English
Related papers

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

200 papers

Transformers have increasingly outperformed gated RNNs in obtaining new state-of-the-art results on supervised tasks involving text sequences. Inspired by this trend, we study the question of how Transformer-based models can improve the…

Machine Learning · Computer Science 2020-08-19 Ricky Loynd , Roland Fernandez , Asli Celikyilmaz , Adith Swaminathan , Matthew Hausknecht

Understanding what and how neural networks memorize during training is crucial, both from the perspective of unintentional memorization of potentially sensitive information and from the standpoint of effective knowledge acquisition for…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Yuxin Wen , Yangsibo Huang , Tom Goldstein , Ravi Kumar , Badih Ghazi , Chiyuan Zhang

Recently multimodal transformer models have gained popularity because their performance on language and vision tasks suggest they learn rich visual-linguistic representations. Focusing on zero-shot image retrieval tasks, we study three…

Computation and Language · Computer Science 2021-02-02 Lisa Anne Hendricks , John Mellor , Rosalia Schneider , Jean-Baptiste Alayrac , Aida Nematzadeh

Transformers have demonstrated impressive capabilities across various tasks, yet their performance on compositional problems remains a subject of debate. In this study, we investigate the internal mechanisms underlying Transformers'…

Computation and Language · Computer Science 2025-01-16 Zhongwang Zhang , Pengxiao Lin , Zhiwei Wang , Yaoyu Zhang , Zhi-Qin John Xu

Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the…

Machine Learning · Computer Science 2025-05-29 Zachary Shinnick , Liangze Jiang , Hemanth Saratchandran , Anton van den Hengel , Damien Teney

Large language models (LLMs) can struggle to memorize factual knowledge in their parameters, often leading to hallucinations and poor performance on knowledge-intensive tasks. In this paper, we formalize fact memorization from an…

Computation and Language · Computer Science 2026-04-10 Jiayuan Ye , Vitaly Feldman , Kunal Talwar

This paper addresses the limitations of large language models in understanding long-term context. It proposes a model architecture equipped with a long-term memory mechanism to improve the retention and retrieval of semantic information…

Computation and Language · Computer Science 2025-05-30 Yue Xing , Tao Yang , Yijiashun Qi , Minggu Wei , Yu Cheng , Honghui Xin

Memorization is a fundamental ability of Transformer-based Large Language Models, achieved through learning. In this paper, we propose a paradigm shift by designing an architecture to memorize text directly, bearing in mind the principle…

Transformers provide promising accuracy and have become popular and used in various domains such as natural language processing and computer vision. However, due to their massive number of model parameters, memory and computation…

Machine Learning · Computer Science 2021-07-01 Hamid Tabani , Ajay Balasubramaniam , Shabbir Marzban , Elahe Arani , Bahram Zonooz

Optimization plays a costly and crucial role in developing machine learning systems. In learned optimizers, the few hyperparameters of commonly used hand-designed optimizers, e.g. Adam or SGD, are replaced with flexible parametric…

Machine Learning · Computer Science 2022-07-19 Luke Metz , C. Daniel Freeman , James Harrison , Niru Maheswaranathan , Jascha Sohl-Dickstein

With an increase of dataset availability, the potential for learning from a variety of data sources has increased. One particular method to improve learning from multiple data sources is to embed the data source during training. This allows…

Computation and Language · Computer Science 2021-12-08 Rob van der Goot , Miryam de Lhoneux

Despite their wide adoption, the underlying training and memorization dynamics of very large language models is not well understood. We empirically study exact memorization in causal and masked language modeling, across model sizes and…

Computation and Language · Computer Science 2022-11-04 Kushal Tirumala , Aram H. Markosyan , Luke Zettlemoyer , Armen Aghajanyan

Episodic memory plays a crucial role in various cognitive processes, such as the ability to mentally recall past events. While cognitive science emphasizes the significance of spatial context in the formation and retrieval of episodic…

Machine Learning · Computer Science 2024-03-04 Junmo Cho , Jaesik Yoon , Sungjin Ahn

Numerous recent works target to extend effective context length for language models and various methods, tasks and benchmarks exist to measure model's effective memorization length. However, through thorough investigations, we find…

Computation and Language · Computer Science 2024-10-08 Xinyu Liu , Runsong Zhao , Pengcheng Huang , Chunyang Xiao , Bei Li , Jingang Wang , Tong Xiao , Jingbo Zhu

We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize…

Transformers, as the fundamental deep learning architecture, have demonstrated great capability in reasoning. This paper studies the generalizable first-order logical reasoning ability of transformers with their parameterized knowledge and…

Computation and Language · Computer Science 2025-07-11 Tianshi Zheng , Jiazheng Wang , Zihao Wang , Jiaxin Bai , Hang Yin , Zheye Deng , Yangqiu Song , Jianxin Li

When training a neural network, it will quickly memorise some source-target mappings from your dataset but never learn some others. Yet, memorisation is not easily expressed as a binary feature that is good or bad: individual datapoints lie…

Computation and Language · Computer Science 2023-11-10 Verna Dankers , Ivan Titov , Dieuwke Hupkes

Transfer learning is an exciting area of Natural Language Processing that has the potential to both improve model performance and increase data efficiency. This study explores the effects of varying quantities of target task training data…

Computation and Language · Computer Science 2022-10-24 Josiah Ross , Luke Yoffe , Alon Albalak , William Yang Wang

Deep networks are frequently tuned to novel tasks and continue learning from ongoing data streams. Such sequential training requires consolidation of new and past information, a challenge predominantly addressed by retaining the most…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Subarnaduti Paul , Manuel Brack , Patrick Schramowski , Kristian Kersting , Martin Mundt

Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al.,…

Machine Learning · Computer Science 2024-06-05 Phoebe Klett , Thomas Ahle
‹ Prev 1 3 4 5 6 7 10 Next ›