyoung Kim, Beomjun Kim, Byungjun Yoon, Changsung Jang, Daewon Choi, Dongsu Han, et al. Rldx-1 technical report.arXiv preprint arXiv:2605.03269, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  29. [29]

    OpenVLA: An Open-Source Vision-Language-Action Model

    Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao, Ashwin Balakrishna, Suraj Nair, Rafael Rafailov, Ethan Foster, Grace Lam, Pannag Sanketi, et al. Openvla: An open-source vision-language-action model.arXiv preprint arXiv:2406.09246, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  30. [30]

    Fine-tuning vision-language-action models: Optimizing speed and success

    Moo Jin Kim, Chelsea Finn, and Percy Liang. Fine-tuning vision-language-action models: Optimizing speed and success. RSS, 2025

    2025

  31. [31]

    Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

    Moo Jin Kim, Yihuai Gao, Tsung-Yi Lin, Yen-Chen Lin, Yunhao Ge, Grace Lam, Percy Liang, Shuran Song, Ming-Yu Liu, Chelsea Finn, et al. Cosmos policy: Fine-tuning video models for visuomotor control and planning. arXiv preprint arXiv:2601.16163, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  32. [32]

    BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation

    Chengshu Li, Ruohan Zhang, Josiah Wong, Cem Gokmen, Sanjana Srivastava, Roberto Martin-Martin, Chen Wang, Gabrael Levine, Wensi Ai, Benjamin Martinez, et al. Behavior-1k: A human-centered, embodied ai benchmark with 1,000 everyday activities and realistic simulation.arXiv preprint arXiv:2403.09227, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  33. [33]

    Causal World Modeling for Robot Control

    Lin Li, Qihang Zhang, Yiming Luo, Shuai Yang, Ruilin Wang, Fei Han, Mingrui Yu, Zelin Gao, Nan Xue, Xing Zhu, et al. Causal world modeling for robot control.arXiv preprint arXiv:2601.21998, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  34. [34]

    CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations

    Anthony Liang, Pavel Czempin, Matthew Hong, Yutai Zhou, Erdem Biyik, and Stephen Tu. Clam: Continuous latent action models for robot learning from unlabeled demonstrations.arXiv preprint arXiv:2505.04999, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  35. [35]

    Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

    Zhixuan Liang, Yizhuo Li, Tianshuo Yang, Chengyue Wu, Sitong Mao, Tian Nian, Liuao Pei, Shunbo Zhou, Xiaokang Yang, Jiangmiao Pang, et al. Discrete diffusion vla: Bringing discrete diffusion to action decoding in vision-language-action policies. arXiv preprint arXiv:2508.20072, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  36. [36]

    Holobrain-0 technical report.arXiv preprint arXiv:2602.12062, 2026

    Xuewu Lin, Tianwei Lin, Yun Du, Hongyu Xie, Yiwei Jin, Jiawei Li, Shijie Wu, Qingze Wang, Mengdi Li, Mengao Zhao, et al. Holobrain-0 technical report.arXiv preprint arXiv:2602.12062, 2026

    work page arXiv 2026

  37. [37]

    Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel, and Matt Le. Flow matching for generative modeling. arXiv preprint arXiv:2210.02747, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  38. [38]

    LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

    Bo Liu, Yifeng Zhu, Chongkai Gao, Yihao Feng, Qiang Liu, Yuke Zhu, and Peter Stone. Libero: Benchmarking knowledge transfer for lifelong robot learning.arXiv preprint arXiv:2306.03310, 2023. 30

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  39. [39]

    Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

    Kunhao Liu, Wenbo Hu, Jiale Xu, Ying Shan, and Shijian Lu. Rolling forcing: Autoregressive long video diffusion in real time.arXiv preprint arXiv:2509.25161, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  40. [40]

