English
Related papers

Related papers: Improving Black-box Robustness with In-Context Rew…

200 papers

Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model…

Machine Learning · Computer Science 2022-06-29 Helen Lu , Divya Shanmugam , Harini Suresh , John Guttag

Spoken Language Models (SLMs) are increasingly central to modern speech-driven applications, but performance degrades under acoustic shift - real-world noise, reverberation, and microphone variation. Prior solutions rely on offline domain…

Test-time adaptation (TTA) for large language models (LLMs) updates model parameters at inference time using signals available at deployment. This paper focuses on a common yet under-explored regime: unsupervised, sample-specific TTA, where…

Computation and Language · Computer Science 2026-02-11 Longhuan Xu , Cunjian Chen , Feng Yin

Test-time augmentation (TTA)--aggregating predictions over multiple augmented copies of a test input--is widely assumed to improve classification accuracy, particularly in medical imaging where it is routinely deployed in production systems…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Daniel Nobrega Medeiros

Data augmentation is known to contribute significantly to the robustness of machine learning models. In most instances, data augmentation is utilized during the training phase. Test-Time Augmentation (TTA) is a technique that instead…

Machine Learning · Statistics 2024-09-20 Masanari Kimura , Howard Bondell

Despite progress in end-to-end ASR, real-world domain mismatches still cause performance drops, which Test-Time Adaptation (TTA) aims to mitigate by adjusting models during inference. Recent work explores combining TTA with external…

Computation and Language · Computer Science 2025-06-16 Wei-Ping Huang , Guan-Ting Lin , Hung-yi Lee

Despite the impressive capabilities of large language models (LLMs), their performance on information extraction tasks is still not entirely satisfactory. However, their remarkable rewriting capabilities and extensive world knowledge offer…

Computation and Language · Computer Science 2024-02-23 Junjie Ye , Nuo Xu , Yikun Wang , Jie Zhou , Qi Zhang , Tao Gui , Xuanjing Huang

Test-time adaptation (TTA) refers to adjusting the model during the testing phase to cope with changes in sample distribution and enhance the model's adaptability to new environments. In real-world scenarios, models often encounter samples…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Ziqiong Liu , Yushun Tang , Junyang Ji , Zhihai He

In recent years, language models (LMs) have made remarkable progress in advancing the field of natural language processing (NLP). However, the impact of data augmentation (DA) techniques on the fine-tuning (FT) performance of these LMs has…

Computation and Language · Computer Science 2023-06-14 Zhengxiang Shi , Aldo Lipani

The static ``train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT)…

Machine Learning · Computer Science 2026-04-08 Guhao Feng , Shengjie Luo , Kai Hua , Ge Zhang , Di He , Wenhao Huang , Tianle Cai

The rapid advancements in vision-language models (VLMs), such as CLIP, have intensified the need to address distribution shifts between training and testing datasets. Although prior Test-Time Training (TTT) techniques for VLMs have…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Yuto Kojima , Jiarui Xu , Xueyan Zou , Xiaolong Wang

Recurrent Neural Networks (RNNs) have emerged as an interesting alternative to conventional material modeling approaches, particularly for nonlinear path dependent materials. Remarkable computational enhancements are obtained using RNNs…

Computational Engineering, Finance, and Science · Computer Science 2024-09-05 Petter Uvdal , Mohsen Mirkhalaf

In this study, we introduce an intelligent Test Time Augmentation (TTA) algorithm designed to enhance the robustness and accuracy of image classification models against viewpoint variations. Unlike traditional TTA methods that…

Image and Video Processing · Electrical Eng. & Systems 2024-06-14 Efe Ozturk , Mohit Prabhushankar , Ghassan AlRegib

Data augmentation has become a promising method of mitigating data sparsity in sequential recommendation. Existing methods generate new yet effective data during model training to improve performance. However, deploying them requires…

Information Retrieval · Computer Science 2025-05-01 Yizhou Dang , Yuting Liu , Enneng Yang , Minhan Huang , Guibing Guo , Jianzhe Zhao , Xingwei Wang

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Samuel Barbeau , Pedram Fekri , David Osowiechi , Ali Bahri , Moslem Yazdanpanah , Masih Aminbeidokhti , Christian Desrosiers

Generalizing deep learning models to unknown target domain distribution with low latency has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches often focus on improving test-time training performance under…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Yushu Li , Xun Xu , Yongyi Su , Kui Jia

Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-time adaptation (TTA) methods adopt positive data…

Machine Learning · Computer Science 2025-11-14 Ruxi Deng , Wenxuan Bao , Tianxin Wei , Jingrui He

Mainstream test-time adaptation (TTA) techniques endeavor to mitigate distribution shifts via entropy minimization for multi-class classification, inherently increasing the probability of the most confident class. However, when encountering…

Computer Vision and Pattern Recognition · Computer Science 2025-02-07 Xiangyu Wu , Feng Yu , Qing-Guo Chen , Yang Yang , Jianfeng Lu

A deployed question answering (QA) model can easily fail when the test data has a distribution shift compared to the training data. Robustness tuning (RT) methods have been widely studied to enhance model robustness against distribution…

Computation and Language · Computer Science 2023-02-10 Hai Ye , Yuyang Ding , Juntao Li , Hwee Tou Ng

Multi-modal test-time adaptation (MM-TTA) adapts models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. While previous MM-TTA methods for 3D segmentation offer a promising solution by…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Haozhi Cao , Yuecong Xu , Pengyu Yin , Xingyu Ji , Shenghai Yuan , Jianfei Yang , Lihua Xie
‹ Prev 1 2 3 10 Next ›