# DLAM: Distributional Latent Actions with Temporal Constraints

arXiv: https://arxiv.org/abs/2607.27138 · HTML: https://mlsanity.com/paper/2607.27138/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Human-video and latent-action pretraining, one of 13 directions in Vision-language-action models.
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- Vision-language-action models / [Human-video and latent-action pretraining](https://mlsanity.com/vla/human-video-and-latent-action-pretraining/)

## Builds on (most cited first, 27 of 27)

- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [Stochastic Video Generation with a Learned Prior](https://mlsanity.com/paper/1802.07687/) (2018)
- [DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge](https://mlsanity.com/paper/2507.04447/) (2025)
- [Prediction with Action: Visual Policy Learning via Joint Denoising Process](https://mlsanity.com/paper/2411.18179/) (2024)
- [Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models](https://mlsanity.com/paper/2606.17846/) (2026)
- [Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments](https://mlsanity.com/paper/2605.30280/) (2026)
- [Meta-World+: An Improved, Standardized, RL Benchmark](https://mlsanity.com/paper/2505.11289/) (2025)
- [CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations](https://mlsanity.com/paper/2505.04999/) (2025)
- [Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment](https://mlsanity.com/paper/2511.04555/) (2025)
- [What Do Latent Action Models Actually Learn?](https://mlsanity.com/paper/2506.15691/) (2025)
- [ABot-M0.5: Unified Mobility-and-Manipulation World Action Model](https://mlsanity.com/paper/2607.00678/) (2026)
- [Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild](https://mlsanity.com/paper/2602.21736/) (2026)
- [RoboTron-Mani: All-in-One Multimodal Large Model for Robotic Manipulation](https://mlsanity.com/paper/2412.07215/) (2024)
- [RotVLA: Rotational Latent Action for Vision-Language-Action Model](https://mlsanity.com/paper/2605.13403/) (2026)
- [Learning Additively Compositional Latent Actions for Embodied AI](https://mlsanity.com/paper/2604.03340/) (2026)
- [One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy](https://mlsanity.com/paper/2605.07931/) (2026)

## Built on by (most cited first, 1 of 1)

- [Algebraic Consistency Alone Does Not Certify Temporal Structure in Latent Action Models](https://mlsanity.com/paper/2609.23478/) (2026)

## Abstract (arXiv)

Vision-language-action (VLA) models remain constrained by scarce action-labeled robot data, whereas action-free videos offer abundant observations of physical change. Latent action models can extract such priors, but reconstruction-trained codes may predict future observations without the structure required for joint generation with robot actions. Existing structured methods add temporal constraints but retain deterministic transition points, so residual errors in locally inferred transitions may propagate and compound under recursive composition. We introduce DLAM, a distributional latent-action model that represents each transition as a diagonal Gaussian. Reconstruction conditioned on the reference frame grounds the mean in observed visual change, while normalized composition and reversal over equal-gap triplets constrain both the mean and dimension-wise variance. Variance composition uses a lightweight shared-correlation coefficient to account for dependence between adjacent transitions that share an intermediate frame, whereas reversal negates the mean and preserves the variance. For downstream policy learning, we freeze the encoder and train a flow-matching policy to jointly generate mean transition sequences and robot actions. On held-out transitions, DLAM learns more temporally consistent latent dynamics than existing latent-action baselines and achieves stronger direct and cumulative reconstruction on held-out videos. Under the same controlled π0 transfer protocol, it also improves policy performance on MetaWorld MT50, LIBERO, and real-world manipulation tasks. Controlled ablations show that normalized mean constraints account for most of the reconstruction gain, while learned variance and correlation-aware composition provide complementary improvements in downstream control.