    Being-h0

    Hao Luo, Ye Wang, Wanpeng Zhang, Sipeng Zheng, Ziheng Xi, Chaoyi Xu, Haiweng Xu, Haoqi Yuan, Chi Zhang, Yiqing Wang, et al. Being-h0. 5: Scaling human-centric robot learning for cross-embodiment generalization.arXiv preprint arXiv:2601.12993, 2026

    work page arXiv 2026

  41. [41]

    Being-H0.7: A Latent World-Action Model from Egocentric Videos

    Hao Luo, Wanpeng Zhang, Yicheng Feng, Sipeng Zheng, Haiweng Xu, Chaoyi Xu, Ziheng Xi, Yuhui Fu, and Zongqing Lu. Being-h0. 7: A latent world-action model from egocentric videos.arXiv preprint arXiv:2605.00078, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  42. [42]

    Coral: Scalable multi-task robot learning via lora experts

    Yuankai Luo, Woping Chen, Tong Liang, and Zhenguo Li. Coral: Scalable multi-task robot learning via lora experts. arXiv preprint arXiv:2603.09298, 2026

    work page arXiv 2026

  43. [43]

    F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

    Qi Lv, Weijie Kong, Hao Li, Jia Zeng, Zherui Qiu, Delin Qu, Haoming Song, Qizhi Chen, Xiang Deng, and Jiangmiao Pang. F1: A vision-language-action model bridging understanding and generation to actions.arXiv preprint arXiv:2509.06951, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  44. [44]

    A survey on vision-language-action models for embodied ai.IEEE Transactionson Neural Networksand Learning Systems, 2026

    Yueen Ma, Zixing Song, Yuzheng Zhuang, Jianye Hao, and Irwin King. A survey on vision-language-action models for embodied ai.IEEE Transactionson Neural Networksand Learning Systems, 2026. doi: 10.1109/TNNLS.2025. 3650584

    work page doi:10.1109/tnnls.2025 2026

  45. [45]

    Robocasa365: A large-scale simulation framework for training and benchmarking generalist robots.arXiv preprint arXiv:2603.04356, 2026

    Soroush Nasiriany, Sepehr Nasiriany, Abhiram Maddukuri, and Yuke Zhu. Robocasa365: A large-scale simulation framework for training and benchmarking generalist robots.arXiv preprint arXiv:2603.04356, 2026

    work page arXiv 2026

  46. [46]

    Elucidating the exposure bias in diffusion models

    Mang Ning, Mingxiao Li, Jianlin Su, Albert Ali Salah, and Itir Onal Ertugrul. Elucidating the exposure bias in diffusion models. InInternational Conference on Learning Representations, volume 2024, pages 15167–15189, 2024

    2024

  47. [47]

    Gr00t n1.5: An improved open foundation model for generalist humanoid robots.https://research

    NVIDIA. Gr00t n1.5: An improved open foundation model for generalist humanoid robots.https://research. nvidia.com/labs/gear/gr00t-n1_5/, 2026

    2026

  48. [48]

    Gr00t n1.6: An improved open foundation model for generalist humanoid robots.https://research

    NVIDIA. Gr00t n1.6: An improved open foundation model for generalist humanoid robots.https://research. nvidia.com/labs/gear/gr00t-n1_6/, 2026

    2026

  49. [49]

    GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

    NVIDIA, Johan Bjorck, Fernando Castañeda, Nikita Cherniadev, Xingye Da, Runyu Ding, Linxi "Jim" Fan, Yu Fang, Dieter Fox, Fengyuan Hu, Spencer Huang, Joel Jang, Zhenyu Jiang, Jan Kautz, Kaushil Kundalia, Lawrence Lao, Zhiqi Li, Zongyu Lin, Kevin Lin, Guilin Liu, Edith Llontop, Loic Magne, Ajay Mandlekar, Avnish Narayan, Soroush Nasiriany, Scott Reed, You ...

