mlsanityData to 13 Oct 2026

UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation

arXiv 2606.31451 ↗First posted 30 Jun 2026cs.RO cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Unified multimodal models (UMMs) have shown great promise in integrating understanding and generation across diverse modalities. However, existing research rarely extends this paradigm to the tactile domain, where both object-level semantics and sensor-level configurations jointly determine the meaning of touch. To address this gap, we propose UniTac, the first UMM designed for tactile understanding and generation. UniTac models the tactile process as a transition from non-contact to contact, capturing the physical interaction between sensors and objects through a dual-level representation that encodes both sensor and object attributes. For tactile understanding, UniTac introduces two tasks, object property description and sensor identification, to enhance reasoning over physical and cross-sensor information. For tactile generation, we design a two-stage training paradigm consisting of reconstruction and alignment, together with a sensor-prior-based sampling strategy that simulates realistic tactile contact. Trained on large-scale multi-sensor datasets, UniTac achieves state-of-the-art performance in tactile understanding and generates realistic tactile signals across sensors.

Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 42 of its 51 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

42 of 51 references.

References · 42

  1. 2022Classifier-Free Diffusion Guidancecited by 5,785
  2. 2022Flow Matching for Generative Modelingcited by 5,542
  3. 2025Qwen2.5-VL Technical Reportcited by 5,499
  4. 2024GPT-4o System Cardcited by 4,536
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,191
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,130
  7. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,714
  8. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,692
  9. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,610
  10. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,699
  11. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 913
  12. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 859
30 more
  1. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 799
  2. 2024Emu3: Next-Token Prediction is All You Needcited by 768
  3. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 740
  4. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 475
  5. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Datasetcited by 368
  6. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 339
  7. 2024TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generationcited by 200
  8. 2020DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulationcited by 165
  9. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 162
  10. 2024Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTcited by 130
  11. 2024LMFusion: Adapting Pretrained Language Models for Multimodal Generationcited by 120
  12. 2024Binding Touch to Everything: Learning Unified Multimodal Tactile Representationscited by 95
  13. 2022Touch and Go: Learning from Human-Collected Vision and Touchcited by 86
  14. 2024A Touch, Vision, and Language Dataset for Multimodal Alignmentcited by 69
  15. 2019Connecting Touch and Vision via Cross-Modal Predictioncited by 66
  16. 2025VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulationcited by 55
  17. 2025AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensorscited by 48
  18. 2024Octopi: Object Property Reasoning with Large Tactile-Language Modelscited by 47
  19. 2024OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flowscited by 46
  20. 2022Self-Supervised Visuo-Tactile Pretraining to Locate and Follow Garment Featurescited by 38
  21. 2025OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensingcited by 38
  22. 2024Touch100k: A Large-Scale Touch-Language-Vision Dataset for Touch-Centric Multimodal Representationcited by 27
  23. 2023Generating Visual Scenes from Touchcited by 26
  24. 2024Tactile-Augmented Radiance Fieldscited by 26
  25. 2024TextToucher: Fine-Grained Text-to-Touch Generationcited by 11
  26. 2025Universal Visuo-Tactile Video Understanding for Embodied Interactioncited by 8
  27. 2024Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generationcited by 6
  28. 2024Touch2Touch: Cross-Modal Tactile Generation for Object Manipulationcited by 5
  29. 2025CLTP: Contrastive Language-Tactile Pre-training for 3D Contact Geometry Understandingcited by 5
  30. 2025SToLa: Self-Adaptive Touch-Language Framework with Tactile Commonsense Reasoning in Open-Ended Scenarioscited by 3

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Cloudscited by 1
  2. 2026VT-MUSE: Multimodal Unified Sequential Visuotactile Representation Learning for Manipulationcited by 0
  3. 2026From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentationcited by 0
  4. 2026ROMA: LLM System for Real-World Object-Centric Multi-Sensory Active Perceptioncited by 0