mlsanityData to 7 Oct 2026

Sensitivity Shaping for Latent Modeling

arXiv 2606.14585 ↗First posted 12 Jun 2026cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative dynamics models enable planning in challenging systems, but safe deployment requires detecting policy-induced out-of-distribution (OOD) transitions. Existing methods typically treat learned dynamics as fixed and rely on post hoc support surrogates for OOD detection. This overlooks a critical failure mode: learned dynamics that are insensitive to control changes can map unsupported controls to latent predictions resembling demonstrated transitions, suppressing OOD signals despite large prediction errors. We introduce support-conditioned control-sensitivity regularization to preserve control-induced variation by promoting local responsiveness in well-supported training regions. Experiments in vision-based obstacle avoidance, manipulation, and real-robot navigation demonstrate improved OOD detection and safer closed-loop planning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 51 of its 60 references that are in the map. First posted on arXiv 12 Jun 2026.

Builds on

51 of 60 references.

References · 51

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  5. 2018Neural Ordinary Differential Equationscited by 3,733
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  11. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
38 more
  1. 2018World Modelscited by 1,444
  2. 2025DINOv3cited by 1,297
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  4. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  5. 2023Mastering Diverse Domains through World Modelscited by 1,193
  6. 2020Mastering Atari with Discrete World Modelscited by 990
  7. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  8. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  9. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  10. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  11. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  12. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  13. 2020MOReL : Model-Based Offline Reinforcement Learningcited by 582
  14. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  15. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  16. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  17. 2024DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planningcited by 357
  18. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  19. 2019Theoretical Limitations of Self-Attention in Neural Sequence Modelscited by 286
  20. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  21. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  22. 2018Sensitivity and Generalization in Neural Networks: an Empirical Studycited by 187
  23. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 186
  24. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  25. 2025Training Agents Inside of Scalable World Modelscited by 122
  26. 2021Pathdreamer: A World Model for Indoor Navigationcited by 117
  27. 2022Denoising diffusion models for out-of-distribution detectioncited by 102
  28. 2020Objective Mismatch in Model-based Reinforcement Learningcited by 87
  29. 2020Density of States Estimation for Out-of-Distribution Detectioncited by 74
  30. 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulationcited by 74
  31. 2024Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progresscited by 63
  32. 2021Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulationcited by 59
  33. 2023SafeDreamer: Safe Reinforcement Learning with World Modelscited by 50
  34. 2023Model-Based Runtime Monitoring with Interactive Imitation Learningcited by 37
  35. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
  36. 2025Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failurescited by 30
  37. 2018Decoupling Dynamics and Reward for Transfer Learningcited by 23
  38. 2024World Model-based Perception for Visual Legged Locomotioncited by 17

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.