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  50. [50]

    mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs

    Jonas Pai, Liam Achenbach, Victoriano Montesinos, Benedek Forrai, Oier Mees, and Elvis Nava. mimic-video: Video-action models for generalizable robot control beyond vlas.arXiv preprint arXiv:2512.15692, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  51. [51]

    AttenA+: Rectifying Action Inequality in Robotic Foundation Models

    Daojie Peng, Fulong Ma, Jiahang Cao, Qiang Zhang, Xupeng Xie, Jian Guo, Ping Luo, Andrew F. Luo, Boyu Zhou, and Jun Ma. Attena+: Rectifying action inequality in robotic foundation models.arXiv preprintarXiv:2605.13548, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  52. [52]

    FAST: Efficient Action Tokenization for Vision-Language-Action Models

    Karl Pertsch, Kyle Stachowicz, Brian Ichter, Danny Driess, Suraj Nair, Quan Vuong, Oier Mees, Chelsea Finn, and Sergey Levine. Fast: Efficient action tokenization for vision-language-action models.arXiv preprint arXiv:2501.09747, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  53. [53]

    $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

    Physical Intelligence, Kevin Black, Noah Brown, James Darpinian, Karan Dhabalia, Danny Driess, Adnan Esmail, Michael Equi, Chelsea Finn, Niccolo Fusai, et al.π0.5: a vision-language-action model with open-world generalization. arXiv preprint arXiv:2504.16054, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  54. [54]

    Physical Intelligence, Bo Ai, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Greg Balke, Kevin Black, George Bokinsky, Shihao Cao, Thomas Charbonnier, et al.π0.7: a steerable generalist robotic foundation model with emergent capabilities.arXiv preprint arXiv:2604.15483, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  55. [55]

    Spatialvla: Exploring spatial representations for visual-language-action model.RSS, 2025

    Delin Qu, Haoming Song, Qizhi Chen, Yuanqi Yao, Xinyi Ye, Yan Ding, Zhigang Wang, JiaYuan Gu, Bin Zhao, Dong Wang, et al. Spatialvla: Exploring spatial representations for visual-language-action model.RSS, 2025. 31

    2025

  56. [56]

    A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

    Stephane Ross, Geoffrey J. Gordon, and J. Andrew Bagnell. A reduction of imitation learning and structured prediction to no-regret online learning.arXiv preprint arXiv:1011.0686, 2011

    work page internal anchor Pith review Pith/arXiv arXiv 2011

  57. [57]

    Generalization in generation: A closer look at exposure bias

    Florian Schmidt. Generalization in generation: A closer look at exposure bias. InProceedings of the 3rd Workshop on Neural Generation and Translation, pages 157–167, 2019

    2019

  58. [58]

    Saivla-0: Cerebrum–pons–cerebellum tripartite architecture for compute-aware vision-language-action.arXiv preprint arXiv:2603.08124, 2026

    Xiang Shi, Wenlong Huang, Menglin Zou, and Xinhai Sun. Saivla-0: Cerebrum–pons–cerebellum tripartite architecture for compute-aware vision-language-action.arXiv preprint arXiv:2603.08124, 2026

    work page arXiv 2026

  59. [59]

    Vla-jepa: Enhancing vision- language-action model with latent world model

    Jingwen Sun, Wenyao Zhang, Zekun Qi, Shaojie Ren, Zezhi Liu, Hanxin Zhu, Guangzhong Sun, Xin Jin, and Zhibo Chen. Vla-jepa: Enhancing vision-language-action model with latent world model.arXiv preprint arXiv:2602.10098, 2026

    work page arXiv 2026

  60. [60]

    Habitat 2.0: Training home assistants to rearrange their habitat

    Andrew Szot, Alex Clegg, Eric Undersander, Erik Wijmans, Yili Zhao, John Turner, Noah Maestre, Mustafa Mukadam, Devendra Chaplot, Oleksandr Maksymets, et al. Habitat 2.0: Training home assistants to rearrange their habitat. arXiv preprint arXiv:2106.14405, 2022

    work page arXiv 2022

  61. [61]

