English
Related papers

Related papers: Memory Mosaics at scale

200 papers

Large language models have demonstrated an impressive ability to perform factual recall. Prior work has found that transformers trained on factual recall tasks can store information at a rate proportional to their parameter count. In our…

Machine Learning · Computer Science 2024-12-10 Eshaan Nichani , Jason D. Lee , Alberto Bietti

In this work, we propose a new class of learnable optimizers, called \textit{Mnemosyne}. It is based on the novel spatio-temporal low-rank implicit attention Transformers that can learn to train entire neural network architectures,…

Machine Learning · Computer Science 2023-06-21 Deepali Jain , Krzysztof Marcin Choromanski , Avinava Dubey , Sumeet Singh , Vikas Sindhwani , Tingnan Zhang , Jie Tan

Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…

Computation and Language · Computer Science 2025-08-11 Derek Yotheringhay , Alistair Kirkland , Humphrey Kirkbride , Josiah Whitesteeple

Rehearsal is one of the key techniques for mitigating catastrophic forgetting and has been widely adopted in continual learning algorithms due to its simplicity and practicality. However, the theoretical understanding of how rehearsal scale…

Machine Learning · Computer Science 2026-02-25 JinLi He , Liang Bai , Xian Yang

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable.…

Machine Learning · Statistics 2023-11-08 Alberto Bietti , Vivien Cabannes , Diane Bouchacourt , Herve Jegou , Leon Bottou

Subword tokenization is a common method for vocabulary building in Neural Machine Translation (NMT) models. However, increasingly complex tasks have revealed its disadvantages. First, a vocabulary cannot be modified once it is learned,…

Computation and Language · Computer Science 2024-08-13 Langlin Huang , Yang Feng

Language models (LMs) require robust episodic grounding-the capacity to learn from and apply past experiences-to excel at physical planning tasks. Current episodic grounding approaches struggle with scalability and integration, limiting…

Computation and Language · Computer Science 2025-06-03 Chunhui Zhang , Sirui , Wang , Zhongyu Ouyang , Xiangchi Yuan , Soroush Vosoughi

The performance of machine learning models can significantly degrade under distribution shifts of the data. We propose a new method for classification which can improve robustness to distribution shifts, by combining expert knowledge about…

Machine Learning · Computer Science 2022-08-31 Souradeep Dutta , Yahan Yang , Elena Bernardis , Edgar Dobriban , Insup Lee

In this paper, we share our reflections and insights on understanding Transformer architectures through the lens of associative memory--a classic psychological concept inspired by human cognition. We start with the basics of associative…

Machine Learning · Computer Science 2025-05-27 Shu Zhong , Mingyu Xu , Tenglong Ao , Guang Shi

Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inference-time memory requirements from the key-value cache.…

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

Machine Learning · Computer Science 2025-10-13 Destiny Okpekpe , Antonio Orvieto

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Memory plays a pivotal role in enabling large language model~(LLM)-based agents to engage in complex and long-term interactions, such as question answering (QA) and dialogue systems. While various memory modules have been proposed for these…

Computation and Language · Computer Science 2024-12-23 Ruihong Zeng , Jinyuan Fang , Siwei Liu , Zaiqiao Meng

Recent studies have demonstrated that the performance of transformers on the task of language modeling obeys a power-law relationship with model size over six orders of magnitude. While transformers exhibit impressive scaling, their…

Machine Learning · Computer Science 2021-10-07 Narsimha Chilkuri , Eric Hunsberger , Aaron Voelker , Gurshaant Malik , Chris Eliasmith

The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…

Computation and Language · Computer Science 2025-03-31 Zhuo-Yang Song , Zeyu Li , Qing-Hong Cao , Ming-xing Luo , Hua Xing Zhu

Recent work has shown that memory modules are crucial for the generalization ability of neural networks on learning simple algorithms. However, we still have little understanding of the working mechanism of memory modules. To alleviate this…

Machine Learning · Computer Science 2019-07-02 Kexin Wang , Yu Zhou , Shaonan Wang , Jiajun Zhang , Chengqing Zong

Large language models (LLMs) are very performant connectionist systems, but do they exhibit more compositionality? More importantly, is that part of why they perform so well? We present empirical analyses across four LLM families (12…

Computation and Language · Computer Science 2025-05-21 Ruchira Dhar , Anders Søgaard

Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for…

Image and Video Processing · Electrical Eng. & Systems 2020-04-21 Andreas Hauptmann , Jonas Adler , Simon Arridge , Ozan Öktem

We study the capabilities of the transformer architecture with varying depth. Specifically, we designed a novel set of sequence learning tasks to systematically evaluate and comprehend how the depth of transformer affects its ability to…

Machine Learning · Computer Science 2024-04-03 Xingwu Chen , Difan Zou

Systematic generalization refers to the capacity to understand and generate novel combinations from known components. Despite recent progress by large language models (LLMs) across various domains, these models often fail to extend their…

Artificial Intelligence · Computer Science 2026-02-27 Philipp Mondorf , Shijia Zhou , Monica Riedler , Barbara Plank