English
Related papers

Related papers: Memory Layers at Scale

200 papers

Looped transformers apply a shared block multiple times and have emerged as a parameter-efficient route to scaling compute in language models. However, at fixed FLOPs a looped model has strictly less capacity than a baseline transformer. We…

Computation and Language · Computer Science 2026-05-29 Markus Frey , Behzad Shomali , Joachim Koehler , Mehdi Ali

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

The surprising ability of Large Language Models (LLMs) to perform well on complex reasoning with only few-shot chain-of-thought prompts is believed to emerge only in very large-scale models (100+ billion parameters). We show that such…

Computation and Language · Computer Science 2023-01-31 Yao Fu , Hao Peng , Litu Ou , Ashish Sabharwal , Tushar Khot

We consider layerwise function-space learning rates, which measure the magnitude of the change in a neural network's output function in response to an update to a parameter tensor. This contrasts with traditional learning rates, which…

Machine Learning · Statistics 2025-05-23 Edward Milsom , Ben Anson , Laurence Aitchison

Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps between current scaling studies and how language models are…

Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require timely, domain-specific information, motivating the…

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

This work is centred around the recently proposed product key memory structure \cite{large_memory}, implemented for a number of computer vision applications. The memory structure can be regarded as a simple computation primitive suitable to…

Computer Vision and Pattern Recognition · Computer Science 2021-04-27 Rasul Karimov , Yury Malkov , Karim Iskakov , Victor Lempitsky

Architectures with multiple classes of memory media are becoming a common part of mainstream supercomputer deployments. So called multi-level memories offer differing characteristics for each memory component including variation in…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-04-04 Mehmet Deveci , Simon D. Hammond , Michael M. Wolf , Sivasankaran Rajamanickam

The full-size MLPs and the projection layers in attention introduce tremendous model sizes of large language models (LLMs), consuming extensive computational resources in pre-training. We empirically observe that the activations of…

Machine Learning · Computer Science 2025-10-03 Ziyue Liu , Ruijie Zhang , Zhengyang Wang , Mingsong Yan , Zi Yang , Paul Hovland , Bogdan Nicolae , Franck Cappello , Sui Tang , Zheng Zhang

How to reduce compute and memory requirements of neural networks (NNs) without sacrificing performance? Many recent works use sparse Mixtures of Experts (MoEs) to build resource-efficient large language models (LMs). Here we introduce…

Machine Learning · Computer Science 2023-11-22 Róbert Csordás , Kazuki Irie , Jürgen Schmidhuber

Modern approaches to enhancing Large Language Models' factual accuracy and knowledge utilization face a fundamental trade-off: non-parametric retrieval-augmented generation (RAG) provides flexible access to external knowledge but suffers…

Computation and Language · Computer Science 2026-03-02 Rubin Wei , Jiaqi Cao , Jiarui Wang , Jushi Kai , Qipeng Guo , Bowen Zhou , Zhouhan Lin

How effectively can LLM-based AI assistants utilize their memory (context) to perform various tasks? Traditional data benchmarks, which are often manually crafted, suffer from several limitations: they are static, susceptible to…

Computation and Language · Computer Science 2025-06-10 Menglin Xia , Victor Ruehle , Saravan Rajmohan , Reza Shokri

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are…

Machine Learning · Computer Science 2023-06-06 Wes Gurnee , Neel Nanda , Matthew Pauly , Katherine Harvey , Dmitrii Troitskii , Dimitris Bertsimas

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

Modern sparse language models typically achieve sparsity through Mixture-of-Experts (MoE) layers, which dynamically route tokens to dense MLP "experts." However, dynamic hard routing has a number of drawbacks, such as potentially poor…

Machine Learning · Computer Science 2026-02-02 Albert Tseng , Christopher De Sa

Dense Associative Memories or Modern Hopfield Networks have many appealing properties of associative memory. They can do pattern completion, store a large number of memories, and can be described using a recurrent neural network with a…

Neural and Evolutionary Computing · Computer Science 2021-07-29 Dmitry Krotov

We develop task scaling laws and model ladders to predict the individual task performance of pretrained language models (LMs) in the overtrained setting. Standard power laws for language modeling loss cannot accurately model task…

In this paper, we propose a highly parameter-efficient approach to scaling pre-trained language models (PLMs) to a deeper model depth. Unlike prior work that shares all parameters or uses extra blocks, we design a more capable…

Computation and Language · Computer Science 2023-04-12 Peiyu Liu , Ze-Feng Gao , Yushuo Chen , Wayne Xin Zhao , Ji-Rong Wen

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

‹ Prev 1 3 4 5 6 7 10 Next ›