    Interactive Post-Training for Vision-Language-Action Models

    Shuhan Tan, Kairan Dou, Yue Zhao, and Philipp Krähenbühl. Interactive post-training for vision-language-action models. arXiv preprint arXiv:2505.17016, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  62. [62]

    ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models

    Zuojin Tang, Haoyun Liu, Xinyuan Chang, Changjie Wu, Dongjie Huo, Yandan Yang, Bin Liu, Zhejia Cai, Feng Xiong, Mu Xu, et al. Alam: Algebraically consistent latent action model for vision-language-action models.arXiv preprint arXiv:2605.10819, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  63. [63]

    One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy

    Zuojin Tang, Shengchao Yuan, Xiaoxin Bai, Zhiyuan Jing, De Ma, Gang Pan, and Bin Liu. One token per frame: Reconsidering visual bandwidth in world models for vla policy.arXiv preprint arXiv:2605.07931, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  64. [64]

    Interndata-a1: Pioneering high-fidelity synthetic data for pre-training generalist policy.arXiv preprint arXiv:2511.16651, 2025

    Yang Tian, Yuyin Yang, Yiman Xie, Zetao Cai, Xu Shi, Ning Gao, Hangxu Liu, Xuekun Jiang, Zherui Qiu, Feng Yuan, et al. Interndata-a1: Pioneering high-fidelity synthetic data for pre-training generalist policy.arXiv preprint arXiv:2511.16651, 2025

    work page arXiv 2025

  65. [65]

    Bridgedata v2: A dataset for robot learning at scale.arXiv preprint arXiv:2308.12952, 2024

    Homer Walke, Kevin Black, Abraham Lee, Moo Jin Kim, Max Du, Chongyi Zheng, Tony Zhao, Philippe Hansen- Estruch, Quan Vuong, Andre He, et al. Bridgedata v2: A dataset for robot learning at scale.arXiv preprint arXiv:2308.12952, 2024

    work page arXiv 2024

  66. [66]

    Wan: Open and Advanced Large-Scale Video Generative Models

    Team Wan, Ang Wang, Baole Ai, Bin Wen, Chaojie Mao, Chen-Wei Xie, Di Chen, Feiwu Yu, Haiming Zhao, Jianx- iao Yang, et al. Wan: Open and advanced large-scale video generative models.arXiv preprint arXiv:2503.20314, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  67. [67]

    Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

    Qiuyue Wang, Mingsheng Li, Jian Guan, Jinhui Ye, Sicheng Xie, Yitao Liu, Junhao Chen, Zhixuan Liang, Jie Zhang, Xintong Hu, et al. Qwen-vla: Unifying vision-language-action modeling across tasks, environments, and robot embodiments. arXiv preprint arXiv:2605.30280, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  68. [68]

    RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation

    Kun Wu, Chengkai Hou, Jiaming Liu, Zhengping Che, Xiaozhu Ju, Zhuqin Yang, Meng Li, Yinuo Zhao, Zhiyuan Xu, Guang Yang, et al. Robomind: Benchmark on multi-embodiment intelligence normative data for robot manipulation. arXiv preprint arXiv:2412.13877, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  69. [69]

    RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation

    Shihan Wu, Xuecheng Liu, Shaoxuan Xie, Pengwei Wang, Xinghang Li, Bowen Yang, Zhe Li, Kai Zhu, Hongyu Wu, Yiheng Liu, et al. Robocoin: An open-sourced bimanual robotic data collection for integrated manipulation. arXiv preprint arXiv:2511.17441, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  70. [70]

    ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning

    Yandan Yang, Shuang Zeng, Tong Lin, Xinyuan Chang, Dekang Qi, Junjin Xiao, Haoyun Liu, Ronghan Chen, Yuzhi Chen, Dongjie Huo, et al. Abot-m0: Vla foundation model for robotic manipulation with action manifold learning. arXiv preprint arXiv:2602.11236, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  71. [71]

