PaperScope
LIVE · 2026-09-09 05:40 UTC

GIFT: Goal-Injected Fine-Tuning for Efficient Manipulation Policy Adaptation

Xiaoyuan Fang, Shuo Feng, Yuxuan Wang, Enhua Cheng, Peng Zhou, Piji Li

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.07006 v1
Category
Submitted
2026-09-07

Abstract

Compared with relying solely on initial observations and language instructions, predicting goal images with generative models as high-level visual guidance can significantly enhance the robustness of Vision-Language-Action (VLA) models. However, most existing foundation models have not systematically incorporated goal image conditioning due to the high computational training cost. To this end, we propose Goal-Injected Fine-Tuning (GIFT), a lightweight and efficient fine-tuning framework that seamlessly integrates generated goal images into multiple representative pretrained VLA models. Our approach introduces goal image features into observations via a zero-initialized convolution which progressively grows parameters from zero and prevents harmful noise from disrupting the pretrained policy during fine-tuning. As training proceeds, goal information is gradually incorporated, enabling efficient goal understanding without disrupting model stability. We further introduce a refined image editing method to generate semantically and visually consistent goal images from initial observations and task instructions. Experiments show that goal-aware VLA models achieve substantial performance gains across tasks: with only a single epoch of fine-tuning, GIFT outperforms the base model by 6.0% and 13.4% on two SIMPLER settings, and by 4.7% on LIBERO, demonstrating both efficiency and effectiveness.

Comment: 20 pages, 12 figures, accepted by EMNLP2026

arXiv abs page · PDF · same-day batch