Related papers: GEM: A Native Graph-based Index for Multi-Vector R…

Similarity search approaches based on graph walks have recently attained outstanding speed-accuracy trade-offs, taking aside the memory requirements. In this paper, we revisit these approaches by considering, additionally, the memory…

Knowledge graph embedding models (KGEMs) have gained considerable traction in recent years. These models learn a vector representation of knowledge graph entities and relations, a.k.a. knowledge graph embeddings (KGEs). Learning versatile…

Conventional approaches to image-text retrieval mainly focus on indexing visual objects appearing in pictures but ignore the interactions between these objects. Such objects occurrences and interactions are equivalently useful and important…

Autonomous web navigation requires agents to perceive complex visual environments and maintain long-term context, yet current Large Language Model (LLM) based agents often struggle with spatial disorientation and navigation loops. In this…

Generative retrieval (GR) differs from the traditional index-then-retrieve pipeline by storing relevance in model parameters and generating retrieval cues directly from the query, but it can be brittle out of domain and expensive to scale.…

Generative retrieval-based recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. However, in large-scale recommendation systems, this approach becomes increasingly…

Causal discovery is a difficult problem that typically relies on strong assumptions on the data-generating model, such as non-Gaussianity. In practice, many modern applications provide multiple related views of the same system, which has…

Sketch-based query formulation is very common in image and video retrieval as these techniques often complement textual retrieval methods that are based on either manual or machine generated annotations. In this paper, we present a…

In most practical applications of image retrieval, high-dimensional feature vectors are required, but current multi-dimensional indexing structures lose their efficiency with growth of dimensions. Our goal is to propose a divisive…

Large language models with retrieval-augmented generation encounter a pivotal challenge in intricate retrieval tasks, e.g., multi-hop question answering, which requires the model to navigate across multiple documents and generate…

Cross-modal retrieval is an important functionality in modern search engines, as it increases the user experience by allowing queries and retrieved objects to pertain to different modalities. In this paper, we focus on the image-sentence…

Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments, etc.)…

An important linear algebra routine, GEneral Matrix Multiplication (GEMM), is a fundamental operator in deep learning. Compilers need to translate these routines into low-level code optimized for specific hardware. Compiler-level…

Vector search, the task of finding the k-nearest neighbors of a query vector against a database of high-dimensional vectors, underpins many machine learning applications, including retrieval-augmented generation, recommendation systems, and…

Long-horizon applications increasingly require large language models (LLMs) to answer queries when relevant evidence is sparse and dispersed across very long contexts. Existing memory systems largely follow two paradigms: explicit…

Named entity recognition (NER) is one of the best studied tasks in natural language processing. However, most approaches are not capable of handling nested structures which are common in many applications. In this paper we introduce a novel…

Visual navigation in complex environments is inefficient with traditional reactive policy or general-purposed recurrent policy. To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture…

We present SeVeN (Semantic Vector Networks), a hybrid resource that encodes relationships between words in the form of a graph. Different from traditional semantic networks, these relations are represented as vectors in a continuous vector…

Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments, etc.)…

Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more accurate and context-aware reasoning. We observe that for…