    Gigaworld-policy: An efficient action-centered world–action model.arXiv preprint arXiv:2603.17240, 2026

    Angen Ye, Boyuan Wang, Chaojun Ni, Guan Huang, Guosheng Zhao, Hao Li, Hengtao Li, Jie Li, Jindi Lv, Jingyu Liu, et al. Gigaworld-policy: An efficient action-centered world–action model.arXiv preprint arXiv:2603.17240, 2026

    work page arXiv 2026

  72. [72]

    Latent Action Pretraining from Videos

    Seonghyeon Ye, Joel Jang, Byeongguk Jeon, Sejune Joo, Jianwei Yang, Baolin Peng, Ajay Mandlekar, Reuben Tan, Yu-Wei Chao, Bill Yuchen Lin, et al. Latent action pretraining from videos.arXiv preprint arXiv:2410.11758, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  73. [73]

    World Action Models are Zero-shot Policies

    Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng, Shenyuan Gao, Sihyun Yu, George Kurian, Suneel Indupuru, You Liang Tan, Chuning Zhu, Jiannan Xiang, et al. World action models are zero-shot policies.arXiv preprint arXiv:2602.15922, 2026. 32

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  74. [74]

    Homerobot: Open-vocabulary mobile manipulation

    Sriram Yenamandra, Arun Ramachandran, Karmesh Yadav, Austin Wang, Mukul Khanna, Theophile Gervet, Tsung-Yen Yang, Vidhi Jain, Alexander William Clegg, John Turner, et al. Homerobot: Open-vocabulary mobile manipulation. arXiv preprint arXiv:2306.11565, 2024

    work page arXiv 2024

  75. [75]

    Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

    Haoqi Yuan, Zhixuan Liang, Anzhe Chen, Ye Wang, Haoyang Li, Pei Lin, Yiyang Huang, Zixing Lei, Tong Zhang, Jiazhao Zhang, et al. Qwen-robotmanip technical report: Alignment unlocks scale for robotic manipulation foundation models. arXiv preprint arXiv:2606.17846, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  76. [76]

    Fast-WAM: Do World Action Models Need Test-time Future Imagination?

    Tianyuan Yuan, Zibin Dong, Yicheng Liu, and Hang Zhao. Fast-wam: Do world action models need test-time future imagination? arXiv preprint arXiv:2603.16666, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  77. [77]

    ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

    Yuyang Zhang, Wenyao Zhang, Zekun Qi, He Zhang, Haitao Lin, Jingbo Zhang, Yao Mu, Xiaokang Yang, Wenjun Zeng, and Xin Jin. Imagewam: Do world action models really need video generation, or just image editing?arXiv preprint arXiv:2606.19531, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  78. [78]

    Cot-vla: Visual chain-of-thought reasoning for vision-language-action models

    Qingqing Zhao, Yao Lu, Moo Jin Kim, Zipeng Fu, Zhuoyang Zhang, Yecheng Wu, Zhaoshuo Li, Qianli Ma, Song Han, Chelsea Finn, et al. Cot-vla: Visual chain-of-thought reasoning for vision-language-action models. InCVPR, 2025

    2025

  79. [79]

    X-vla: Soft-prompted transformer as scalable cross-embodiment vision-language-action model

    Jinliang Zheng, Jianxiong Li, Zhihao Wang, Dongxiu Liu, Xirui Kang, Yuchun Feng, Yinan Zheng, Jiayin Zou, Yilun Chen, Jia Zeng, et al. X-vla: Soft-prompted transformer as scalable cross-embodiment vision-language-action model. ICLR, 2025

    2025

  80. [80]

    Acot-vla: Action chain-of-thought for vision-language-action models

    Linqing Zhong, Yi Liu, Yifei Wei, Ziyu Xiong, Si Liu, and Guanghui Ren. Acot-vla: Action chain-of-thought for vision-language-action models. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8152–8162, 2026

    2026

Showing first 80 references.