Related papers: Efficient Multivector Retrieval with Token-Aware C…

Vector search plays a crucial role in many real-world applications. In addition to single-vector search, multi-vector search becomes important for multi-modal and multi-feature scenarios today. In a multi-vector database, each row is an…

Most existing methods in vision-language retrieval match two modalities by either comparing their global feature vectors which misses sufficient information and lacks interpretability, detecting objects in images or videos and aligning the…

While multi-vector retrieval models outperform single-vector models of comparable size in retrieval quality, their practicality is limited by substantially larger index sizes, driven by the additional sequence-length dimension in their…

Like k-means and Gaussian Mixture Model (GMM), fuzzy c-means (FCM) with soft partition has also become a popular clustering algorithm and still is extensively studied. However, these algorithms and their variants still suffer from some…

The increasing adoption of large language models (LLMs) with extended context windows necessitates efficient Key-Value Cache (KVC) management to optimize inference performance. Inference workloads like Retrieval-Augmented Generation (RAG)…

Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive…

Rashomon sets are model sets within one model class that perform nearly as well as a reference model from the same model class. They reveal the existence of alternative well-performing models, which may support different interpretations.…

With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with limited computational capabilities, the predominant inference…

Clustering is a fundamental tool in unsupervised learning, used to group objects by distinguishing between similar and dissimilar features of a given data set. One of the most common clustering algorithms is k-means. Unfortunately, when…

Kernel-based clustering algorithms have the ability to capture the non-linear structure in real world data. Among various kernel-based clustering algorithms, kernel k-means has gained popularity due to its simple iterative nature and ease…

Large vision-language models (VLMs) are enabling interactive video reasoning, giving rise to streaming long-video understanding. In this setting, frames arrive continuously, while the system preserves long-term context and generates…

This paper revisits cluster-based retrieval that partitions the inverted index into multiple groups and skips the index partially at cluster and document levels during online inference using a learned sparse representation. It proposes an…

Multi-vector visual retrievers (e.g., ColPali-style late interaction models) deliver strong accuracy, but scale poorly because each page yields thousands of vectors, making indexing and search increasingly expensive. We present Visual RAG…

The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…

K-means -- and the celebrated Lloyd algorithm -- is more than the clustering method it was originally designed to be. It has indeed proven pivotal to help increase the speed of many machine learning and data analysis techniques such as…

The success of deep learning hinges on enormous data and large models, which require labor-intensive annotations and heavy computation costs. Subset selection is a fundamental problem that can play a key role in identifying smaller portions…

The k-means algorithm can simplify large-scale spatial vectors, such as 2D geo-locations and 3D point clouds, to support fast analytics and learning. However, when processing large-scale datasets, existing k-means algorithms have been…

Multi-view clustering has attracted broad attention due to its capacity to utilize consistent and complementary information among views. Although tremendous progress has been made recently, most existing methods undergo high complexity,…

k-means has recently been recognized as one of the best algorithms for clustering unsupervised data. Since k-means depends mainly on distance calculation between all data points and the centers, the time cost will be high when the size of…

Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers and have achieved state-of-the-art performance on various retrieval tasks. These methods, however, are orders of magnitude slower and…