Related papers: ACORN: Performant and Predicate-Agnostic Search Ov…

Medical foundation models show promise to learn broadly generalizable features from large, diverse datasets. This could be the base for reliable cross-modality generalization and rapid adaptation to new, task-specific goals, with only a few…

The vast increase in amount and complexity of digital content led to a wide interest in ad-hoc retrieval systems in recent years. Complementary, the existence of heterogeneous data sources and retrieval models stimulated the proliferation…

Many emerging use cases of data mining and machine learning operate on large datasets with data from heterogeneous sources, specifically with both sparse and dense components. For example, dense deep neural network embedding vectors are…

The objective of ordinal embedding is to find a Euclidean representation of a set of abstract items, using only answers to triplet comparisons of the form "Is item $i$ closer to the item $j$ or item $k$?". In recent years, numerous…

Despite the recent successes of deep neural networks, it remains challenging to achieve high precision keyword spotting task (KWS) on resource-constrained devices. In this study, we propose a novel context-aware and compact architecture for…

There is a growing need to deploy machine learning for different tasks on a wide array of new hardware platforms. Such deployment scenarios require tackling multiple challenges, including identifying a model architecture that can achieve a…

Graph convolutional neural networks (GCNs) generalize tradition convolutional neural networks (CNNs) from low-dimensional regular graphs (e.g., image) to high dimensional irregular graphs (e.g., text documents on word embeddings). Due to…

Text embedding models enable semantic search, powering several NLP applications like Retrieval Augmented Generation by efficient information retrieval (IR). However, text embedding models are commonly studied in scenarios where the training…

In visual recognition, both the object of interest (referred to as foreground, FG, for simplicity) and its surrounding context (background, BG) play an important role. However, standard supervised learning often leads to unintended…

Multimodal retrieval methods have limitations in handling complex, compositional queries that require reasoning about the visual content of both the query and the retrieved entities. On the other hand, Large Multimodal Models (LMMs) can…

Pretrained contextualized embeddings are powerful word representations for structured prediction tasks. Recent work found that better word representations can be obtained by concatenating different types of embeddings. However, the…

In this paper, we claim that Vector Cosine, which is generally considered one of the most efficient unsupervised measures for identifying word similarity in Vector Space Models, can be outperformed by a completely unsupervised measure that…

Corner cases are rare or extreme scenarios that drive real-world failures, but they are difficult to curate at scale: web data are noisy, labels are brittle, and edge deployments preclude large retraining. We present ReCCur (Recursive…

High-definition (HD) maps are crucial to autonomous driving, providing structured representations of road elements to support navigation and planning. However, existing query-based methods often employ random query initialization and depend…

Current face detectors utilize anchors to frame a multi-task learning problem which combines classification and bounding box regression. Effective anchor design and anchor matching strategy enable face detectors to localize faces under…

The collaborative reasoning for understanding each image-question pair is very critical but under-explored for an interpretable Visual Question Answering (VQA) system. Although very recent works also tried the explicit compositional…

Approximate k-Nearest Neighbour (ANN) methods are often used for mining information and aiding machine learning on large scale high-dimensional datasets. ANN methods typically differ in the index structure used for accelerating searches,…

Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via…

Hybrid queries combining high-dimensional vector similarity search with spatio-temporal filters are increasingly critical for modern retrieval-augmented generation (RAG) systems. Existing systems typically handle these workloads by nesting…

Citation recommendation systems aim to recommend citations for either a complete paper or a small portion of text called a citation context. The process of recommending citations for citation contexts is called local citation recommendation…