mlsanityData to 14 Oct 2026

EV-WM: Event-Verified World Models for Long-Horizon Robotic Manipulation

arXiv 2606.13053 ↗First posted 11 Jun 2026cs.RO cs.AIcited by 3

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

Abstract (arXiv)

Pretrained-feature world models provide a useful substrate for robot imagination, but visual or latent prediction alone does not determine whether an imagined future satisfies task-relevant predicates. Long-horizon manipulation requires progress signals that are relational, predicate-level, and physically grounded: whether an object has moved, whether a drawer or contact state has changed, whether a placement predicate is satisfied, and whether a candidate future is reliable enough for execution. We introduce EV-WM, a predicate-grounded verification framework for world-model planning. EV-WM rolls out candidate futures in pretrained visual-feature space, decodes them into structured event states, and scores them using task-progress, semantic-consistency, physical-feasibility, and uncertainty terms. The verifier guides sampling-based planning, gates candidate actions, and, in the contact-sensitive LIBERO wine-rack setting, selects among PPO-generated proposals. Across navigation, deformable-object, wall-constrained, and language-described manipulation studies, EV-WM shows that predicate-grounded verification can make feature-space world-model planning more interpretable and better aligned with task progress.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Embodied and robot world models, one of 11 directions in World models. Builds on 29 of its 32 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

29 of 32 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning11 Jun
  2. 2025WorldEval: World Model as Real-World Robot Policies Evaluator25 May
  3. 2024Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination19 Dec
  4. 2024iVideoGPT: Interactive VideoGPTs are Scalable World Models24 May
  5. 2024RoboDreamer: Learning Compositional World Models for Robot Imagination18 Apr
  6. 20243D-VLA: A 3D Vision-Language-Action Generative World Model14 Mar
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 22

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  7. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  8. 2018World Modelscited by 1,513
  9. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  10. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  11. 2023Mastering Diverse Domains through World Modelscited by 1,253
  12. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
10 more
  1. 2020Mastering Atari with Discrete World Modelscited by 1,007
  2. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  3. 2024Genie: Generative Interactive Environmentscited by 747
  4. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  5. 2024Revisiting Feature Prediction for Learning Visual Representations from Videocited by 531
  6. 2022DayDreamer: World Models for Physical Robot Learningcited by 400
  7. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
  8. 2026LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixelscited by 273
  9. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 221
  10. 2022TransDreamer: Reinforcement Learning with Transformer World Modelscited by 143

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perceptioncited by 1
  2. 2026Ontology-Grounded World Models for Failure Diagnosis and Closed-Loop Repair in Physical AI Systemscited by 0
  3. 2026ARS: Agentic Reward System for Robot Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Spatially Grounded Long-Horizon Task Planning in the Wild
  2. 2025Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation
  3. 2026H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model
  4. 2026When to Trust Imagination: Adaptive Action Execution for World Action Models
  5. 2026DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation
  6. 2026Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation
  7. 2026Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation
  8. 2026PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation