Related papers: You only need 4 extra tokens: Synergistic Test-tim…

Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by…

Finetuning a large vision language model (VLM) on a target dataset after large scale pretraining is a dominant paradigm in visual question answering (VQA). Datasets for specialized tasks such as knowledge-based VQA or VQA in non…

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…

Efficiently fine-tuning Large Language Models (LLMs) for specific tasks presents a considerable challenge in natural language processing. Traditional methods, like prompt or prefix tuning, typically rely on arbitrary tokens for training,…

The performance of deep learning models depends heavily on test samples at runtime, and shifts from the training data distribution can significantly reduce accuracy. Test-time adaptation (TTA) addresses this by adapting models during…

Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific…

Performance of a pre-trained semantic segmentation model is likely to substantially decrease on data from a new domain. We show a pre-trained model can be adapted to unlabelled target domain data by calculating soft-label prototypes under…

Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model…

Test-time adaptation with pre-trained vision-language models (VLMs) has attracted increasing attention for tackling the issue of distribution shift during the test phase. While prior methods have shown effectiveness in addressing…

Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the…

A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is to adapt a pre-trained model to novel domains using only…

Lemmatization is the task of transforming all words in a given text to their dictionary forms. While large language models (LLMs) have demonstrated their ability to achieve competitive results across a wide range of NLP tasks, there is no…

The issue of source-free time-series domain adaptations still gains scarce research attentions. On the other hand, existing approaches rely solely on time-domain features ignoring frequency components providing complementary information.…

While there are many advantages to deploying machine learning models on edge devices, the resource constraints of mobile platforms, the dynamic nature of the environment, and differences between the distribution of training versus…

Large Language Models (LLMs) can achieve enhanced complex problem-solving through test-time computing scaling, yet this often entails longer contexts and numerous reasoning token costs. In this paper, we propose an efficient test-time…

Instruction-based Large Language Models (LLMs) have proven effective in numerous few-shot or zero-shot Natural Language Processing (NLP) tasks. However, creating human-annotated instruction data is time-consuming, expensive, and often…

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important for deep models when the test environment…

In recent years, developing compact and efficient large language models (LLMs) has emerged as a thriving area of research. Traditional Supervised Fine-Tuning (SFT), which relies on singular ground truth labels, often fails to capture…

Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to…

Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference. However, the model performance can be significantly impaired by continuous distribution changes…