English
Related papers

Related papers: Capacity Matters: a Proof-of-Concept for Transform…

200 papers

As robotics continues to advance, the need for adaptive and continuously-learning embodied agents increases, particularly in the realm of assistance robotics. Quick adaptability and long-term information retention are essential to operate…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Paolo Cudrano , Xiaoyu Luo , Matteo Matteucci

Training Memory-based transformers can require a large amount of memory and can be quite inefficient. We propose a novel two-phase training mechanism and a novel regularization technique to improve the training efficiency of memory-based…

Machine Learning · Computer Science 2023-11-15 Vishwajit Kumar Vishnu , C. Chandra Sekhar

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya

Recent advances in Deep Learning have led to a significant performance increase on several NLP tasks, however, the models become more and more computationally demanding. Therefore, this paper tackles the domain of computationally efficient…

Computation and Language · Computer Science 2022-05-18 Pedro Alonso , Kumar Shridhar , Denis Kleyko , Evgeny Osipov , Marcus Liwicki

In this work, we present compelling evidence that controlling model capacity during fine-tuning can effectively mitigate memorization in diffusion models. Specifically, we demonstrate that adopting Parameter-Efficient Fine-Tuning (PEFT)…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Raman Dutt , Pedro Sanchez , Ondrej Bohdal , Sotirios A. Tsaftaris , Timothy Hospedales

In this preregistration submission, we propose an empirical study of how networks handle changes in complexity of the data. We investigate the effect of network capacity on generalization performance in the face of increasing data…

Machine Learning · Computer Science 2019-11-12 Emir Konuk , Kevin Smith

In human-level NLP tasks, such as predicting mental health, personality, or demographics, the number of observations is often smaller than the standard 768+ hidden state sizes of each layer within modern transformer-based language models,…

Computation and Language · Computer Science 2023-06-05 Adithya V Ganesan , Matthew Matero , Aravind Reddy Ravula , Huy Vu , H. Andrew Schwartz

This study investigates the mechanisms and factors influencing memorization in fine-tuned large language models (LLMs), with a focus on the medical domain due to its privacy-sensitive nature. We examine how different aspects of the…

Computation and Language · Computer Science 2025-08-06 Danil Savine

Knowledge Tracing (KT) models face a critical ``Performance-Complexity Trap'': capturing complex cognitive dynamics like learning sessions and memory decay typically requires deep hierarchical architectures, which incur prohibitive…

Artificial Intelligence · Computer Science 2025-12-09 Xiao-li Xia , Hou-biao Li

It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…

Machine Learning · Computer Science 2025-02-07 Zihao Huang , Qiyang Min , Hongzhi Huang , Defa Zhu , Yutao Zeng , Ran Guo , Xun Zhou

The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well, despite being able to perfectly fit (memorise) completely random labels. To…

Machine Learning · Computer Science 2023-10-10 Michal Lukasik , Vaishnavh Nagarajan , Ankit Singh Rawat , Aditya Krishna Menon , Sanjiv Kumar

In Transformers, Position Embeddings (PEs) significantly influence Length Generalization (LG) performance, yet their fundamental role remains unclear. In this work, we investigate the limitations and capabilities of PEs in achieving LG. We…

Machine Learning · Computer Science 2025-10-07 Yang Chen , Yitao Liang , Zhouchen Lin

The Transformer architecture has become prominent in developing large causal language models. However, mechanisms to explain its capabilities are not well understood. Focused on the training process, here we establish a meta-learning view…

Machine Learning · Computer Science 2024-03-26 Xinbo Wu , Lav R. Varshney

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Learned embeddings are widely used to obtain concise data representation and enable transfer learning between different data sets and tasks. In this paper, we present Silhouette, our approach that leverages publicly-available performance…

Machine Learning · Computer Science 2022-12-16 Tarikul Islam Papon , Abdul Wasay

Scaling laws describe the relationship between the size of language models and their capabilities. Unlike prior studies that evaluate a model's capability via loss or benchmarks, we estimate the number of knowledge bits a model stores. We…

Computation and Language · Computer Science 2024-04-09 Zeyuan Allen-Zhu , Yuanzhi Li

Understanding the transformer architecture and its workings is essential for machine learning (ML) engineers. However, truly understanding the transformer architecture can be demanding, even if you have a solid background in machine…

Machine Learning · Computer Science 2025-02-28 Joni-Kristian Kämäräinen

We study the performance of transformers as a function of the number of repetitions of training examples with algorithmically generated datasets. On three problems of mathematics: the greatest common divisor, modular multiplication, and…

Machine Learning · Computer Science 2024-10-10 François Charton , Julia Kempe

To enable embodied agents to operate effectively over extended timeframes, it is crucial to develop models that form and access memories to stay contextualized in their environment. In the current paradigm of training transformer-based…

Artificial Intelligence · Computer Science 2025-12-01 Gunshi Gupta , Karmesh Yadav , Zsolt Kira , Yarin Gal , Rahaf Aljundi

Transformers and their attention mechanism have been revolutionary in the field of Machine Learning. While originally proposed for the language data, they quickly found their way to the image, video, graph, etc. data modalities with various…

Machine Learning · Computer Science 2025-09-22 Saeed Amizadeh , Sara Abdali , Yinheng Li , Kazuhito Koishida