English
Related papers

Related papers: BASE Layers: Simplifying Training of Large, Sparse…

200 papers

Neural information retrieval architectures based on transformers such as BERT are able to significantly improve system effectiveness over traditional sparse models such as BM25. Though highly effective, these neural approaches are very…

Information Retrieval · Computer Science 2022-04-26 Antonio Mallia , Joel Mackenzie , Torsten Suel , Nicola Tonellotto

We introduce, Q-Sparse, a simple yet effective approach to training sparsely-activated large language models (LLMs). Q-Sparse enables full sparsity of activations in LLMs which can bring significant efficiency gains in inference. This is…

Computation and Language · Computer Science 2024-07-25 Hongyu Wang , Shuming Ma , Ruiping Wang , Furu Wei

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

In this work, we demonstrate that affine mappings between residual streams of language models is a cheap way to effectively transfer represented features between models. We apply this technique to transfer the weights of Sparse Autoencoders…

Computation and Language · Computer Science 2025-11-04 Alan Chen , Jack Merullo , Alessandro Stolfo , Ellie Pavlick

Mixture-of-Experts (MoE) architectures scale large language models (LLMs) by activating only a subset of experts per token, but the standard TopK routing assigns the same fixed number of experts to all tokens, ignoring their varying…

Machine Learning · Computer Science 2026-03-30 Tiansheng Wen , Yifei Wang , Aosong Feng , Long Ma , Xinyang Liu , Yifan Wang , Lixuan Guo , Bo Chen , Stefanie Jegelka , Chenyu You

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation in averaging. While model routing addresses this issue by…

Machine Learning · Computer Science 2025-02-12 Kunfeng Lai , Zhenheng Tang , Xinglin Pan , Peijie Dong , Xiang Liu , Haolan Chen , Li Shen , Bo Li , Xiaowen Chu

Learning to defer uncertain predictions to costly experts offers a powerful strategy for improving the accuracy and efficiency of machine learning systems. However, standard training procedures for deferral algorithms typically require…

Machine Learning · Computer Science 2025-10-31 Giulia DeSalvo , Clara Mohri , Mehryar Mohri , Yutao Zhong

Mixture-of-Experts models enable large language models to scale efficiently, as they only activate a subset of experts for each input. Their core mechanisms, Top-k routing and auxiliary load balancing, remain heuristic, however, lacking a…

Machine Learning · Computer Science 2026-01-08 Ye Su , Yong Liu

Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to every downstream task. We introduce TALE (Task-Aware Layer Elimination), an inference-time method that…

Machine Learning · Computer Science 2026-05-12 Omar Naim , Krish Sharma , Niyar R Barman , Nicholas Asher

Scalable load balancing algorithms are of great interest in cloud networks and data centers, necessitating the use of tractable techniques to compute optimal load balancing policies for good performance. However, most existing scalable…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-03-25 Anam Tahir , Kai Cui , Heinz Koeppl

Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be viewed as partitioning a large Feed-Forward Network (FFN) at…

Machine Learning · Computer Science 2025-08-27 Weilin Cai , Le Qin , Shwai He , Junwei Cui , Ang Li , Jiayi Huang

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

Machine Learning · Computer Science 2026-02-11 Jonathan Svirsky , Yehonathan Refael , Ofir Lindenbaum

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Haowei Zhu , Ji Liu , Ziqiong Liu , Dong Li , Junhai Yong , Bin Wang , Emad Barsoum

Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning. Mixture-of-experts (MoE) provides a promising solution with a dynamic architecture, enabling effective task decoupling. However,…

Machine Learning · Computer Science 2025-05-28 Rongyu Zhang , Yijiang Liu , Huanrui Yang , Shenli Zheng , Dan Wang , Yuan Du , Li Du , Shanghang Zhang

Mixture-of-Experts (MoE) architectures have become standard in large language models, yet many of their core design choices - expert count, granularity, shared experts, load balancing, token dropping - have only been studied one or two at a…

Machine Learning · Computer Science 2026-05-13 Margaret Li , Sneha Kudugunta , Danielle Rothermel , Luke Zettlemoyer

This work presents a new method for enhancing communication efficiency in stochastic Federated Learning that trains over-parameterized random networks. In this setting, a binary mask is optimized instead of the model weights, which are kept…

Machine Learning · Computer Science 2024-03-01 Mohamad Mestoukirdi , Omid Esrafilian , David Gesbert , Qianrui Li , Nicolas Gresset

We present a comprehensive framework for structured sparse coding and modeling extending the recent ideas of using learnable fast regressors to approximate exact sparse codes. For this purpose, we develop a novel block-coordinate proximal…

Machine Learning · Computer Science 2012-06-22 Alex Bronstein , Pablo Sprechmann , Guillermo Sapiro

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

State-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model. However, such modules are trained separately for each task and thus do not enable sharing…

Computation and Language · Computer Science 2021-06-09 Rabeeh Karimi Mahabadi , Sebastian Ruder , Mostafa Dehghani , James Henderson

Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the…

Machine Learning · Computer Science 2023-09-11 Denis Kuznedelev , Eldar Kurtic , Eugenia Iofinova , Elias Frantar , Alexandra Peste , Dan Alistarh