Related papers: Sparse Radial Sampling LBP for Writer Identificati…

Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the use of highly compressed draft models. In this work, we introduce Self-Distilled…

We propose a nonparametric method for detecting nonlinear causal relationship within a set of multidimensional discrete time series, by using sparse additive models (SpAMs). We show that, when the input to the SpAM is a $\beta$-mixing time…

There are two types of information in each handwritten word image: explicit information which can be easily read or derived directly, such as lexical content or word length, and implicit attributes such as the author's identity. Whether…

Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously…

In complex visual recognition tasks it is typical to adopt multiple descriptors, that describe different aspects of the images, for obtaining an improved recognition performance. Descriptors that have diverse forms can be fused into a…

Text independent writer identification is a challenging problem that differentiates between different handwriting styles to decide the author of the handwritten text. Earlier writer identification relied on handcrafted features to reveal…

Insufficient prior knowledge of a captured hyperspectral image (HSI) scene may lead the experts or the automatic labeling systems to offer incorrect labels or ambiguous labels (i.e., assigning each training sample to a group of candidate…

Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of trainable parameters and lower memory usage, they do not decrease computational cost.…

In this paper, a high performance face recognition system based on local binary pattern (LBP) using the probability distribution functions (PDF) of pixels in different mutually independent color channels which are robust to frontal…

We present sparse topical coding (STC), a non-probabilistic formulation of topic models for discovering latent representations of large collections of data. Unlike probabilistic topic models, STC relaxes the normalization constraint of…

A new line of research for feature selection based on neural networks has recently emerged. Despite its superiority to classical methods, it requires many training iterations to converge and detect informative features. The computational…

Watermarking LLM-generated text is critical for content attribution and misinformation prevention. However, existing methods compromise text quality, require white-box model access and logit manipulation. These limitations exclude API-based…

Distilling state-of-the-art transformer models into lightweight student models is an effective way to reduce computation cost at inference time. The student models are typically compact transformers with fewer parameters, while expensive…

Many Natural Language Processing (NLP) related applications involves topics and sentiments derived from short documents such as consumer reviews and social media posts. Topics and sentiments of short documents are highly sparse because a…

We present a novel approach to the formulation and the resolution of sparse Linear Discriminant Analysis (LDA). Our proposal, is based on penalized Optimal Scoring. It has an exact equivalence with penalized LDA, contrary to the multi-class…

Sparse dictionary coding represents signals as linear combinations of a few dictionary atoms. It has been applied to images, time series, graph signals and multi-way spatio-temporal data by jointly employing temporal and spatial…

We investigate the use of sparse coding and dictionary learning in the context of multitask and transfer learning. The central assumption of our learning method is that the tasks parameters are well approximated by sparse linear…

Semantic Textual Similarity (STS) is a crucial component of many Natural Language Processing (NLP) applications. However, existing approaches typically reduce semantic nuances to a single score, limiting interpretability. To address this,…

The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language…

Sensor selection is an important design problem in large-scale sensor networks. Sensor selection can be interpreted as the problem of selecting the best subset of sensors that guarantees a certain estimation performance. We focus on…