mlsanityData to 14 Oct 2026

FLARE: Robot Learning with Implicit World Modeling

arXiv 2505.15659 ↗First posted 21 May 2025cs.RO cs.LGcited by 113

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

also in 1 more
Abstract (arXiv)

We introduce Future LAtent REpresentation Alignment (FLARE), a novel framework that integrates predictive latent world modeling into robot policy learning. By aligning features from a diffusion transformer with latent embeddings of future observations, FLARE enables a diffusion transformer policy to anticipate latent representations of future observations, allowing it to reason about long-term consequences while generating actions. Remarkably lightweight, FLARE requires only minimal architectural modifications -- adding a few tokens to standard vision-language-action (VLA) models -- yet delivers substantial performance gains. Across two challenging multitask simulation imitation learning benchmarks spanning single-arm and humanoid tabletop manipulation, FLARE achieves state-of-the-art performance, outperforming prior policy learning baselines by up to 26%. Moreover, FLARE unlocks the ability to co-train with human egocentric video demonstrations without action labels, significantly boosting policy generalization to a novel object with unseen geometry with as few as a single robot demonstration. Our results establish FLARE as a general and scalable approach for combining implicit world modeling with high-frequency robotic control.

Key facts. Cited by 113 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 65 of its 67 references that are in the map. First posted on arXiv 21 May 2025.

Builds on

65 of 67 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets3 Apr
  2. 20243D-VLA: A 3D Vision-Language-Action Generative World Model14 Mar
  3. 2023Learning to Act without Actions17 Dec
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 61

  1. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  2. 2022Scalable Diffusion Models with Transformerscited by 6,054
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  5. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  8. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  9. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  10. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  11. 2020Mastering Atari with Discrete World Modelscited by 1,007
  12. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
38 more
  1. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 862
  2. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  3. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  4. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
  5. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  6. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  7. 2023Learning Universal Policies via Text-Guided Video Generationcited by 522
  8. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 451
  9. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 407
  10. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 405
  11. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  12. 2024DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planningcited by 386
  13. 2023An Embodied Generalist Agent in 3D Worldcited by 365
  14. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 364
  15. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 349
  16. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 339
  17. 2024Latent Action Pretraining from Videoscited by 321
  18. 2020Data-Efficient Reinforcement Learning with Self-Predictive Representationscited by 318
  19. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 304
  20. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 296
  21. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 226
  22. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 223
  23. 2023Any-point Trajectory Modeling for Policy Learningcited by 215
  24. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 206
  25. 2025Unified Video Action Modelcited by 205
  26. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 169
  27. 2023Video Language Planningcited by 162
  28. 2025Seedream 3.0 Technical Reportcited by 154
  29. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 139
  30. 2022VideoDex: Learning Dexterity from Internet Videoscited by 106
  31. 2021Pretraining Representations for Data-Efficient Reinforcement Learningcited by 105
  32. 2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learningcited by 75
  33. 2023MUTEX: Learning Unified Policies from Multimodal Task Specificationscited by 70
  34. 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Modelscited by 70
  35. 2024Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videoscited by 69
  36. 2023TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learningcited by 57
  37. 2023Zero-Shot Robot Manipulation from Passive Human Videoscited by 51
  38. 2024Vision-based Manipulation from Single Human Video with Open-World Object Graphscited by 50

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 17; 2026: 96.

113 papers.

Sort:

By area:

  1. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 809
  2. 2026World Action Models are Zero-shot Policiescited by 465
  3. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 300
  4. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
  5. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulationcited by 167
  6. 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videoscited by 135
  7. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 112
  8. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  9. 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulationcited by 82
  10. 2026DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Controlcited by 76
  11. 2025RynnVLA-002: A Unified Vision-Language-Action and World Modelcited by 74
  12. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 70
38 more
  1. 2025A Comprehensive Survey on World Models for Embodied AIcited by 68
  2. 2026LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policiescited by 52
  3. 2026World Action Models: The Next Frontier in Embodied AIcited by 50
  4. 2026World Model for Robot Learning: A Comprehensive Surveycited by 46
  5. 2025Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Modelcited by 36
  6. 2026Interactive World Simulator for Robot Policy Training and Evaluationcited by 31
  7. 2025NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewardscited by 26
  8. 2026MultiWorld: Scalable Multi-Agent Multi-View Video World Modelscited by 23
  9. 2026LIBERO-X: Robustness Litmus for Vision-Language-Action Modelscited by 22
  10. 2026FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignmentcited by 19
  11. 2026DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLAcited by 19
  12. 2026World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetrycited by 18
  13. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  14. 2025Contrastive Representation Regularization for Vision-Language-Action Modelscited by 17
  15. 2026MaskWAM: Unifying Mask Prompting and Prediction for World-Action Modelscited by 16
  16. 2026Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wildcited by 15
  17. 2026JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modelingcited by 15
  18. 2026VideoWorld 2: Learning Transferable Knowledge from Real-world Videoscited by 12
  19. 2026World Action Models: A Surveycited by 12
  20. 2026Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playingcited by 11
  21. 2026LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Priorcited by 11
  22. 2026Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Modelscited by 11
  23. 2026Making Foresight Actionable: Repurposing Representation Alignment in World Action Modelscited by 11
  24. 2026Geometric Action Model for Robot Policy Learningcited by 11
  25. 2026UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modelingcited by 10
  26. 2026HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Modelscited by 10
  27. 2026ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretrainingcited by 10
  28. 2026Kairos: A Regret-Aware Native World-Action Model Stack for Physical AIcited by 9
  29. 2026LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulationcited by 9
  30. 2026World2Act: Latent Action Post-Training from World Model Dynamicscited by 8
  31. 2026Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulationcited by 7
  32. 2025Towards High-Consistency Embodied World Model with Multi-View Trajectory Videoscited by 6
  33. 2026AoE: Always-on Egocentric Human Video Collection for Embodied AIcited by 5
  34. 2026Veo-Act: Enhancing VLA Policies with Frontier Video Modelscited by 5
  35. 2026AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignmentcited by 5
  36. 2026LARA: Latent Action Representation Alignment for Vision-Language-Action Modelscited by 5
  37. 2026Spatially Aware World Action Model via Geometric Latent Diffusioncited by 5
  38. 2026Self-Correcting VLA: Online Action Refinement via Sparse World Imaginationcited by 4

50 most cited of 113 All 113 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments
  2. 2024FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning
  3. 2025LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation
  4. 2026XPACE: Joint World and Action Modeling from Heterogeneous Experience
  5. 2026Copper-Policy: Focus on the Representation for Robust Robot Manipulation
  6. 2024Prediction with Action: Visual Policy Learning via Joint Denoising Process
  7. 2026ω-EVA: Envision, Verify, and Act with Latent Interactive World Models
  8. 2024IRASim: A Fine-Grained World Model for Robot Manipulation