Related papers: Bayesian Test-time Adaptation for Object Recogniti…

Test-time adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, offering the distinct advantage of not requiring access to training data and processes, especially valuable in the context…

Continual test-time adaptation (cTTA) methods are designed to facilitate the continual adaptation of models to dynamically changing real-world environments where computational resources are limited. Due to this inherent limitation, existing…

Test-time adaptation (TTA) is an effective approach to mitigate performance degradation of trained models when encountering input distribution shifts at test time. However, existing TTA methods often suffer significant performance drops…

Test-Time Adaptation (TTA) methods improve the robustness of deep neural networks to domain shift on a variety of tasks such as image classification or segmentation. This work explores adapting segmentation models to a single unlabelled…

This paper introduces the Budding Ensemble Architecture (BEA), a novel reduced ensemble architecture for anchor-based object detection models. Object detection models are crucial in vision-based tasks, particularly in autonomous systems.…

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…

Continual Test-Time Adaptation (CTA) is a challenging task that aims to adapt a source pre-trained model to continually changing target domains. In the CTA setting, a model does not know when the target domain changes, thus facing a drastic…

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. These capabilities stem primarily from the self-attention mechanism, which enables modeling of long-range…

Test-time Adaptation (TTA) adapts a given model to testing domain data with potential domain shifts through online unsupervised learning, yielding impressive performance. However, to date, existing TTA methods primarily focus on…

Adapting pre-trained models to open classes is a challenging problem in machine learning. Vision-language models fully explore the knowledge of text modality, demonstrating strong zero-shot recognition performance, which is naturally suited…

Language models (LMs) pretrained on a large text corpus and fine-tuned on a downstream text corpus and fine-tuned on a downstream task becomes a de facto training strategy for several natural language processing (NLP) tasks. Recently, an…

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) aims to adapt a trained classifier using online unlabeled test data only, without any information related to the training procedure. Most existing TTA methods adapt the trained classifier using the classifier's…

Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or…

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending…

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…

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…

Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text and image information to fully attend to one another within…

Speech Foundation Models encounter significant performance degradation when deployed in real-world scenarios involving acoustic domain shifts, such as background noise and speaker accents. Test-time adaptation (TTA) has recently emerged as…

Attention is a core operation in large language models (LLMs) and vision-language models (VLMs). We present BD Attention (BDA), the first lossless algorithmic reformulation of attention. BDA is enabled by a simple matrix identity from Basis…