Related papers: DRAMA: Domain Retrieval using Adaptive Module Allo…

Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are…

Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain adaptation, which tends to corrupt feature discriminability.…

Clients wishing to implement generative AI in the domain of IT Support and AIOps face two critical issues: domain coverage and model size constraints due to model choice limitations. Clients might choose to not use larger proprietary models…

Post-disaster road assessment (PDRA) is essential for emergency response, enabling rapid evaluation of infrastructure conditions and efficient allocation of resources. Although drones provide a flexible and effective tool for PDRA, routing…

Domain adaptation remains a challenge when there is significant manifold discrepancy between source and target domains. Although recent methods leverage manifold-aware adversarial perturbations to perform data augmentation, they often…

Existing All-In-One image restoration (IR) methods usually lack flexible modeling on various types of degradation, thus impeding the restoration performance. To achieve All-In-One IR with higher task dexterity, this work proposes an…

While retrieval-augmented generation (RAG) has been shown to enhance factuality of large language model (LLM) outputs, LLMs still suffer from hallucination, generating incorrect or irrelevant information. A common detection strategy…

In many real-world applications, we want to exploit multiple source datasets of similar tasks to learn a model for a different but related target dataset -- e.g., recognizing characters of a new font using a set of different fonts. While…

Video generative models can be regarded as world simulators due to their ability to capture dynamic, continuous changes inherent in real-world environments. These models integrate high-dimensional information across visual, temporal,…

Large Language Models (LLMs) encounter challenges with the unique syntax of specific domains, such as biomolecules. Existing fine-tuning or modality alignment techniques struggle to bridge the domain knowledge gap and understand complex…

Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data…

Large language models (LLMs) often struggle with knowledge-intensive tasks due to hallucinations and outdated parametric knowledge. While Retrieval-Augmented Generation (RAG) addresses this by integrating external corpora, its effectiveness…

In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e.g. a new centreor a new…

Recent advancements in Retrieval-Augmented Language Models (RALMs) have demonstrated their efficacy in knowledge-intensive tasks. However, existing evaluation benchmarks often assume a single optimal approach to leveraging retrieved…

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…

Data sparsity and cold-start problems are persistent challenges in recommendation systems. Cross-domain recommendation (CDR) is a promising solution that utilizes knowledge from the source domain to improve the recommendation performance in…

Current Retrieval-Augmented Generation systems use uniform processing, causing inefficiency as simple queries consume resources similar to complex multi-hop tasks. We present SymRAG, a framework that introduces adaptive query routing via…

Retrieval-Augmented Generation (RAG) has become a foundational paradigm for equipping large language models (LLMs) with external knowledge, playing a critical role in information retrieval and knowledge-intensive applications. However,…

Deploying dense retrieval models efficiently is becoming increasingly important across various industries. This is especially true for enterprise search services, where customizing search engines to meet the time demands of different…

Retrieval-augmented generation (RAG) systems often rely on static retrieval, limiting adaptation to evolving intent and content drift. We introduce Dynamic Memory Alignment (DMA), an online learning framework that systematically…