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

Effective document reranking is essential for improving search relevance across diverse applications. While Large Language Models (LLMs) excel at reranking due to their deep semantic understanding and reasoning, their high computational…

Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved…

Learning with a limited number of labeled data is a central problem in real-world applications of machine learning, as it is often expensive to obtain annotations. To deal with the scarcity of labeled data, transfer learning is a…

We study the domain adaptation problem with label shift in this work. Under the label shift context, the marginal distribution of the label varies across the training and testing datasets, while the conditional distribution of features…

Test-time adaptation (TTA) is a technique used to reduce distribution gaps between the training and testing sets by leveraging unlabeled test data during inference. In this work, we expand TTA to a more practical scenario, where the test…

Learning to adapt pretrained language models to unlabeled, out-of-distribution data is a critical challenge, as models often falter on structurally novel reasoning tasks even while excelling within their training distribution. We introduce…

This paper introduces a method for adapting LoRA adapters in smaller-sized language models to arbitrary downstream tasks. Unlike standard mixture-of-expert architectures, our method employs a gradient-free routing function to choose a…

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…

Realignment becomes necessary when a language model (LM) fails to meet expected performance. We propose a flexible realignment framework that supports quantitative control of alignment degree during training and inference. This framework…

Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods are usually evaluated on benchmarks that are only a…

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…

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

The number of pretrained Large Language Models (LLMs) is increasing steadily, though the majority are designed predominantly for the English language. While state-of-the-art LLMs can handle other languages, due to language contamination or…

Text-based person search faces inherent limitations due to data scarcity, driven by stringent privacy constraints and the high cost of manual annotation. To mitigate this, existing methods usually rely on a Pretrain-then-Finetune paradigm,…

Test-time adaptation (TTA) refers to adapting a trained model to a new domain during testing. Existing TTA techniques rely on having multiple test images from the same domain, yet this may be impractical in real-world applications such as…

Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test…

When solving NLP tasks with limited labelled data, researchers typically either use a general large language model without further update, or use a small number of labelled samples to tune a specialised smaller model. In this work, we…

Large Language Models (LLMs) have improved substantially alignment, yet their behavior remains highly sensitive to prompt phrasing. This brittleness has motivated automated prompt engineering, but most existing methods (i) require a…

In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets. However, the large size and high computation demands of LLMs limit their practicality in many…

Fully-test-time adaptation (F-TTA) can mitigate performance loss due to distribution shifts between train and test data (1) without access to the training data, and (2) without knowledge of the model training procedure. In online F-TTA, a…