English
Related papers

Related papers: Disentangling Geometry, Performance, and Training …

200 papers

We investigate how embedding dimension affects the emergence of an internal "world model" in a transformer trained with reinforcement learning to perform bubble-sort-style adjacent swaps. Models achieve high accuracy even with very small…

Machine Learning · Computer Science 2025-10-22 Brady Bhalla , Honglu Fan , Nancy Chen , Tony Yue YU

Vector embeddings derived from large language models (LLMs) show promise in capturing latent information from the literature. Interestingly, these can be integrated into material embeddings, potentially useful for data-driven predictions of…

Computation and Language · Computer Science 2024-09-19 Luke P. J. Gilligan , Matteo Cobelli , Hasan M. Sayeed , Taylor D. Sparks , Stefano Sanvito

Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in…

Machine Learning · Computer Science 2025-04-04 Jiho Choi , Donggyun Kim , Chanhyuk Lee , Seunghoon Hong

We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the…

Machine Learning · Computer Science 2026-01-15 Prudhviraj Naidu , Zixian Wang , Leon Bergen , Ramamohan Paturi

Humans and animals can recognize latent structures in their environment and apply this information to efficiently navigate the world. However, it remains unclear what aspects of neural activity contribute to these computational…

Neurons and Cognition · Quantitative Biology 2024-04-12 Albert J. Wakhloo , Will Slatton , SueYeon Chung

Enforcing orthonormal or isometric property for the weight matrices has been shown to enhance the training of deep neural networks by mitigating gradient exploding/vanishing and increasing the robustness of the learned networks. However,…

Machine Learning · Computer Science 2024-03-01 Zhen Qin , Xuwei Tan , Zhihui Zhu

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

Quantifying robustness in a single measure for the purposes of model selection, development of adversarial training methods, and anticipating trends has so far been elusive. The simplest metric to consider is the number of trainable…

Machine Learning · Computer Science 2024-10-25 David Khachaturov , Robert Mullins

We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples learning the transformation from the source language to the target language into (a)…

Machine Learning · Computer Science 2018-12-19 Pratik Jawanpuria , Arjun Balgovind , Anoop Kunchukuttan , Bamdev Mishra

The history-dependent behaviors of classical plasticity models are often driven by internal variables evolved according to phenomenological laws. The difficulty to interpret how these internal variables represent a history of deformation,…

Machine Learning · Computer Science 2023-01-04 Nikolaos N. Vlassis , WaiChing Sun

Large language models use high-dimensional latent spaces to encode and process textual information. Much work has investigated how the conceptual content of words translates into geometrical relationships between their vector…

Computation and Language · Computer Science 2025-05-26 Raphaël Sarfati , Haley Moller , Toni J. B. Liu , Nicolas Boullé , Christopher Earls

Geometrical interpretations of deep learning models offer insightful perspectives into their underlying mathematical structures. In this work, we introduce a novel approach that leverages differential geometry, particularly concepts from…

Machine Learning · Computer Science 2026-05-04 Sung Moon Ko , Jaewan Lee , Sumin Lee , Soorin Yim , Kyunghoon Bae , Sehui Han

The utility of a learned neural representation depends on how well its geometry supports performance in downstream tasks. This geometry depends on the structure of the inputs, the structure of the target outputs, and the architecture of the…

Machine Learning · Computer Science 2024-01-25 Matteo Alleman , Jack W Lindsey , Stefano Fusi

Deep learning (DL) models have been widely used in materials property prediction with great success, especially for properties with large datasets. However, the out-of-distribution (OOD) performances of such models are questionable,…

Materials Science · Physics 2024-07-23 Nihang Fu , Sadman Sadeed Omee , Jianjun Hu

Reasoning-oriented large language models (RLMs) achieve strong gains on tasks such as mathematics and coding by generating explicit intermediate reasoning. However, their impact on machine translation (MT) remains underexplored. We…

Computation and Language · Computer Science 2026-02-17 Sara Rajaee , Sebastian Vincent , Alexandre Berard , Marzieh Fadaee , Kelly Marchisio , Tom Kocmi

The expanding scale of large neural network models introduces significant challenges, driving efforts to reduce memory usage and enhance computational efficiency. Such measures are crucial to ensure the practical implementation and…

Machine Learning · Computer Science 2025-02-14 Eduardo Lobo Lustosa Cabral , Larissa Driemeier

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind…

Machine Learning · Computer Science 2014-04-24 Yoshua Bengio , Aaron Courville , Pascal Vincent

Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in…

Computation and Language · Computer Science 2024-01-09 Yiming Wang , Jinyu Li

This study explores using embedding rank as an unsupervised evaluation metric for general-purpose speech encoders trained via self-supervised learning (SSL). Traditionally, assessing the performance of these encoders is resource-intensive…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-22 Zakaria Aldeneh , Vimal Thilak , Takuya Higuchi , Barry-John Theobald , Tatiana Likhomanenko

Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric structure. Contrary to the widespread practice of using…

Machine Learning · Computer Science 2026-05-25 Arnesh Batra , Arush Gumber , Aniket Khandelwal , Jashn Khemani , Anubha Gupta