English
Related papers

Related papers: Same Geometry, Opposite Noise: Transformer Magnitu…

200 papers

Representational similarity analysis and related methods have become standard tools for comparing the internal geometries of neural networks and biological systems. These methods measure what is represented, the alignment between two…

Machine Learning · Computer Science 2026-04-21 Prashant C. Raju

Although transformer-based models have shown strong performance in word- and sentence-level tasks, effectively representing long documents, especially in fields like law and medicine, remains difficult. Sparse attention mechanisms can…

Computation and Language · Computer Science 2026-01-01 Waheed Ahmed Abro , Zied Bouraoui

Visual Language Models (VLMs) have achieved remarkable progress, yet their reliability under small, meaning-preserving input changes remains poorly understood. We present the first large-scale, systematic study of VLM robustness to benign…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Amir Rosenfeld , Neta Glazer , Ethan Fetaya

This computer science master thesis aims at modelling the nonlinearities of a loudspeaker. A piecewise linear approximation is initially explored and then we present a nonlinear Volterra model to simulate the behavior of the system. The…

Sound · Computer Science 2017-03-02 Alessandro Loriga

We provide high-probability sample complexity guarantees for exact structure recovery and accurate predictive learning using noise-corrupted samples from an acyclic (tree-shaped) graphical model. The hidden variables follow a…

Machine Learning · Statistics 2021-02-18 Konstantinos E. Nikolakakis , Dionysios S. Kalogerias , Anand D. Sarwate

Large language models (LLMs) have complicated internal dynamics, but induce representations of words and phrases whose geometry we can study. Human language processing is also opaque, but neural response measurements can provide (noisy)…

Computation and Language · Computer Science 2023-11-01 Jiaang Li , Antonia Karamolegkou , Yova Kementchedjhieva , Mostafa Abdou , Sune Lehmann , Anders Søgaard

Reproducibility must validate architectural robustness, not just numerical accuracy. We evaluate ColBERT-v2 and ConstBERT across five dimensions, finding that while ConstBERT reproduces within 0.05% MRR@10 on MS-MARCO, both models show a…

Information Retrieval · Computer Science 2026-04-17 Utshab Kumar Ghosh , Ashish David , Shubham Chatterjee

We test whether the causal inner product of \citet{park2024linear} -- defined by the unembedding covariance $\Sigma$ -- enables cross-lingual concept transport. Across 17 models and 4 language pairs, a matched-spectrum randomization test…

Machine Learning · Computer Science 2026-05-05 Pratyush Acharya , Nuraj Rimal , Habish Dhakal

The articulatory geometric configurations of the vocal tract and the acoustic properties of the resultant speech sound are considered to have a strong causal relationship. This paper aims at finding a joint latent representation between the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-02 Pramit Saha , Sidney Fels

Recent advancements in Large Speech-Language Models have significantly bridged the gap between acoustic signals and linguistic understanding. However, a persistent performance disparity remains in speech-based input tasks compared to direct…

Computation and Language · Computer Science 2026-03-03 Ming-Hao Hsu , Xueyao Zhang , Xiaohai Tian , Jun Zhang , Zhizheng Wu

A significant obstacle in the development of robust machine learning models is covariate shift, a form of distribution shift that occurs when the input distributions of the training and test sets differ while the conditional label…

Machine Learning · Statistics 2021-11-17 Nilesh Tripuraneni , Ben Adlam , Jeffrey Pennington

We measure shifts of the acoustic scale due to nonlinear growth and redshift distortions to a high precision using a very large volume of high-force-resolution simulations. We compare results from various sets of simulations that differ in…

Large Language Models (LLMs) perform internal computations in continuous vector spaces yet produce discrete tokens -- a fundamental mismatch whose geometric consequences remain poorly understood. We develop a mathematical framework that…

Machine Learning · Computer Science 2026-03-25 Mohamed A. Mabrok

Sparse auto-encoders are useful for extracting low-dimensional representations from high-dimensional data. However, their performance degrades sharply when the input noise at test time differs from the noise employed during training. This…

Machine Learning · Computer Science 2024-07-01 Nelson Goldenstein , Jeremias Sulam , Yaniv Romano

Different transformer architectures implement identical linguistic computations via distinct connectivity patterns, yielding model imprinted ``computational fingerprints'' detectable through spectral analysis. Using graph signal processing…

Computation and Language · Computer Science 2025-10-23 Valentin Noël

Model collapse, the progressive degradation of LLMs trained on their own outputs, has been characterized statistically but lacks a linguistic explanation for which structures degrade, in what order, and why. We show that iterated learning…

Computation and Language · Computer Science 2026-05-25 Dongxin Guo , Jikun Wu , Siu Ming Yiu

A simple sparse coding mechanism appears in the sensory systems of several organisms: to a coarse approximation, an input $x \in \R^d$ is mapped to much higher dimension $m \gg d$ by a random linear transformation, and is then sparsified by…

Neural and Evolutionary Computing · Computer Science 2020-06-09 Sanjoy Dasgupta , Christopher Tosh

In this paper, we consider asymptotic properties of the support vector machine (SVM) in high-dimension, low-sample-size (HDLSS) settings. We show that the hard-margin linear SVM holds a consistency property in which misclassification rates…

Machine Learning · Statistics 2017-02-28 Yugo Nakayama , Kazuyoshi Yata , Makoto Aoshima

The distortion-rate performance of certain randomly-designed scalar quantizers is determined. The central results are the mean-squared error distortion and output entropy for quantizing a uniform random variable with thresholds drawn…

Information Theory · Computer Science 2012-01-04 Vivek K Goyal

The success of machine learning has resulted from its structured representation of data. Similar data have close internal representations as compressed codes for classification or emerged labels for clustering. We observe that the frequency…

Machine Learning · Computer Science 2022-04-13 Sungyeop Lee , Junghyo Jo
‹ Prev 1 4 5 6 7 8 10 Next ›