# CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning

arXiv: https://arxiv.org/abs/2505.17006 · HTML: https://mlsanity.com/paper/2505.17006/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 80 of its 100 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 30 of 80)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)

## Built on by (most cited first, 30 of 40)

- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos](https://mlsanity.com/paper/2602.06949/) (2026)
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization](https://mlsanity.com/paper/2601.12993/) (2026)
- [villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models](https://mlsanity.com/paper/2507.23682/) (2025)
- [LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies](https://mlsanity.com/paper/2606.15768/) (2026)
- [Learning Latent Action World Models In The Wild](https://mlsanity.com/paper/2601.05230/) (2026)
- [World Guidance: World Modeling in Condition Space for Action Generation](https://mlsanity.com/paper/2602.22010/) (2026)
- [MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models](https://mlsanity.com/paper/2510.19022/) (2025)
- [ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation](https://mlsanity.com/paper/2602.00557/) (2026)
- [LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment](https://mlsanity.com/paper/2604.11689/) (2026)
- [StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation](https://mlsanity.com/paper/2510.05057/) (2025)
- [Olaf-World: Orienting Latent Actions for Video World Modeling](https://mlsanity.com/paper/2602.10104/) (2026)
- [DiLA: Disentangled Latent Action World Models](https://mlsanity.com/paper/2605.15725/) (2026)
- [RotVLA: Rotational Latent Action for Vision-Language-Action Model](https://mlsanity.com/paper/2605.13403/) (2026)
- [Cross-Hand Latent Representation for Vision-Language-Action Models](https://mlsanity.com/paper/2603.10158/) (2026)
- [Learning Additively Compositional Latent Actions for Embodied AI](https://mlsanity.com/paper/2604.03340/) (2026)
- [NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces](https://mlsanity.com/paper/2510.03895/) (2025)
- [GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert](https://mlsanity.com/paper/2510.03896/) (2025)
- [What Matters for Latent Actions in Robot Learning](https://mlsanity.com/paper/2608.19613/) (2026)
- [CARE: Multi-Task Pretraining for Latent Continuous Action Representation in Robot Control](https://mlsanity.com/paper/2601.22467/) (2026)
- [Vision-Language Models Unlock Task-Centric Latent Actions](https://mlsanity.com/paper/2601.22714/) (2026)
- [10 Open Challenges Steering the Future of Vision-Language-Action Models](https://mlsanity.com/paper/2511.05936/) (2025)
- [CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation](https://mlsanity.com/paper/2601.23087/) (2026)
- [From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation](https://mlsanity.com/paper/2605.12167/) (2026)
- [Why Latent Actions Fail, and How to Prevent It](https://mlsanity.com/paper/2605.20223/) (2026)
- [LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching](https://mlsanity.com/paper/2606.10517/) (2026)
- [ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow](https://mlsanity.com/paper/2607.28362/) (2026)
- [LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models](https://mlsanity.com/paper/2608.05706/) (2026)

## Abstract (arXiv)

Unsupervised learning of latent motion from Internet videos is crucial for robot learning. Existing discrete methods generally mitigate the shortcut learning caused by extracting excessive static backgrounds through vector quantization with a small codebook size. However, they suffer from information loss and struggle to capture more complex and fine-grained dynamics. Moreover, there is an inherent gap between the distribution of discrete latent motion and continuous robot action, which hinders the joint learning of a unified policy. We propose CoMo, which aims to learn more precise continuous latent motion from internet-scale videos. CoMo employs an early temporal difference (Td) mechanism to increase the shortcut learning difficulty and explicitly enhance motion cues. Additionally, to ensure latent motion better captures meaningful foregrounds, we further propose a temporal contrastive learning (Tcl) scheme. Specifically, positive pairs are constructed with a small future frame temporal offset, while negative pairs are formed by directly reversing the temporal direction. The proposed Td and Tcl work synergistically and effectively ensure that the latent motion focuses better on the foreground and reinforces motion cues. Critically, CoMo exhibits strong zeroshot generalization, enabling it to generate effective pseudo action labels for unseen videos. Extensive simulated and real-world experiments show that policies co-trained with CoMo pseudo action labels achieve superior performance with both diffusion and auto-regressive architectures.