VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models

• URL: http://arxiv.org/abs/2506.10085v3
• Date: Sun, 12 Oct 2025 11:46:33 GMT
• Title: VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models
• Authors: Christos Ziakas, Alessandra Russo,
• Abstract summary: VITA is a zero-shot value function learning method that enhances both capabilities via test-time adaptation.<n>We demonstrate that VITA's zero-shot value estimates can be utilized for reward shaping in offline reinforcement learning.
• Score: 49.78447737655287
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics [46.912038830356714]
  We introduce TOPReward, a novel, probabilistically grounded temporal value function that estimates robotic task progress.<n>In zero-shot evaluations across 130+ distinct real-world tasks, TOPReward achieves 0.947 mean Value-Order Correlation (VOC) on Qwen3-VL.<n>We demonstrate that TOPReward serves as a versatile tool for downstream applications, including success detection and reward-aligned behavior cloning.
  arXiv  Detail & Related papers  (2026-02-22T19:25:48Z)
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models [57.75717492488268]
  Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models.<n>Supervised Finetuning (SFT) requires hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training.<n>We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations.
  arXiv  Detail & Related papers  (2025-12-16T18:26:38Z)
• Test-time Offline Reinforcement Learning on Goal-related Experience [50.94457794664909]
  Research in foundation models has shown that performance can be substantially improved through test-time training.<n>We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state.<n>Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out.
  arXiv  Detail & Related papers  (2025-07-24T21:11:39Z)
• Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding [53.63482987410292]
  We present a self-adaptive curriculum learning paradigm that prioritizes fine-tuning examples based on difficulty scores predicted by pre-trained language models.<n>We evaluate our method on four natural language understanding (NLU) datasets covering both binary and multi-class classification tasks.
  arXiv  Detail & Related papers  (2025-07-13T19:36:17Z)
• Enhanced Continual Learning of Vision-Language Models with Model Fusion [16.764069327701186]
  Vision-Language Models (VLMs) represent a breakthrough in artificial intelligence.<n>VLMs are susceptible to catastrophic forgetting when sequentially fine-tuned on multiple downstream tasks.<n>We propose Continual Decoupling-Unifying (ConDU), a novel approach, by introducing model fusion into continual learning.
  arXiv  Detail & Related papers  (2025-03-12T15:48:13Z)
• Space Rotation with Basis Transformation for Training-free Test-Time Adaptation [25.408849667998993]
  We propose a training-free feature space rotation with basis transformation for test-time adaptation.<n>By leveraging the inherent distinctions among classes, we reconstruct the original feature space and map it to a new representation.<n>Our method outperforms state-of-the-art techniques in terms of both performance and efficiency.
  arXiv  Detail & Related papers  (2025-02-27T10:15:34Z)
• Vision Language Models are In-Context Value Learners [89.29486557646624]
  We present Generative Value Learning (GVL), a universal value function estimator that leverages the world knowledge embedded in vision-language models (VLMs) to predict task progress. Without any robot or task specific training, GVL can in-context zero-shot and few-shot predict effective values for more than 300 distinct real-world tasks.
  arXiv  Detail & Related papers  (2024-11-07T09:17:50Z)
• Adaptive Cascading Network for Continual Test-Time Adaptation [12.718826132518577]
  We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods on test-time training suffer from several limitations.
  arXiv  Detail & Related papers  (2024-07-17T01:12:57Z)
• BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models [20.88680592729709]
  We propose a novel backpropagation-free algorithm BaFTA for test-time adaptation of vision-language models. BaFTA directly estimates class centroids using online clustering within a projected embedding space. We demonstrate that BaFTA consistently outperforms state-of-the-art test-time adaptation methods in both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2024-06-17T08:16:24Z)
• A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models [3.0495235326282186]
  In deep learning, maintaining robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models at test-time.
  arXiv  Detail & Related papers  (2024-05-23T18:27:07Z)
• In-context Prompt Learning for Test-time Vision Recognition with Frozen Vision-language Model [13.983810804606264]
  We propose In-Context Prompt Learning (InCPL) for test-time visual recognition tasks. InCPL associates a new test sample with very few labeled examples as context information. We introduce a context-aware unsupervised loss to optimize visual prompts tailored to test samples.
  arXiv  Detail & Related papers  (2024-03-10T08:15:51Z)
• Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models [88.47454470043552]
  We consider the problem of online fine tuning the parameters of a language model at test time, also known as dynamic evaluation. Online adaptation turns parameters into temporally changing states and provides a form of context-length extension with memory in weights.
  arXiv  Detail & Related papers  (2024-03-03T14:03:48Z)
• Value Explicit Pretraining for Learning Transferable Representations [11.069853883599102]
  We propose a method that learns generalizable representations for transfer reinforcement learning. We learn new tasks that share similar objectives as previously learned tasks, by learning an encoder for objective-conditioned representations. Experiments using a realistic navigation simulator and Atari benchmark show that the pretrained encoder produced by our method outperforms current SoTA pretraining methods.
  arXiv  Detail & Related papers  (2023-12-19T17:12:35Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Predictive Experience Replay for Continual Visual Control and Forecasting [62.06183102362871]
  We present a new continual learning approach for visual dynamics modeling and explore its efficacy in visual control and forecasting. We first propose the mixture world model that learns task-specific dynamics priors with a mixture of Gaussians, and then introduce a new training strategy to overcome catastrophic forgetting. Our model remarkably outperforms the naive combinations of existing continual learning and visual RL algorithms on DeepMind Control and Meta-World benchmarks with continual visual control tasks.
  arXiv  Detail & Related papers  (2023-03-12T05:08:03Z)
• Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning [97.28779163988833]
  Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling. We propose textitMOMETAS, a novel adaptive sampler based on meta-learning, which learns the latent sampling pattern on arbitrary pre-training objectives.
  arXiv  Detail & Related papers  (2022-10-19T04:38:26Z)
• Meta-learning the Learning Trends Shared Across Tasks [123.10294801296926]
  Gradient-based meta-learning algorithms excel at quick adaptation to new tasks with limited data. Existing meta-learning approaches only depend on the current task information during the adaptation. We propose a 'Path-aware' model-agnostic meta-learning approach.
  arXiv  Detail & Related papers  (2020-10-19T08:06:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.