English
Related papers

Related papers: Convergent Evolution: How Different Language Model…

200 papers

Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that leverages the capabilities of language models to interpret the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Saeid Asgari Taghanaki , Aliasghar Khani , Ali Saheb Pasand , Amir Khasahmadi , Aditya Sanghi , Karl D. D. Willis , Ali Mahdavi-Amiri

A substantial gap persists in understanding the reasons behind the exceptional performance of the Transformer architecture in NLP. A particularly unexplored area involves the mechanistic description of how the distribution of parameters…

Computation and Language · Computer Science 2024-03-14 Carlo Nicolini , Jacopo Staiano , Bruno Lepri , Raffaele Marino

Transformers have achieved state-of-the-art performance in morphological inflection tasks, yet their ability to generalize across languages and morphological rules remains limited. One possible explanation for this behavior can be the…

Computation and Language · Computer Science 2025-06-03 Gal Astrach , Yuval Pinter

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled…

Computer Vision and Pattern Recognition · Computer Science 2015-09-09 Ross Goroshin , Joan Bruna , Jonathan Tompson , David Eigen , Yann LeCun

Molecular generative models often assume meaningful latent geometry, but apparent property predictability can reflect sequence-level shortcuts rather than chemical organization. We study this issue in an unsupervised autoregressive…

Machine Learning · Computer Science 2026-05-08 Zakaria Elabid , Jan Andrzejewski , Bartosz Brzoza , Attila Cangi

What can large language models learn? By definition, language models (LM) are distributions over strings. Therefore, an intuitive way of addressing the above question is to formalize it as a matter of learnability of classes of…

Computation and Language · Computer Science 2025-01-14 Nadav Borenstein , Anej Svete , Robin Chan , Josef Valvoda , Franz Nowak , Isabelle Augenstein , Eleanor Chodroff , Ryan Cotterell

Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable…

Computation and Language · Computer Science 2026-02-25 Jan Philip Wahle

To overcome the restriction of identical distribution assumption, invariant representation learning for unsupervised domain adaptation (UDA) has made significant advances in computer vision and pattern recognition communities. In UDA…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 You-Wei Luo , Chuan-Xian Ren , Xiao-Lin Xu , Qingshan Liu

Real-world datasets are inherently heterogeneous, yet how per-class structural differences and sampling imbalance shape the training dynamics of diffusion models-and potentially exacerbate disparities-remains poorly understood. While models…

Machine Learning · Statistics 2026-05-08 Flavio Nicoletti , Chenxiao Ma , Enrico Ventura , Luca Saglietti , Stefano Sarao Mannelli

How much data is required to learn the structure of a language via next-token prediction? We study this question for synthetic datasets generated via a Probabilistic Context-Free Grammar (PCFG) -- a tree-like generative model that captures…

Computation and Language · Computer Science 2024-10-30 Francesco Cagnetta , Matthieu Wyart

An important characteristic of neural networks is their ability to learn representations of the input data with effective features for prediction, which is believed to be a key factor to their superior empirical performance. To better…

Machine Learning · Computer Science 2022-06-06 Zhenmei Shi , Junyi Wei , Yingyu Liang

Deep learning algorithms are responsible for a technological revolution in a variety of tasks including image recognition or Go playing. Yet, why they work is not understood. Ultimately, they manage to classify data lying in high dimension…

Machine Learning · Computer Science 2021-01-01 Mario Geiger , Leonardo Petrini , Matthieu Wyart

A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate to its function. We take a high-level geometric approach to…

Computation and Language · Computer Science 2025-05-01 Emily Cheng , Diego Doimo , Corentin Kervadec , Iuri Macocco , Jade Yu , Alessandro Laio , Marco Baroni

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al.,…

Machine Learning · Statistics 2024-09-06 Hugo Cui , Luca Pesce , Yatin Dandi , Florent Krzakala , Yue M. Lu , Lenka Zdeborová , Bruno Loureiro

Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…

Machine Learning · Computer Science 2022-10-21 Pavel Izmailov , Polina Kirichenko , Nate Gruver , Andrew Gordon Wilson

Discrete transforms, such as the discrete Fourier transform, are widely used in machine learning to improve model performance by extracting meaningful features. However, with numerous transforms available, selecting an appropriate one often…

Machine Learning · Computer Science 2025-05-09 Gekko Budiutama , Shunsuke Daimon , Hirofumi Nishi , Yu-ichiro Matsushita

We study the problem of learning features through self-supervision that are generalisable to multiple graphs. State-of-the-art graph self-supervision restricts training to only one graph, resulting in graph-specific models that are…

Machine Learning · Computer Science 2024-07-31 Laya Das , Sai Munikoti , Nrushad Joshi , Mahantesh Halappanavar

How do transformer language models represent magnitude? Recent work disagrees: some find logarithmic spacing, others linear encoding, others per-digit circular representations. We apply the formal tools of psychophysics to resolve this.…

Computation and Language · Computer Science 2026-03-24 Jon-Paul Cacioli

Numbers are a basic part of how humans represent and describe the world around them. As a consequence, learning effective representations of numbers is critical for the success of large language models as they become more integrated into…

Computation and Language · Computer Science 2025-02-04 Raja Marjieh , Veniamin Veselovsky , Thomas L. Griffiths , Ilia Sucholutsky

Can recurrent neural nets, inspired by human sequential data processing, learn to understand language? We construct simplified datasets reflecting core properties of natural language as modeled in formal syntax and semantics: recursive…

Computation and Language · Computer Science 2021-12-30 Denis Paperno
‹ Prev 1 8 9 10 Next ›