Related papers: WARP: An Efficient Engine for Multi-Vector Retriev…

The paper presents an approach to solving the Robust Energy Capacitated Vehicle Routing Problem (RECVRP), focusing on electric vehicles and their limited battery capacity. A finite number of customers, each with their own demand, have to be…

Solving different types of optimization models (including parameters fitting) for support vector machines on large-scale training data is often an expensive computational task. This paper proposes a multilevel algorithmic framework that…

To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely on simplistic similarity measures, which limit their effectiveness. We introduce…

Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has garnered growing attention due to resource efficiency and…

Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ranking. To overcome this challenge, this paper presents BECR…

Retrieval-Augmented Generation (RAG) has proven effective on server infrastructures, but its application on mobile devices is still underexplored due to limited memory and power resources. Existing vector search and RAG solutions largely…

Neural ranking has become a cornerstone of modern information retrieval. While single vector search remains the dominant paradigm, it suffers from the shortcoming of compressing all the information into a single vector. This compression…

Late interaction retrieval methods, pioneered by ColBERT, have emerged as a powerful alternative to single-vector neural IR. By leveraging fine-grained, token-level representations, they have been demonstrated to deliver strong…

Pre-trained language models have shown stellar performance in various downstream tasks. But, this usually comes at the cost of high latency and computation, hindering their usage in resource-limited settings. In this work, we propose a…

Large Language Models (LLMs) have demonstrated impressive ability in generation and reasoning tasks but struggle with handling up-to-date knowledge, leading to inaccuracies or hallucinations. Retrieval-Augmented Generation (RAG) mitigates…

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…

Retrieval-Augmented Generation (RAG) systems lose retrieval accuracy when similar documents coexist in the vector database, causing unnecessary information, hallucinations, and factual errors. To alleviate this issue, we propose CHOP, a…

Multi-task learning is a natural approach for computer vision applications that require the simultaneous solution of several distinct but related problems, e.g. object detection, classification, tracking of multiple agents, or denoising, to…

Retrieval Augmented Generation (RAG) has proven to be highly effective in boosting the generative performance of language model in knowledge-intensive tasks. However, existing RAG framework either indiscriminately perform retrieval or rely…

Multi-vector late-interaction retrievers such as ColBERT achieve state-of-the-art retrieval quality, but their query-time cost is dominated by exhaustively computing token-level MaxSim interactions for every candidate document. While…

The increasing use of Retrieval-Augmented Generation (RAG) systems in various applications necessitates stringent protocols to ensure RAG systems accuracy, safety, and alignment with user intentions. In this paper, we introduce VERA…

To effectively leverage user-specific data, retrieval augmented generation (RAG) is employed in multimodal large language model (MLLM) applications. However, conventional retrieval approaches often suffer from limited retrieval accuracy.…

Today, two major trends are shaping the evolution of ML systems. First, modern AI systems are becoming increasingly complex, often integrating components beyond the model itself. A notable example is Retrieval-Augmented Generation (RAG),…

Embedding-based retrieval (EBR) methods are widely used in modern recommender systems thanks to its simplicity and effectiveness. However, along the journey of deploying and iterating on EBR in production, we still identify some fundamental…

Leveraging query variants (QVs), i.e., queries with potentially similar information needs to the target query, has been shown to improve the effectiveness of query performance prediction (QPP) approaches. Existing QV-based QPP methods…