# Adaptive Visuo-Tactile Fusion with Predictive Force Attention for Dexterous Manipulation

arXiv: https://arxiv.org/abs/2505.13982 · HTML: https://mlsanity.com/paper/2505.13982/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2025.

## Built on by (most cited first, 12 of 12)

- [FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulation](https://mlsanity.com/paper/2602.23648/) (2026)
- [AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perception](https://mlsanity.com/paper/2602.09617/) (2026)
- [AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models](https://mlsanity.com/paper/2605.07308/) (2026)
- [Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective](https://mlsanity.com/paper/2509.09154/) (2025)
- [Tactile Modality Fusion for Vision-Language-Action Models](https://mlsanity.com/paper/2603.14604/) (2026)
- [Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation](https://mlsanity.com/paper/2606.29941/) (2026)
- [Selective Perception for Robot: Task-Aware Attention in Multimodal VLA](https://mlsanity.com/paper/2602.15543/) (2026)
- [Tac-DINO: Learning Vision-Tactile Features with Patch Alignment](https://mlsanity.com/paper/2606.12069/) (2026)
- [Symmetry-Aware Fusion of Vision and Tactile Sensing via Bilateral Force Priors for Robotic Manipulation](https://mlsanity.com/paper/2602.13689/) (2026)
- [TransDex: Pre-training Visuo-Tactile Policy with Point Cloud Reconstruction for Dexterous Manipulation of Transparent Objects](https://mlsanity.com/paper/2603.13869/) (2026)
- [DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imagination](https://mlsanity.com/paper/2609.09119/) (2026)
- [ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation](https://mlsanity.com/paper/2609.16586/) (2026)

## Abstract (arXiv)

Effectively utilizing multi-sensory data is important for robots to generalize across diverse tasks. However, the heterogeneous nature of these modalities makes fusion challenging. Existing methods propose strategies to obtain comprehensively fused features but often ignore the fact that each modality requires different levels of attention at different manipulation stages. To address this, we propose a force-guided attention fusion module that adaptively adjusts the weights of visual and tactile features without human labeling. We also introduce a self-supervised future force prediction auxiliary task to reinforce the tactile modality, improve data imbalance, and encourage proper adjustment. Our method achieves an average success rate of 93% across three fine-grained, contactrich tasks in real-world experiments. Further analysis shows that our policy appropriately adjusts attention to each modality at different manipulation stages. The videos can be viewed at https://adaptac-dex.github.io/.