# FBI: Learning Dexterous In-hand Manipulation with Dynamic Visuotactile Shortcut Policy

arXiv: https://arxiv.org/abs/2508.14441 · HTML: https://mlsanity.com/paper/2508.14441/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2025.

## Built on by (most cited first, 1 of 1)

- [PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph](https://mlsanity.com/paper/2608.01905/) (2026)

## Abstract (arXiv)

Dexterous in-hand manipulation is a long-standing challenge in robotics due to complex contact dynamics and partial observability. While humans synergize vision and touch for such tasks, robotic approaches often prioritize one modality, therefore limiting adaptability. This paper introduces Flow Before Imitation (FBI), a visuotactile imitation learning framework that dynamically fuses tactile interactions with visual observations through motion dynamics. Unlike prior static fusion methods, FBI establishes a causal link between tactile signals and object motion via a dynamics-aware latent model. FBI employs a transformer-based interaction module to fuse flow-derived tactile features with visual inputs, training a one-step diffusion policy for real-time execution. Extensive experiments demonstrate that the proposed method outperforms the baseline methods in both simulation and the real world on two customized in-hand manipulation tasks and three standard dexterous manipulation tasks. Code, models, and more results are available in the website https://sites.google.com/view/dex-fbi.