Saved in:
Bibliographic Details
Main Authors: Ziakas, Christos, Russo, Alessandra
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.10085
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918360537628672
author Ziakas, Christos
Russo, Alessandra
author_facet Ziakas, Christos
Russo, Alessandra
contents Vision-Language Models (VLMs) show promise as zero-shot goal-conditioned value functions, but their frozen pre-trained representations limit generalization and temporal reasoning. We introduce VITA, a zero-shot value function learning method that enhances both capabilities via test-time adaptation. At inference, a lightweight adaptation module is updated via a gradient step on a meta-learned self-supervised loss, such that each test-time update improves value estimation. By updating sequentially over a trajectory, VITA encodes history into its parameters, addressing the temporal reasoning limitations. To mitigate shortcut learning, we propose a dissimilarity-based sampling strategy that selects semantically diverse segments of the trajectory during training. In real-world robotic manipulation tasks, VITA generalizes from a single training environment to diverse out-of-distribution tasks, environments, and embodiments, outperforming the state-of-the-art zero-shot method using autoregressive VLMs. Furthermore, we demonstrate that VITA's zero-shot value estimates can be utilized for reward shaping in offline reinforcement learning, resulting in multi-task policies on the Meta-World benchmark that exceed the performance of those trained with the simulation's fuzzy-logic dense rewards. Project website: https://chziakas.github.io/vita/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10085
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models
Ziakas, Christos
Russo, Alessandra
Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.6; I.2.9; I.2.10
Vision-Language Models (VLMs) show promise as zero-shot goal-conditioned value functions, but their frozen pre-trained representations limit generalization and temporal reasoning. We introduce VITA, a zero-shot value function learning method that enhances both capabilities via test-time adaptation. At inference, a lightweight adaptation module is updated via a gradient step on a meta-learned self-supervised loss, such that each test-time update improves value estimation. By updating sequentially over a trajectory, VITA encodes history into its parameters, addressing the temporal reasoning limitations. To mitigate shortcut learning, we propose a dissimilarity-based sampling strategy that selects semantically diverse segments of the trajectory during training. In real-world robotic manipulation tasks, VITA generalizes from a single training environment to diverse out-of-distribution tasks, environments, and embodiments, outperforming the state-of-the-art zero-shot method using autoregressive VLMs. Furthermore, we demonstrate that VITA's zero-shot value estimates can be utilized for reward shaping in offline reinforcement learning, resulting in multi-task policies on the Meta-World benchmark that exceed the performance of those trained with the simulation's fuzzy-logic dense rewards. Project website: https://chziakas.github.io/vita/.
title VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.6; I.2.9; I.2.10
url https://arxiv.org/abs/2506.10085