# Improving Fine-Grained Manipulation through Demonstration Expansion and Execution Design

**Authors:** Jingxu Gu, Dongze Lian  
**Lab:** Nanjing University · **Published:** 29 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.40430) · [PDF](https://arxiv.org/pdf/2610.40430) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.40430.html)

## Key numbers

- **85.55%**: DEED achieves an official Overall score of 85.55%

## Abstract

Fine-grained manipulation requires a robot policy to follow instructions, remain robust to visual variations, and translate predicted actions into precise robot control. We present Demonstration Expansion and Execution Design (DEED), a framework for adapting a pretrained vision-language-action policy to the five MetaFine tasks through structured demonstration expansion and execution design. DEED generates demonstrations for different instructions from the same initial scene and renders each physical trajectory under different camera positions and lighting conditions while preserving its original states and action targets. A hierarchical sampling strategy balances instructions, trajectories, and visual conditions during supervised adaptation. At deployment, DEED converts predicted action chunks into robot commands using inverse kinematics, gripper mappings selected for each task, and closed-loop replanning. DEED achieves an official Overall score of 85.55%. Fixed-policy evaluations show that performance varies with execution horizon, denoising budget, and gripper mapping.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.