Related papers: Fully Online Grammar Compression in Constant Space
We propose a special-purpose class of compression algorithms for efficient compression of Prolog programs. It is a dictionary-based compression method, specially designed for the compression of Prolog code, and therefore we name it PCA…
Transformer-based Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant responses. This constraint restricts their applicability in scenarios involving long…
Despite their remarkable achievements, modern Large Language Models (LLMs) face exorbitant computational and memory footprints. Recently, several works have shown significant success in training-free and data-free compression (pruning and…
Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose LLoCO, a…
We explore an extension to straight-line programs (SLPs) that outperforms, for some text families, the measure $\delta$ based on substring complexity, a lower bound for most measures and compressors exploiting repetitiveness (which are…
Computation on compressed strings is one of the key approaches to processing massive data sets. We consider local subsequence recognition problems on strings compressed by straight-line programs (SLP), which is closely related to…
In this work, we study the online robust principal components' analysis (RPCA) problem. In recent work, RPCA has been defined as a problem of separating a low-rank matrix (true data), $L$, and a sparse matrix (outliers), $S$, from their…
A Straight-Line Program (SLP) for a string $T$ is a context-free grammar in Chomsky normal form that derives $T$ only, which can be seen as a compressed form of $T$. Kida et al.\ introduced collage systems [Theor. Comput. Sci., 2003] to…
Despite the recent success of Large Language Models (LLMs), it remains challenging to feed LLMs with long prompts due to the fixed size of LLM inputs. As a remedy, prompt compression becomes a promising solution by removing redundant tokens…
Structured data, such as tables, graphs, and databases, play a critical role in plentiful NLP tasks such as question answering and dialogue system. Recently, inspired by Vision-Language Models, Graph Neutral Networks (GNNs) have been…
A compressed self-index stores a string in compressed form while supporting locate queries without decompression. For highly repetitive strings (arising in web crawls, versioned documents, and genomic collections), static self-indexes can…
We study the problem of enumerating results from a query over a compressed document. The model we use for compression are straight-line programs (SLPs), which are defined by a context-free grammar that produces a single string. For our…
We consider the problem of evaluating regular spanners over compressed documents, i.e., we wish to solve evaluation tasks directly on the compressed data, without decompression. As compressed forms of the documents we use straight-line…
Large Language Models (LLMs) have achieved remarkable performance across a wide range of Natural Language Processing (NLP) tasks. However, in long-context scenarios, they face two challenges: high computational cost and information…
We present an algorithm for computing the Lyndon factorization of a string that is given in grammar compressed form, namely, a Straight Line Program (SLP). The algorithm runs in $O(n^4 + mn^3h)$ time and $O(n^2)$ space, where $m$ is the…
Parameter-Efficient Fine-Tuning (PEFT), particularly Low-Rank Adaptation (LoRA), has become a standard approach for adapting Large Language Models (LLMs) under limited compute. However, in continual settings where models are updated…
In this paper, a compressed membership problem for finite automata, both deterministic and non-deterministic, with compressed transition labels is studied. The compression is represented by straight-line programs (SLPs), i.e. context-free…
The rise of large language models (LLMs) is revolutionizing information retrieval, question answering, summarization, and code generation tasks. However, in addition to confidently presenting factually inaccurate information at times (known…
The rapid growth of high-resolution scientific simulations and observation systems is generating massive spatiotemporal datasets, making efficient, error-bounded compression increasingly important. Meanwhile, decoder-only large language…
Large Language Models (LLMs) exhibit strong capabilities in text processing, and recent research has augmented SQL and DataFrame with LLM-powered semantic operators for data analysis. However, LLM-based data processing is hindered by slower…