Related papers: Synthetic Target Domain Supervision for Open Retri…

Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge…

Recent developments in deep learning have led to a significant innovation in various classic and practical subjects, including speech recognition, computer vision, question answering, information retrieval and so on. In the context of…

Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly focus on model-based adaptation in a self-training manner, such…

Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its…

Autonomous systems (AS) often use Deep Neural Network (DNN) classifiers to allow them to operate in complex, high-dimensional, non-linear, and dynamically changing environments. Due to the complexity of these environments, DNN classifiers…

Existing syntactically-controlled paraphrase generation (SPG) models perform promisingly with human-annotated or well-chosen syntactic templates. However, the difficulty of obtaining such templates actually hinders the practical application…

Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to an unlabeled target domain with no access to the source data. Inspired by the success of large Vision-Language (ViL) models in many applications, the latest…

Cross-domain retrieval (CDR), as a crucial tool for numerous technologies, is finding increasingly broad applications. However, existing efforts face several major issues, with the most critical being the need for accurate supervision,…

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

We present structured domain randomization (SDR), a variant of domain randomization (DR) that takes into account the structure and context of the scene. In contrast to DR, which places objects and distractors randomly according to a uniform…

We present Mr. TyDi, a multi-lingual benchmark dataset for mono-lingual retrieval in eleven typologically diverse languages, designed to evaluate ranking with learned dense representations. The goal of this resource is to spur research in…

Semi-supervised domain adaptation (SSDA) aims at training a high-performance model for a target domain using few labeled target data, many unlabeled target data, and plenty of auxiliary data from a source domain. Previous works in SSDA…

Dysarthric speech detection (DSD) systems aim to detect characteristics of the neuromotor disorder from speech. Such systems are particularly susceptible to domain mismatch where the training and testing data come from the source and target…

Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously…

Recent domain adaptation methods have demonstrated impressive improvement on unsupervised domain adaptation problems. However, in the semi-supervised domain adaptation (SSDA) setting where the target domain has a few labeled instances…

Passage retrieval is a fundamental task in information retrieval (IR) research, which has drawn much attention recently. In the English field, the availability of large-scale annotated dataset (e.g, MS MARCO) and the emergence of deep…

Dense retrievers have demonstrated significant potential for neural information retrieval; however, they exhibit a lack of robustness to domain shifts, thereby limiting their efficacy in zero-shot settings across diverse domains. Previous…

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full…

Neural 'dense' retrieval models are state of the art for many datasets, however these models often exhibit limited domain transfer ability. Existing approaches to adaptation are unwieldy, such as requiring explicit supervision, complex…

Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth estimation) has the…