English
Related papers

Related papers: WINA: Weight Informed Neuron Activation for Accele…

200 papers

Large Language Models (LLMs) are difficult to fully fine-tune (e.g., with instructions or human feedback) due to their sheer number of parameters. A family of parameter-efficient sparse fine-tuning methods have proven promising in terms of…

Computation and Language · Computer Science 2024-02-05 Alan Ansell , Ivan Vulić , Hannah Sterz , Anna Korhonen , Edoardo M. Ponti

Post-training compression of large language models (LLMs) often relies on low-rank weight approximations that represent each column of the weight matrix in a shared low-dimensional subspace. This strategy is computationally efficient but…

Computation and Language · Computer Science 2026-05-05 Denis Makhov , Dmitriy Shopkhoev , Magauiya Zhussip , Ammar Ali , Stamatios Lefkimmiatis

Recent research has shown that pruning large-scale language models for inference is an effective approach to improving model efficiency, significantly reducing model weights with minimal impact on performance. Interestingly, pruning can…

Computation and Language · Computer Science 2025-02-19 Yiran Luo , Het Patel , Yu Fu , Dawon Ahn , Jia Chen , Yue Dong , Evangelos E. Papalexakis

The excessive computational requirements of modern artificial neural networks (ANNs) are posing limitations on the machines that can run them. Sparsification of ANNs is often motivated by time, memory and energy savings only during model…

Machine Learning · Computer Science 2025-05-01 Mike Heddes , Narayan Srinivasa , Tony Givargis , Alexandru Nicolau

Flexible cognition demands discovering hidden rules to quickly adapt stimulus-response mappings. Standard neural networks struggle in such tasks requiring rapid, context-driven remapping. Recently, Hummos (2023) introduced a fast-and-slow…

Neurons and Cognition · Quantitative Biology 2025-02-26 Rowan P. Sommers , Sushrut Thorat , Daniel Anthes , Tim C. Kietzmann

Neural network pruning is a promising technique to mitigate the excessive computational and memory requirements of large language models (LLMs). Despite its promise, however, progress in this area has diminished, as conventional methods are…

Machine Learning · Computer Science 2026-02-24 Kwanhee Lee , Hyeondo Jang , Dongyeop Lee , Dan Alistarh , Namhoon Lee

We present ELSA, a practical solution for creating deep networks that can easily be deployed at different levels of sparsity. The core idea is to embed one or more sparse networks within a single dense network as a proper subset of the…

Machine Learning · Computer Science 2023-12-19 Paniz Halvachi , Alexandra Peste , Dan Alistarh , Christoph H. Lampert

Recently, the scale of transformers has grown rapidly, which introduces considerable challenges in terms of training overhead and inference efficiency in the scope of task adaptation. Existing works, namely Parameter-Efficient Fine-Tuning…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Yizhe Xiong , Hui Chen , Tianxiang Hao , Zijia Lin , Jungong Han , Yuesong Zhang , Guoxin Wang , Yongjun Bao , Guiguang Ding

Scaling deep learning recommendation models is an effective way to improve model expressiveness. Existing approaches often incur substantial computational overhead, making them difficult to deploy in large-scale industrial systems under…

Information Retrieval · Computer Science 2026-02-10 Shikang Wu , Hui Lu , Jinqiu Jin , Zheng Chai , Shiyong Hong , Junjie Zhang , Shanlei Mu , Kaiyuan Ma , Tianyi Liu , Yuchao Zheng , Zhe Wang , Jingjian Lin

Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights. However, most…

Computation and Language · Computer Science 2025-07-25 Duy Nguyen , Archiki Prasad , Elias Stengel-Eskin , Mohit Bansal

Mixture-of-Experts (MoE) models scale more effectively than dense models due to sparse computation through expert routing, selectively activating only a small subset of expert modules. However, sparse computation challenges traditional…

The deep learning literature is continuously updated with new architectures and training techniques. However, weight initialization is overlooked by most recent research, despite some intriguing findings regarding random weights. On the…

Neural and Evolutionary Computing · Computer Science 2022-07-19 Leonardo Scabini , Bernard De Baets , Odemir M. Bruno

Deep neural networks (DNNs) frequently contain far more weights, represented at a higher precision, than are required for the specific task which they are trained to perform. Consequently, they can often be compressed using techniques such…

Machine Learning · Computer Science 2020-12-03 Vinu Joseph , Saurav Muralidharan , Animesh Garg , Michael Garland , Ganesh Gopalakrishnan

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but…

Machine Learning · Computer Science 2024-08-22 Elias Frantar , Roberto L. Castro , Jiale Chen , Torsten Hoefler , Dan Alistarh

We present a psychoacoustically enhanced cost function to balance network complexity and perceptual performance of deep neural networks for speech denoising. While training the network, we utilize perceptual weights added to the ordinary…

Sound · Computer Science 2018-01-31 Kai Zhen , Aswin Sivaraman , Jongmo Sung , Minje Kim

We propose a diffractive neural network with strong robustness based on Weight Noise Injection training, which achieves accurate and fast optical-based classification while diffraction layers have a certain amount of surface shape error. To…

Image and Video Processing · Electrical Eng. & Systems 2020-06-23 Jiashuo Shi

For computer vision applications, prior works have shown the efficacy of reducing numeric precision of model parameters (network weights) in deep neural networks. Activation maps, however, occupy a large memory footprint during both the…

Computer Vision and Pattern Recognition · Computer Science 2017-09-06 Asit Mishra , Eriko Nurvitadhi , Jeffrey J Cook , Debbie Marr

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-29 Mingyu Sun , Xiao Zhang , Shen Qu , Yan Li , Mengbai Xiao , Yuan Yuan , Dongxiao Yu

Long-context inference in large language models (LLMs) is bottlenecked by the linear growth of the self-attention key-value (KV) cache. Top-k sparse attention alleviates this by loading only a small fraction of the KV cache, but accurately…

Computation and Language · Computer Science 2026-05-28 Keqi Deng , Shaoshi Ling , Ruchao Fan , Jinyu Li

Large language model (LLM) inference poses significant challenges due to its intensive memory and computation demands. Weight and activation quantization (WAQ) offers a promising solution by reducing both memory footprint and arithmetic…

Machine Learning · Computer Science 2025-09-11 Xueying Wu , Baijun Zhou , Zhihui Gao , Yuzhe Fu , Qilin Zheng , Yintao He , Hai Li
‹ Prev 1 8 9 10 Next ›