English
Related papers

Related papers: Exploring and Reshaping the Weight Distribution in…

200 papers

Linear codes with a few weights can be applied to communication, consumer electronics and data storage system. In addition, the weight hierarchy of linear codes has many applications such as on the type II wire-tap channel, dealing with…

Information Theory · Computer Science 2021-06-08 Fei Li , Xiumei Li

The success of today's large language models (LLMs) depends on the observation that larger models perform better. However, the origin of this neural scaling law, that loss decreases as a power law with model size, remains unclear. We…

Machine Learning · Computer Science 2026-05-05 Yizhou Liu , Ziming Liu , Jeff Gore

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

Computers and Society · Computer Science 2025-06-11 Bryan Chen Zhengyu Tan , Roy Ka-Wei Lee

Large Language Models (LLMs) have recently been successfully applied to regression tasks -- such as time series forecasting and tabular prediction -- by leveraging their in-context learning abilities. However, their autoregressive decoding…

Machine Learning · Computer Science 2026-03-04 Julianna Piskorz , Katarzyna Kobalczyk , Mihaela van der Schaar

Neural networks enjoy widespread use, but many aspects of their training, representation, and operation are poorly understood. In particular, our view into the training process is limited, with a single scalar loss being the most common…

Machine Learning · Computer Science 2020-03-04 Janice Lan , Rosanne Liu , Hattie Zhou , Jason Yosinski

Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token prediction training could contribute to this, because each…

Computation and Language · Computer Science 2025-03-13 Falko Helm , Nico Daheim , Iryna Gurevych

Large Language Models (LLMs) inherently encode a wealth of knowledge within their parameters through pre-training on extensive corpora. While prior research has delved into operations on these parameters to manipulate the underlying…

Computation and Language · Computer Science 2024-05-09 Ming Zhong , Chenxin An , Weizhu Chen , Jiawei Han , Pengcheng He

We explore on-device self-supervised collaborative fine-tuning of large language models with limited local data availability. Taking inspiration from the collaborative learning community, we introduce three distinct trust-weighted gradient…

Computation and Language · Computer Science 2024-08-08 Nicolas Wagner , Dongyang Fan , Martin Jaggi

In this paper, we introduce \textbf{Share}d \textbf{Lo}w \textbf{R}ank \textbf{A}daptation (ShareLoRA), a Large Language Model (LLM) fine-tuning technique that balances parameter efficiency, adaptability, and robustness without compromising…

Computation and Language · Computer Science 2025-05-20 Yurun Song , Junchen Zhao , Ian G. Harris , Sangeetha Abdu Jyothi

The determination of the weight distribution of linear codes has been a fascinating problem since the very beginning of coding theory. There has been a lot of research on weight enumerators of special cases, such as self-dual codes and…

Combinatorics · Mathematics 2021-09-28 Alessio Meneghetti , Marco Pellegrini , Massimiliano Sala

We show that a language model's ability to predict text is tightly linked to the breadth of its embedding space: models that spread their contextual representations more widely tend to achieve lower perplexity. Concretely, we find that…

Computation and Language · Computer Science 2026-04-21 Yanhong Li , Ming Li , Karen Livescu , Jiawei Zhou

Large Language Models (LLMs) are known for their expensive and time-consuming training. Thus, oftentimes, LLMs are fine-tuned to address a specific task, given the pretrained weights of a pre-trained LLM considered a foundation model. In…

Computation and Language · Computer Science 2025-12-05 Eshed Gal , Moshe Eliasof , Javier Turek , Uri Ascher , Eran Treister , Eldad Haber

We consider the problem of learning Relational Logistic Regression (RLR). Unlike standard logistic regression, the features of RLRs are first-order formulae with associated weight vectors instead of scalar weights. We turn the problem of…

We study the capability to learn and to generate long-range, power-law correlated sequences by a fully connected asymmetric network. The focus is set on the ability of neural networks to extract statistical features from a sequence. We…

Disordered Systems and Neural Networks · Physics 2016-08-31 A. Priel , I. Kanter

This paper introduces two learning schemes for distributed agents in Reinforcement Learning (RL) environments, namely Reward-Weighted (R-Weighted) and Loss-Weighted (L-Weighted) gradient merger. The R/L weighted methods replace standard…

Machine Learning · Computer Science 2024-08-20 Martin Holen , Per-Arne Andersen , Kristian Muri Knausgård , Morten Goodwin

LoRA achieves remarkable resource efficiency and comparable performance when adapting LLMs for specific tasks. Since ChatGPT demonstrated superior performance on various tasks, there has been a growing desire to adapt one model for all…

Machine Learning · Computer Science 2023-11-21 Yiming Wang , Yu Lin , Xiaodong Zeng , Guannan Zhang

We analytically derive the geometrical structure of the weight space in multilayer neural networks (MLN), in terms of the volumes of couplings associated to the internal representations of the training set. Focusing on the parity and…

Condensed Matter · Physics 2016-08-31 R. Monasson , R. Zecchina

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

Low-rank Adaptation (LoRA) has demonstrated remarkable capabilities for task specific fine-tuning. However, in scenarios that involve multiple tasks, training a separate LoRA model for each one results in considerable inefficiency in terms…

Computation and Language · Computer Science 2025-07-08 Yihua Shao , Minxi Yan , Yang Liu , Siyu Chen , Wenjie Chen , Xinwei Long , Ziyang Yan , Lei Li , Chenyu Zhang , Nicu Sebe , Hao Tang , Yan Wang , Hao Zhao , Mengzhu Wang , Jingcai Guo

Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion, which brings considerable costs to both model training and inference. However, existing methods such as model quantization, knowledge…

Computation and Language · Computer Science 2024-10-16 Yifei Yang , Zouying Cao , Hai Zhao