paper-with-me

홈 › Papers

Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation

2026-08-19 · Prachi Garg, Steve Xing, Prahit Yaugand, Saurabh Gupta, Derek Hoiem arxiv

State-of-the-art vision-language-action (VLA) models such as $π_{0.5}$ exhibit strong semantic understanding, instruction following and task behavior. However, when deployed on new robots, even minor mismatches in hardware configuration relative to pretraining can cause severe performance drops. Finetuning the VLA on in-domain expert data from the new embodiment improves performance on the expert task but leads to a loss in its original instruction following and behavioral priors. In this paper, we propose a self-supervised method that generates online interaction rollouts from the zero-shot VLA as additional training data for finetuning. Our experiments show this finetuning scheme yields strong multi-task policies that, on the target robot, (1) inherit prior tasks distilled from the zero-shot model, (2) enable generalist instruction following, while (3) learning new skills from expert data with improved sample efficiency. We demonstrate the success of our approach across test sets probing generalization on a real ALOHA robot and a new simulation benchmark in RoboTwin. Video results are available at https://self-supervised-control.pages.dev/

📄 PDF Abstract BibTeX arXiv:2608.19490

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction Following

Similar Papers 제목 키워드 기반

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human

2025-09-18 · Nan Sun, Yongchang Li, Chenxu Wang, Huiying Li 외 arxiv

In this work, we present CollabVLA, a self-reflective vision-language-action framework that transforms a standard visuomotor policy into a collaborative assistant. CollabVLA tackles key limitations of prior VLAs, includi…

RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models

2025-06-21 · Jacky Kwok, Christopher Agia, Rohan Sinha, Matt Foutter 외

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in visuomotor control, yet ensuring their robustness in unstructured real-world environments remains a persistent challenge. In this paper, we…

Synthetic Data GenerationVision-Language-Action

Uncertainty Quantification for Flow-Based Vision-Language-Action Models

2026-06-16 · Ralf Römer, Maximilian Seeliger, Saida Liu, Ben Sturgis 외 arxiv

Vision-language-action models (VLAs) combine vision-language backbones with expressive generative action heads trained via flow matching on large-scale robotic datasets. Despite their strong empirical performance in robo…

Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds

2026-03-19 · Andrew Choi, Xinjie Wang, Zhizhong Su, Wei Xu arxiv

The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in robotics. Many recent works f…

Zero-shot GeneralizationReinforcement Learning

Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations

2025-11-27 · Chancharik Mitra, Yusen Luo, Raj Saravanan, Dantong Niu 외 arxiv

Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for robotics require finetuning to contend …