English
Related papers

Related papers: Structure and Redundancy in Large Language Models:…

200 papers

We study the emergence of multi-step reasoning in deep Transformer language models through a geometric and statistical-physics lens. Treating the hidden-state trajectory as a flow on an implicit Riemannian manifold, we analyze the layerwise…

Machine Learning · Computer Science 2026-01-29 Faruk Alpay , Bugra Kilictas

Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A distinctive ability of these reasoning models is…

Artificial Intelligence · Computer Science 2025-12-17 Ge Yan , Chung-En Sun , Tsui-Wei , Weng

A central challenge in representation learning is constructing latent embeddings that are both expressive and efficient. In practice, deep networks often produce redundant latent spaces where multiple coordinates encode overlapping…

Machine Learning · Computer Science 2025-09-09 Mehmet Can Yavuz , Berrin Yanikoglu

Deep neural networks come in many sizes and architectures. The choice of architecture, in conjunction with the dataset and learning algorithm, is commonly understood to affect the learned neural representations. Yet, recent results have…

Machine Learning · Computer Science 2024-07-08 Loek van Rossem , Andrew M. Saxe

Graph representation learning has become a standard approach for analyzing networked data, with latent embeddings widely used for link prediction, community detection, and related tasks. Yet a basic design choice, the latent dimension, is…

Knowledge Tracing (KT) infers a student's knowledge state from past interactions to predict future performance. Conventional Deep Learning (DL)-based KT models are typically tied to platform-specific identifiers and latent representations,…

Artificial Intelligence · Computer Science 2026-04-23 Zhiyi Duan , Hongyu Yuan , Rui Liu

Neural network-based language models deal with data sparsity problems by mapping the large discrete space of words into a smaller continuous space of real-valued vectors. By learning distributed vector representations for words, each…

Computation and Language · Computer Science 2018-09-27 Davide Nunes , Luis Antunes

Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated remarkable potential in enhancing the reasoning capability of Large Reasoning Models (LRMs). However, RLVR often drives the policy toward over-determinism,…

Machine Learning · Computer Science 2026-03-23 Shimin Zhang , Xianwei Chen , Yufan Shen , Ziyuan Ye , Jibin Wu

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

Machine Learning · Computer Science 2026-05-20 Zhipeng Zhang

This work considers the problem of learning the structure of multivariate linear tree models, which include a variety of directed tree graphical models with continuous, discrete, and mixed latent variables such as linear-Gaussian models,…

Machine Learning · Computer Science 2011-11-09 Animashree Anandkumar , Kamalika Chaudhuri , Daniel Hsu , Sham M. Kakade , Le Song , Tong Zhang

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in…

Computation and Language · Computer Science 2025-03-26 Joseph Sakau , Evander Kozlowski , Roderick Thistledown , Basil Steinberger

Understanding the behavior of deep networks is crucial to increase our confidence in their results. Despite an extensive body of work for explaining their predictions, researchers have faced reliability issues, which can be attributed to…

Machine Learning · Computer Science 2025-08-15 Amir Mehrpanah , Erik Englesson , Hossein Azizpour

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks.…

Computation and Language · Computer Science 2024-11-21 Luohe Shi , Yao Yao , Zuchao Li , Lefei Zhang , Hai Zhao

Evaluating whether large language models (LLMs) capture the structure of natural language beyond local fluency remains an open challenge. Existing evaluation methods, largely based on task performance or short-context behavior, provide…

Computation and Language · Computer Science 2026-05-26 Kumiko Tanaka-Ishii

This study investigates the internal representations of verb-particle combinations within transformer-based large language models (LLMs), specifically examining how these models capture lexical and syntactic nuances at different neural…

Computation and Language · Computer Science 2024-12-20 Hassane Kissane , Achim Schilling , Patrick Krauss

In large language models (LLMs), each block operates on the residual stream to map input token sequences to output token distributions. However, most of the interpretability literature focuses on internal latent representations, leaving…

Machine Learning · Computer Science 2026-02-03 Riccardo Ali , Francesco Caso , Christopher Irwin , Pietro Liò

Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular…

Artificial Intelligence · Computer Science 2026-03-13 Junnan Dong , Chuang Zhou , Zheng Yuan , Yifei Yu , Qiufeng Wang , Yinghui Li , Siyu An , Di Yin , Xing Sun , Feiyue Huang

Deep Recurrent Neural Network architectures, though remarkably capable at modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while many problems in computer vision inherently have an underlying high-level…

Computer Vision and Pattern Recognition · Computer Science 2016-04-12 Ashesh Jain , Amir R. Zamir , Silvio Savarese , Ashutosh Saxena

Random Matrix Theory (RMT) is capable of making predictions for the spectral fluctuations of a physical system only after removing the influence of the level density by unfolding the spectra. When the level density is known, unfolding is…

Statistical Mechanics · Physics 2013-12-16 Ashraf A. Abul-Magd , Adel Y. Abul-Magd

Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning models achieve high accuracy, they often lack…

Computation and Language · Computer Science 2026-03-25 Runze Li , Kedi Chen , Guwei Feng , Mo Yu , Jun Wang , Wei Zhang
‹ Prev 1 3 4 5 6 7 10 Next ›