mlsanityData to 7 Oct 2026

Hierarchical Latent Action Model

arXiv 2603.05815 ↗First posted 6 Mar 2026cs.ROcited by 6

On the map: World models → Embodied and robot world models

Abstract (arXiv)

Latent Action Models (LAMs) enable learning from actionless data for applications ranging from robotic control to interactive world models. However, existing LAMs typically focus on short-horizon frame transitions and capture low-level motion while overlooking longer-term temporal structure. In contrast, actionless videos often contain temporally extended and high-level skills. We present HiLAM, a hierarchical latent action model that discovers latent skills by modeling long-term temporal information. To capture these dependencies across long horizons, we utilize a pretrained LAM as a low-level extractor. This architecture aggregates latent action sequences, which contain the underlying dynamic patterns of the video, into high-level latent skills. Our experiments demonstrate that HiLAM improves over the baseline and exhibits robust dynamic skill discovery.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Embodied and robot world models, one of 11 directions in World models. Builds on 23 of its 23 references that are in the map. First posted on arXiv 6 Mar 2026.

Builds on

23 of 23 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026Learning Latent Action World Models In The Wild8 Jan
  2. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning11 Jun
  3. 2025AdaWorld: Learning Adaptable World Models with Latent Actions24 Mar
  4. 2023Learning to Act without Actions17 Dec

Other references · 19

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2017Neural Discrete Representation Learningcited by 4,650
  3. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  4. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  5. 2024Genie: Generative Interactive Environmentscited by 706
  6. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  7. 2024Latent Action Pretraining from Videoscited by 302
  8. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  9. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 220
  10. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
  11. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulationcited by 82
  12. 2024BAKU: An Efficient Transformer for Multi-Task Policy Learningcited by 80
7 more
  1. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learningcited by 77
  2. 2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 73
  3. 2023SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Executioncited by 69
  4. 2025Dynamic Chunking for End-to-End Hierarchical Sequence Modelingcited by 65
  5. 2025Latent Action Learning Requires Supervision in the Presence of Distractorscited by 40
  6. 2025CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrationscited by 39
  7. 2025UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representationscited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Modelscited by 3
  2. 2026World-Action Models for Robot Learning and Control: A Surveycited by 1
  3. 2026Latent Actions from Factorized Transition Effects under Agent Ambiguitycited by 0
  4. 2026Orbis 2: A Hierarchical World Model for Drivingcited by 0
  5. 2026From Generation to Simulation: How Far Are World Models from Being True Simulators?cited by 0
  6. 2026WLA3: World Latent Action Modeling for Semantics, Dynamics, and Kinematicscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026What Matters for Latent Actions in Robot Learning
  2. 2026LD4WAM: Learning Latent Dynamics from Human Videos for World Action Models
  3. 2026FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning
  4. 2026DiLA: Disentangled Latent Action World Models
  5. 2026LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
  6. 2026ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation
  7. 2026HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation
  8. 2025Latent Action Pretraining Through World Modeling