Related papers: An efficient reverse-lookup table based strategy f…

GPU-based concurrent data structures (CDSs) achieve high throughput for read-only queries, but efficient support for dynamic updates on fully GPU-resident data remains challenging. Ordered CDSs (e.g., B-trees and LSM-trees) maintain an…

Multi-vector retrieval methods, exemplified by the ColBERT architecture, have shown substantial promise for retrieval by providing strong trade-offs in terms of retrieval latency and effectiveness. However, they come at a high cost in terms…

The suffix array is an efficient data structure for in-memory pattern search. Suffix arrays can also be used for external-memory pattern search, via two-level structures that use an internal index to identify the correct block of suffix…

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

Sparse-dense linear algebra is crucial in many domains, but challenging to handle efficiently on CPUs, GPUs, and accelerators alike; multiplications with sparse formats like CSR and CSF require indirect memory lookups. In this work, we…

Computers continue to diversify with respect to system designs, emerging memory technologies, and application memory demands. Unfortunately, continually adapting the conventional virtual memory framework to each possible system…

Planning under uncertainty for real-world robotics tasks, such as autonomous driving, requires reasoning in enormous high-dimensional belief spaces, rendering the problem computationally intensive. While parallelization offers scalability,…

Traditional multimodal retrieval systems rely primarily on bi-encoder architectures, where performance is closely tied to embedding dimensionality. Recent work, Think-Then-Embed (TTE), shows that incorporating multimodal reasoning to elicit…

Due to the coarse granularity of data accesses and the heavy use of latches, indices in the B-tree family are not efficient for in-memory databases, especially in the context of today's multi-core architecture. In this paper, we present PI,…

Recent advances in long-text understanding have pushed the context length of large language models (LLMs) up to one million tokens. It boosts LLMs's accuracy and reasoning capacity but causes exorbitant computational costs and…

Processing-in-cache (PiC) and Processing-in-memory (PiM) architectures, especially those utilizing bit-line computing, offer promising solutions to mitigate data movement bottlenecks within the memory hierarchy. While previous studies have…

Mining the latent intentions from large volumes of natural language inputs is a key step to help data analysts design and refine Intelligent Virtual Assistants (IVAs) for customer service and sales support. We created a flexible and…

Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although…

Over the years, many different indexing techniques and search algorithms have been proposed, including CSS-trees, CSB+ trees, k-ary binary search, and fast architecture sensitive tree search. There have also been papers on how best to set…

To overcome the barrier of storage and computation, the hashing technique has been widely used for nearest neighbor search in multimedia retrieval applications recently. Particularly, cross-modal retrieval that searches across different…

Impact craters are a cornerstone of planetary surface analysis. However, while most deep learning pipelines treat craters solely as a detection problem, critical scientific workflows such as catalog deduplication, cross-observation…

Approximate nearest neighbor search for vectors relies on indexes that are most often accessed from RAM. Therefore, storage is the factor limiting the size of the database that can be served from a machine. Lossy vector compression, i.e.,…

We introduce the problem of Table Reclamation. Given a Source Table and a large table repository, reclamation finds a set of tables that, when integrated, reproduce the source table as closely as possible. Unlike query discovery problems…

This paper discusses clustering and latent semantic indexing (LSI) aspects of the singular value decomposition (SVD). The purpose of this paper is twofold. The first is to give an explanation on how and why the singular vectors can be used…

Large language models (LLMs) have excelled in various applications, yet serving them at scale is challenging due to their substantial resource demands and high latency. Our real-world studies reveal that over 70% of user requests to LLMs…