Related papers: Chunked Lists versus Extensible Arrays for Text In…
Transformer-based embedding models suffer from quadratic computational and linear memory complexity, limiting their utility for long sequences. We propose recurrent architectures as an efficient alternative, introducing a vertically chunked…
Chunking data is obviously no new concept; however, I had never found any data structures that used chunking as the basis of their implementation. I figured that by using chunking alongside concurrency, I could create an extremely fast…
Linked lists have long served as a valuable teaching tool in programming. However, the question arises: Are they truly practical for everyday program use? In most cases, it appears that array-based data structures offer distinct advantages,…
Dividing sentences in chunks of words is a useful preprocessing step for parsing, information extraction and information retrieval. (Ramshaw and Marcus, 1995) have introduced a "convenient" data representation for chunking by converting it…
For text retrieval systems, the assumption that all data structures reside in main memory is increasingly common. In this context, we present a novel incremental inverted indexing algorithm for web-scale collections that directly constructs…
We present first algorithmic ideas for a practical and lightweight adaption of the DCX suffix array construction algorithm [Sanders et al., 2003] to the distributed-memory setting. Our approach relies on a bucketing technique which enables…
We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems. In our study, 36 segmentation methods spanning…
Chunked codes are efficient random linear network coding (RLNC) schemes with low computational cost, where the input packets are encoded into small chunks (i.e., subsets of the coded packets). During the network transmission, RLNC is…
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…
Answering time-sensitive questions from long documents requires temporal reasoning over the times in questions and documents. An important open question is whether large language models can perform such reasoning solely using a provided…
As long-context language modeling becomes increasingly important, the cost of maintaining and attending to large Key/Value (KV) caches grows rapidly, becoming a major bottleneck in both training and inference. While prior works such as…
Inverted indexes are vital in providing fast key-word-based search. For every term in the document collection, a list of identifiers of documents in which the term appears is stored, along with auxiliary information such as term frequency,…
Efficiently querying data on embedded sensor and IoT devices is challenging given the very limited memory and CPU resources. With the increasing volumes of collected data, it is critical to process, filter, and manipulate data on the edge…
We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an…
Linear RNNs with gating recently demonstrated competitive performance compared to Transformers in language modeling. Although their linear compute scaling in sequence length offers theoretical runtime advantages over Transformers, realizing…
The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically…
Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…
We propose two suffix array inspired full-text indexes. One, called SA-hash, augments the suffix array with a hash table to speed up pattern searches due to significantly narrowed search interval before the binary search phase. The other,…
We consider strategies to organize easily updatable associative arrays in external memory. These arrays are used for full-text search. We study indexes with different keys: single word form, two word forms, and sequences of word forms. The…
Many applications need to process massive streams of spatio-textual data in real-time against continuous spatio-textual queries. For example, in location-aware ad targeting publish/subscribe systems, it is required to disseminate millions…