TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning

• URL: http://arxiv.org/abs/2604.00696v1
• Date: Wed, 01 Apr 2026 09:52:57 GMT
• Title: TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning
• Abstract summary: We leverage the paradigm of Test-Time Reinforcement Learning on video-language data to allow for adapting a pretrained model to incoming video samples at test-time without explicit labels.<n>The proposed test-time adaptation for video approach (TTA-Vid) combines two components that work simultaneously.<n>TTA-Vid yields consistent improvements across various video reasoning tasks and is able to outperform current state-of-the-art methods trained on large-scale data.
• Score: 54.70019148172847
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent video reasoning models have shown strong results on temporal and multimodal understanding, yet they depend on large-scale supervised data and multi-stage training pipelines, making them costly to train and difficult to adapt to new domains. In this work, we leverage the paradigm of Test-Time Reinforcement Learning on video-language data to allow for adapting a pretrained model to incoming video samples at test-time without explicit labels. The proposed test-time adaptation for video approach (TTA-Vid) combines two components that work simultaneously: (1) a test-time adaptation that performs step-by-step reasoning at inference time on multiple frame subsets. We then use a batch-aware frequency-based reward computed across different frame subsets as pseudo ground truth to update the model. It shows that the resulting model trained on a single batch or even a single sample from a dataset, is able to generalize at test-time to the whole dataset and even across datasets. Because the adaptation occurs entirely at test time, our method requires no ground-truth annotations or dedicated training splits. Additionally, we propose a multi-armed bandit strategy for adaptive frame selection that learns to prioritize informative frames, guided by the same reward formulation. Our evaluation shows that TTA-Vid yields consistent improvements across various video reasoning tasks and is able to outperform current state-of-the-art methods trained on large-scale data. This highlights the potential of test-time reinforcement learning for temporal multimodal understanding.

Related papers

• VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations [59.40631942092535]
  Video temporal grounding (VTG) aims to locate precise segments in videos based on language queries.<n>Recent Multimodal Large Language Models (MLLMs) have shown promise in tackling VTG through reinforcement learning (RL)<n>We propose VideoTG-R1, a novel curriculum RL framework with reflected boundary annotations, enabling data-efficient training.
  arXiv  Detail & Related papers  (2025-10-27T14:55:38Z)
• Learning from Streaming Video with Orthogonal Gradients [62.51504086522027]
  We address the challenge of representation learning from a continuous stream of video as input, in a self-supervised manner.<n>This differs from the standard approaches to video learning where videos are chopped and shuffled during training in order to create a non-redundant batch.<n>We demonstrate the drop in performance when moving from shuffled to sequential learning on three tasks.
  arXiv  Detail & Related papers  (2025-04-02T17:59:57Z)
• Test-Time Alignment via Hypothesis Reweighting [56.71167047381817]
  Large pretrained models often struggle with underspecified tasks.<n>We propose a novel framework to address the challenge of aligning models to test-time user intent.
  arXiv  Detail & Related papers  (2024-12-11T23:02:26Z)
• Efficient Open Set Single Image Test Time Adaptation of Vision Language Models [15.621092104244003]
  Adapting models to dynamic, real-world environments is a critical challenge in deep learning.<n>We propose ROSITA, a novel framework that leverages dynamically updated feature banks to identify reliable test samples.<n>Our approach effectively adapts models to domain shifts for known classes while rejecting unfamiliar samples.
  arXiv  Detail & Related papers  (2024-06-01T16:21:42Z)
• Test-Time Training on Video Streams [66.63237260332984]
  Prior work has established Test-Time Training (TTT) as a general framework to further improve a trained model at test time.<n>We extend TTT to the streaming setting, where multiple test instances arrive in temporal order.<n>Online TTT significantly outperforms the fixed-model baseline for four tasks, on three real-world datasets.
  arXiv  Detail & Related papers  (2023-07-11T05:17:42Z)
• Transform-Equivariant Consistency Learning for Temporal Sentence Grounding [66.10949751429781]
  We introduce a novel Equivariant Consistency Regulation Learning framework to learn more discriminative representations for each video. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted. In particular, we devise a self-supervised consistency loss module to enhance the completeness and smoothness of the augmented video.
  arXiv  Detail & Related papers  (2023-05-06T19:29:28Z)
• Self-supervised pre-training and contrastive representation learning for multiple-choice video QA [39.78914328623504]
  Video Question Answering (Video QA) requires fine-grained understanding of both video and language modalities to answer the given questions. We propose novel training schemes for multiple-choice video question answering with a self-supervised pre-training stage and a supervised contrastive learning in the main stage as an auxiliary learning. We evaluate our proposed model on highly competitive benchmark datasets related to multiple-choice video QA: TVQA, TVQA+, and DramaQA.
  arXiv  Detail & Related papers  (2020-09-17T03:37:37Z)

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.