Related papers: V3DB: Audit-on-Demand Zero-Knowledge Proofs for Ve…

Approximate nearest neighbor (ANN) indexes deployed against streaming corpora silently lose recall over weeks. The standard diagnosis is distribution shift, but under shuffled-i.i.d. ingestion -- no shift at all -- product quantization…

While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the…

Vector search underpins modern information-retrieval systems, including retrieval-augmented generation (RAG) pipelines and search engines over unstructured text and images. As datasets scale to billions of vectors, disk-based vector search…

Recent advances in detecting arbitrary objects in the real world are trained and evaluated on object detection datasets with a relatively restricted vocabulary. To facilitate the development of more general visual object detection, we…

Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization…

Vector search and database systems have become a keystone component in many AI applications. While many prior research has investigated how to accelerate the performance of generic vector search, emerging AI applications require running…

With the recent proliferation of sensor data, there is an increasing need for the efficient evaluation of analytical queries over multiple sensor datasets. The magnitude of such datasets makes exact query answering infeasible, leading…

Retrieval-Augmented Generation (RAG) has established itself as the standard paradigm for grounding Large Language Models (LLMs) in domain-specific, up-to-date data. However, the prevailing architecture for RAG has evolved into a complex,…

We present an unsupervised explainable word embedding technique, called EVE, which is built upon the structure of Wikipedia. The proposed model defines the dimensions of a semantic vector representing a word using human-readable labels,…

Verifiable computing (VC) has gained prominence in decentralized machine learning systems, where resource-intensive tasks like deep neural network (DNN) inference are offloaded to external participants due to blockchain limitations. This…

In long, multi-page industrial documents, retrieval-augmented generation (RAG) depends heavily on whether chunk boundaries follow the document's true structure. Existing text-centric chunkers and generative hierarchy parsers often miss…

Chain-of-Thought (CoT) reasoning has advanced the capabilities and transparency of language models (LMs); however, reasoning chains can contain inaccurate statements that reduce performance and trustworthiness. To address this, we propose…

Approximate nearest neighbor (ANN) search is a performance-critical component of many machine learning pipelines. Rigorous benchmarking is essential for evaluating the performance of vector indexes for ANN search. However, the datasets of…

Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving comprehensive semantic…

Semantic caches return cached responses for semantically similar prompts to reduce LLM inference latency and cost. They embed cached prompts and store them alongside their response in a vector database. Embedding similarity metrics assign a…

Retrieval-Augmented Generation (RAG) systems have become a dominant approach to augment large language models (LLMs) with external knowledge. However, existing vector database (VecDB) retrieval pipelines rely on flat or single-resolution…

Unstructured data formats account for over 80% of the data currently stored, and extracting value from such formats remains a considerable challenge. In particular, current approaches for managing unstructured documents do not support…

Large-scale vector databases for approximate nearest neighbor (ANN) search typically store a quantized dataset in main memory for fast access, and full precision data on remote disk. State-of-the-art ANN quantization methods are highly…

Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first…

Reliable product identification from images is a critical requirement in industrial and commercial applications, particularly in maintenance, procurement, and operational workflows where incorrect matches can lead to costly downstream…