mlsanityData to 14 Oct 2026

ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation

arXiv 2505.22159 ↗First posted 28 May 2025cs.RO cs.CVcited by 91

On the map: Vision-language-action models → Tactile, force-aware and humanoid VLA

also in 1 more
Abstract (arXiv)

Vision-Language-Action (VLA) models have advanced general-purpose robotic manipulation by leveraging pretrained visual and linguistic representations. However, they struggle with contact-rich tasks that require fine-grained control involving force, especially under visual occlusion or dynamic uncertainty. To address these limitations, we propose ForceVLA, a novel end-to-end manipulation framework that treats external force sensing as a first-class modality within VLA systems. ForceVLA introduces FVLMoE, a force-aware Mixture-of-Experts fusion module that dynamically integrates pretrained visual-language embeddings with real-time 6-axis force feedback during action decoding. This enables context-aware routing across modality-specific experts, enhancing the robot's ability to adapt to subtle contact dynamics. We also introduce ForceVLA-Data, a new dataset comprising synchronized vision, proprioception, and force-torque signals across five contact-rich manipulation tasks. ForceVLA improves average task success by 23.2% over strong pi0-based baselines, achieving up to 80% success in tasks such as plug insertion. Our approach highlights the importance of multimodal integration for dexterous manipulation and sets a new benchmark for physically intelligent robotic control. Code and data will be released at https://sites.google.com/view/forcevla2025.

Key facts. Cited by 91 papers in the map (data through 14 Oct 2026). Placed in Tactile, force-aware and humanoid VLA, one of 13 directions in Vision-language-action models. Builds on 52 of its 57 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

52 of 57 references.

References · 52

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  4. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  6. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  11. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  12. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
38 more
  1. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  2. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  3. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 897
  4. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
  5. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  6. 2021Scaling Vision with Sparse Mixture of Expertscited by 747
  7. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  8. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  9. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  10. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 451
  11. 2022VIMA: General Robot Manipulation with Multimodal Promptscited by 407
  12. 2022ST-MoE: Designing Stable and Transferable Sparse Expert Modelscited by 399
  13. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 283
  14. 2022Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Expertscited by 203
  15. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Controlcited by 195
  16. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 183
  17. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 181
  18. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 113
  19. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Modelscited by 105
  20. 2024Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulationcited by 73
  21. 2024Prediction with Action: Visual Policy Learning via Joint Denoising Processcited by 70
  22. 2025VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulationcited by 55
  23. 2022Factory: Fast Contact for Robotic Assemblycited by 54
  24. 2023IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Realitycited by 53
  25. 2024Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoningcited by 52
  26. 2025VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulationcited by 51
  27. 2025Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructionscited by 51
  28. 2025TLA: Tactile-Language-Action Model for Contact-Rich Manipulationcited by 47
  29. 2025Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Groundingcited by 42
  30. 2024Adaptive Compliance Policy: Learning Approximate Compliance for Diffusion Guided Controlcited by 41
  31. 2024ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulationcited by 36
  32. 2024FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulationcited by 33
  33. 2025MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Modelscited by 27
  34. 2024FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation under Uncertaintycited by 23
  35. 2024TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulationcited by 23
  36. 2023Efficient Sim-to-real Transfer of Contact-Rich Manipulation Skills with Online Admittance Residual Learningcited by 21
  37. 2024Should We Learn Contact-Rich Manipulation Policies from Sampling-Based Planners?cited by 10
  38. 2025Towards Forceful Robotic Foundation Models: a Literature Surveycited by 10

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 16; 2026: 75.

91 papers.

Sort:

By area:

  1. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  2. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 69
  3. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 49
  4. 2025OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensingcited by 38
  5. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thoughtcited by 30
  6. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Modelscited by 28
  7. 2026RLDX-1 Technical Reportcited by 28
  8. 2026From Foundation to Application: Improving VLA Models in Practicecited by 26
  9. 2025When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Modelscited by 20
  10. 2025Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalizationcited by 19
  11. 2026TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulationcited by 19
  12. 2026Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulationcited by 19
38 more
  1. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  2. 2026FD-VLA: Force-Distilled Vision-Language-Action Model for Contact-Rich Manipulationcited by 17
  3. 2026VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAscited by 17
  4. 2026AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robotscited by 16
  5. 2026FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulationcited by 15
  6. 2026TaF-VLA: Tactile-Force Alignment in Vision-Language-Action Models for Force-aware Manipulationcited by 13
  7. 2026T-Rex: Tactile-Reactive Dexterous Manipulationcited by 13
  8. 2025Expertise need not monopolize: Action-Specialized Mixture of Experts for Vision-Language-Action Learningcited by 12
  9. 2026TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulationcited by 11
  10. 2025WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Drivingcited by 10
  11. 2026HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensingcited by 10
  12. 2025ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learningcited by 9
  13. 2026Demystifying Action Space Design for Robotic Manipulation Policiescited by 9
  14. 2026CORAL: Scalable Multi-Task Robot Learning via LoRA Expertscited by 9
  15. 2026AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Modelscited by 9
  16. 2026CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuningcited by 8
  17. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
  18. 2026Cross-Hand Latent Representation for Vision-Language-Action Modelscited by 7
  19. 2026SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reusecited by 5
  20. 2026Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLAcited by 5
  21. 2026ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matchingcited by 5
  22. 2026UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Modelscited by 5
  23. 2026ViTacWorld: Scaling Visuo-Tactile World Models for Contact-Rich Robot Manipulationcited by 5
  24. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challengescited by 4
  25. 2026DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adaptercited by 4
  26. 2026Tactile Modality Fusion for Vision-Language-Action Modelscited by 4
  27. 2026Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Actioncited by 4
  28. 2026TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulationcited by 4
  29. 2026CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Expertscited by 4
  30. 2026Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Modelscited by 3
  31. 2026GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulationcited by 3
  32. 2026FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulationcited by 3
  33. 2026FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learningcited by 2
  34. 2026MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulationcited by 2
  35. 2026Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlationcited by 2
  36. 2026FM-VLA: Force-based Memory for Vision-Language-Action Models in Contact-Rich Manipulationcited by 2
  37. 2026τ: Learning Touch-Augmented Vision-Language-Action Models from Future Visual Supervisioncited by 2
  38. 2026Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Themcited by 2

50 most cited of 91 All 91 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation
  2. 2026DEFT-VLA: Stage-Localized Force Specialization for Contact-Rich Robotic Manipulation ↗
  3. 2026DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation
  4. 2026Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection
  5. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  6. 2025TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models
  7. 2026SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation
  8. 2026Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision