mlsanityData to 7 Oct 2026

Tactile, force-aware and humanoid VLA

50 papers1 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: tactile, contact-rich, force, manipulation, vla

Key facts. Tactile, force-aware and humanoid VLA: 50 papers on arXiv since 2025 (data through 7 Oct 2026). 24 of its 50 mapped papers (48%) cite “ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation” (2025, arXiv 2505.22159). 18 of its 50 mapped papers (36%) cite “Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization” (2025, arXiv 2507.09160). 11 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

11 new papers, 17 Sep – 7 Oct; 1 this week.

  1. This week · 1
  2. MIM-VLA: Learning Physical Interaction Representations from Gripper Motor Feedback
  3. Earlier · 10
  4. AgenticTactileVLA: Contact-Guided Execution-Time Supervision for Generalizable Dexterous Manipulation without VLA Retraining
  5. ManiPhysicsBench: Physics-Based Assessment of Object Preservation in VLA Manipulation
  6. SimpleTouch: Can Vision-Language-Action Models Master Contact-Rich Manipulation Without Tactile Policy Pretraining?
  7. Uni-VLaT: Whole-Body Tactile Adaptation of VLA Policies for Humanoid Loco-Manipulation
  8. RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation also fits: Efficient VLA inference and adaptation
  9. Humanoid Loco-Manipulation With Discrete VLA Model also fits: Human-video and latent-action pretraining
  10. Opt2VLA: Force-Aware Vision-Language-Action for Contact-Rich Humanoid Whole-Body Manipulation
  11. CompVLA: A Variable Compliance Vision-Language-Action Model for Contact-rich Manipulation
  12. VT-Bridge: Bridging Pretrained Foundation VLAs to VTLAs via Lightweight Residual Adaptation
All 11
  1. ForeTac-VLA: A Forecasting-Based Tactile-Vision-Language-Action Model for Contact-Rich Robotic Manipulation

Foundations

Most cited by papers here

  1. ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation2025cited by 24 here
  2. Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization2025cited by 18 here
  3. VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedback2025cited by 12 here
  4. OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensing2025cited by 11 here
  5. TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models2025cited by 9 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 35 here
  2. 2024Octo: An Open-Source Generalist Robot Policycited by 25 here
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 42 here
  4. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 7 here
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 38 here
  6. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 6 here
  7. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Controlcited by 7 here
  8. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 39 here
  9. 2025ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulationcited by 24 here
  10. 2025Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalizationcited by 18 here
  11. 2025OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensingcited by 11 here
  12. 2025Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulationcited by 5 here
12 more it builds on, not in this chain
  1. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 8 here
  2. 2025Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Groundingcited by 11 here
  3. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 8 here
  4. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 7 here
  5. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 5 here
  6. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 8 here
  7. 2025LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instructioncited by 6 here
  8. 2025VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedbackcited by 12 here
  9. 2025TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Modelscited by 9 here
  10. 2025MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulationcited by 6 here
  11. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 6 here
  12. 2025π*0.6: a VLA That Learns From Experiencecited by 6 here

The 24 most cited of 163.

Browse

30 of 50, ranked 6–35

  1. 6LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction20256
  2. 7FD-VLA: Force-Distilled Vision-Language-Action Model for Contact-Rich Manipulation20265
  3. 8FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulation20265
  4. 9TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulation20265
  5. 10Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulation20255
  6. 11TaF-VLA: Tactile-Force Alignment in Vision-Language-Action Models for Force-aware Manipulation20263
  7. 12HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensing20263
  8. 13AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models20263
  9. 14CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuning20262
  10. 15TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation20261
All 30
  1. 16TacCoRL: Integrating Tactile Feedback into VLA via Simulation20261
  2. 17T-Rex: Tactile-Reactive Dexterous Manipulation20261
  3. 18Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection20261
  4. 19FM-VLA: Force-based Memory for Vision-Language-Action Models in Contact-Rich Manipulation20261
  5. 20TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning20251
  6. 21CLAW: A Vision-Language-Action Framework for Weight-Aware Robotic Grasping20251
  7. 22PhysiFlow: Physics-Aware Humanoid Whole-Body VLA via Multi-Brain Latent Flow Matching and Robust Tracking20260
  8. 23Tactile Modality Fusion for Vision-Language-Action Models20260
  9. 24HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation20260
  10. 25AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models20260
  11. 26Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models20260
  12. 27Phone2Act: A Low-Cost, Hardware-Agnostic Teleoperation System for Scalable VLA Data Collection20260
  13. 28VILAS: A VLA-Integrated Low-cost Architecture with Soft Grasping for Robotic Manipulation20260
  14. 29Mag-VLA: Vision-Language-Action Model for Bimanual Magnetically Actuated Microrobot Manipulation20260
  15. 30PaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation20260
  16. 31LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World20260
  17. 32PhysVLA: Towards Physically-Grounded VLA for Embodied Robotic Manipulation20260
  18. 33ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning20260
  19. 34OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation20260
  20. 35WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning20260