English
Related papers

Related papers: Memory Mosaics at scale

200 papers

Memory is a complex phenomenon that involves several distinct mechanisms. These mechanisms operate at different spatial and temporal levels. This chapter focuses on the theoretical framework and the mathematical models that have been…

Neurons and Cognition · Quantitative Biology 2021-12-22 Stefano Fusi

Long-context efficiency has recently become a trending topic in serving large language models (LLMs). And mixture of depths (MoD) is proposed as a perfect fit to bring down both latency and memory. In this paper, however, we discover that…

Computation and Language · Computer Science 2024-10-21 Chen Zhang , Meizhi Zhong , Qimeng Wang , Xuantao Lu , Zheyu Ye , Chengqiang Lu , Yan Gao , Yao Hu , Kehai Chen , Min Zhang , Dawei Song

Deep features have been proven powerful in building accurate dense semantic correspondences in various previous works. However, the multi-scale and pyramidal hierarchy of convolutional neural networks has not been well studied to learn…

Computer Vision and Pattern Recognition · Computer Science 2021-08-30 Dongyang Zhao , Ziyang Song , Zhenghao Ji , Gangming Zhao , Weifeng Ge , Yizhou Yu

Traditional multimodal retrieval systems rely primarily on bi-encoder architectures, where performance is closely tied to embedding dimensionality. Recent work, Think-Then-Embed (TTE), shows that incorporating multimodal reasoning to elicit…

Learnable embedding vector is one of the most important applications in machine learning, and is widely used in various database-related domains. However, the high dimensionality of sparse data in recommendation tasks and the huge volume of…

Machine Learning · Computer Science 2024-02-14 Hailin Zhang , Penghao Zhao , Xupeng Miao , Yingxia Shao , Zirui Liu , Tong Yang , Bin Cui

Achieving machine intelligence requires a smooth integration of perception and reasoning, yet models developed to date tend to specialize in one or the other; sophisticated manipulation of symbols acquired from rich perceptual spaces has so…

Machine Learning · Computer Science 2018-09-14 Eric Crawford , Guillaume Rabusseau , Joelle Pineau

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

Computation and Language · Computer Science 2023-01-16 Beyza Ermis , Giovanni Zappella , Martin Wistuba , Aditya Rawal , Cedric Archambeau

Large language models (LLMs) have demonstrated remarkable proficiency in understanding and generating responses to complex queries through large-scale pre-training. However, the efficacy of these models in memorizing and reasoning among…

Computation and Language · Computer Science 2024-02-23 Qiyuan He , Yizhong Wang , Wenya Wang

Scaling laws with respect to the amount of training data and the number of parameters allow us to predict the cost-benefit trade-offs of pretraining language models (LMs) in different configurations. In this paper, we consider another…

Computation and Language · Computer Science 2024-07-19 Rulin Shao , Jacqueline He , Akari Asai , Weijia Shi , Tim Dettmers , Sewon Min , Luke Zettlemoyer , Pang Wei Koh

This work explores the challenge of building ``Machines that Can Remember'', framing long-term memory as the problem of efficient ultra-long context modeling. We argue that this requires three key properties: \textbf{sparsity},…

Computation and Language · Computer Science 2025-12-01 Xiang Hu , Zhanchao Zhou , Ruiqi Liang , Zehuan Li , Wei Wu , Jianguo Li

Recent research has explored the memorization capacity of multi-head attention, but these findings are constrained by unrealistic limitations on the context size. We present a novel proof for language-based Transformers that extends the…

Artificial Intelligence · Computer Science 2025-03-11 Léo Dana , Muni Sreenivas Pydi , Yann Chevaleyre

Large language model (LLM) agents increasingly operate in settings where a single context window is far too small to capture what has happened, what was learned, and what should not be repeated. Memory -- the ability to persist, organize,…

Artificial Intelligence · Computer Science 2026-03-10 Pengfei Du

This paper introduces the Large Memory Model (LM2), a decoder-only Transformer architecture enhanced with an auxiliary memory module that aims to address the limitations of standard Transformers in multi-step reasoning, relational…

Computation and Language · Computer Science 2025-02-11 Jikun Kang , Wenqi Wu , Filippos Christianos , Alex J. Chan , Fraser Greenlee , George Thomas , Marvin Purtorab , Andy Toulis

We study transformers' in-context learning of variable-length Markov chains (VOMCs), focusing on the finite-sample accuracy as the number of in-context examples increases. Compared to fixed-order Markov chains (FOMCs), learning VOMCs is…

Machine Learning · Computer Science 2026-04-01 Ruida Zhou , Chao Tian , Suhas Diggavi

In practice, deep neural networks are often able to easily interpolate their training data. To understand this phenomenon, many works have aimed to quantify the memorization capacity of a neural network architecture: the largest number of…

Machine Learning · Statistics 2024-12-09 Sjoerd Dirksen , Patrick Finke , Martin Genzel

Large language models based on the transformer architecture can solve highly complex tasks, yet their fundamental limitations on simple algorithmic problems remain poorly understood. In this work, we focus on basic counting tasks and…

Computation and Language · Computer Science 2026-02-26 Gilad Yehudai , Haim Kaplan , Guy Dar , Royi Rassin , Asma Ghandeharioun , Mor Geva , Amir Globerson

Recent advancements in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing diverse data types, yet significant disparities persist between human cognitive processes and computational approaches…

Computation and Language · Computer Science 2025-05-09 Dongxing Yu

Recent progress in diverse intelligence has shown simple learning capacities below the organism level - single cells and even molecular networks. However, there are still many knowledge gaps around learning capacity above the organism…

Populations and Evolution · Quantitative Biology 2026-05-29 Adrita Samanta , Hananel Hazan , Michael Levin

Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes…

Machine Learning · Computer Science 2026-03-02 Ali Behrouz , Zeman Li , Yuan Deng , Peilin Zhong , Meisam Razaviyayn , Vahab Mirrokni

We propose a self-organizing memory architecture for perceptual experience, capable of supporting autonomous learning and goal-directed problem solving in the absence of any prior information about the agent's environment. The architecture…

Artificial Intelligence · Computer Science 2015-02-24 Dan P. Guralnik , Daniel E. Koditschek