Related papers: Adaptive encodings for small and fast compressed s…

Blind source separation (BSS) plays a pivotal role in modern astrophysics by enabling the extraction of scientifically meaningful signals from multi-frequency observations. Traditional BSS methods, such as those relying on fixed wavelet…

We show that the compressed suffix array and the compressed suffix tree for a string of length $n$ over an integer alphabet of size $\sigma\leq n$ can both be built in $O(n)$ (randomized) time using only $O(n\log\sigma)$ bits of working…

Recent advances demonstrate that increasing inference-time computation can significantly boost the reasoning capabilities of large language models (LLMs). Although repeated sampling (i.e., generating multiple candidate outputs) is a highly…

We investigate properties of the bijective Burrows-Wheeler transform (BBWT). We show that for any string $w$, a bidirectional macro scheme of size $O(r_B)$ can be induced from the BBWT of $w$, where $r_B$ is the number of maximal character…

The Burrows-Wheeler transform (BWT) is used by the bzip2 family of compressors. In this paper, we present a hardware architecture that implements an inplace algorithm to compute the BWT. Our design does not have explicit storage for the…

Automatic Speech Recognition (ASR) still face challenges when recognizing time-variant rare-phrases. Contextual biasing (CB) modules bias ASR model towards such contextually-relevant phrases. During training, a list of biasing phrases are…

Transformer-based architectures have advanced text summarization, yet their quadratic complexity limits scalability on long documents. This paper introduces BiSparse-AAS (Bilinear Sparse Attention with Adaptive Spans), a novel framework…

Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn embeddings which are invariant to distortions of the input sample. However, a…

An algorithm (bliss) is proposed to speed up the construction of slow adaptive walks. Slow adaptive walks are adaptive walks biased towards closer points or smaller move steps. They were previously introduced to explore a search space, e.g.…

Code search is a widely used technique by developers during software development. It provides semantically similar implementations from a large code corpus to developers based on their queries. Existing techniques leverage deep learning…

Large-scale foundation models have demonstrated exceptional performance in language and vision tasks. However, the numerous dense matrix-vector operations involved in these large networks pose significant computational challenges during…

Attention-based contextual biasing approaches have shown significant improvements in the recognition of generic and/or personal rare-words in End-to-End Automatic Speech Recognition (E2E ASR) systems like neural transducers. These…

We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our…

Learned sparse retrieval (LSR) is a family of first-stage retrieval methods that are trained to generate sparse lexical representations of queries and documents for use with an inverted index. Many LSR methods have been recently introduced,…

The era of Big Data has spawned unprecedented interests in developing hashing algorithms for efficient storage and fast nearest neighbor search. Most existing work learn hash functions that are numeric quantizations of feature values in…

Developers often search and reuse existing code snippets in the process of software development. Code search aims to retrieve relevant code snippets from a codebase according to natural language queries entered by the developer. Up to now,…

Symbolic reasoning and neural networks are often considered incompatible approaches. Connectionist models known as Vector Symbolic Architectures (VSAs) can potentially bridge this gap. However, classical VSAs and neural networks are still…

Recently, Cenzato et al.\ proposed a new text index, called the \emph{suffixient array}, which is a subset of the suffix array and supports locating a single pattern occurrence or finding its maximal exact matches (MEMs), assuming random…

Text indexing is a fundamental and well-studied problem. Classic solutions either replace the original text with a compressed representation, e.g., the FM-index and its variants, or keep it uncompressed but attach some redundancy - an index…

In this work, we present an optimization framework for sparse variable-length stop-feedback (VLSF) codes based on a saddlepoint approximation, which jointly optimizes the decoding configuration parameters. Thanks to the analytical…