English
Related papers

Related papers: Sparsity-Aware Evolution for Model Merging

200 papers

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

Machine Learning · Computer Science 2026-05-19 Michał Brzozowski , Neo Christopher Chung

This letter proposes a novel sparsity-aware adaptive filtering scheme and algorithms based on an alternating optimization strategy with shrinkage. The proposed scheme employs a two-stage structure that consists of an alternating…

Systems and Control · Computer Science 2023-07-19 Rodrigo C. de Lamare , Raimundo Sampaio-Neto

Model merging has emerged as a promising paradigm for composing the capabilities of large language models by directly operating in weight space, enabling the integration of specialized models without costly retraining. However, existing…

Artificial Intelligence · Computer Science 2026-02-13 Weihong Lin , Lin Sun , Qilong Shi , Aomufei Yuan , Yuxuan Tian , Zhengyang Wang , Guangxiang Zhao , Xiangzheng Zhang , Tong Yang

We explore and illustrate the concept of ranked sparsity, a phenomenon that often occurs naturally in modeling applications when an expected disparity exists in the quality of information between different feature sets. Its presence can…

Methodology · Statistics 2022-01-28 Ryan A. Peterson , Joseph E. Cavanaugh

Additive nonparametric regression models provide an attractive tool for variable selection in high dimensions when the relationship between the response and predictors is complex. They offer greater flexibility compared to parametric…

Machine Learning · Statistics 2016-07-12 Garret Vo , Debdeep Pati

Sparsity is a desirable attribute. It can lead to more efficient and more effective representations compared to the dense model. Meanwhile, learning sparse latent representations has been a challenging problem in the field of computer…

Computer Vision and Pattern Recognition · Computer Science 2022-09-22 Hanao Li , Tian Han

The advancement of deep learning has led to the emergence of Mixture-of-Experts (MoEs) models, known for their dynamic allocation of computational resources based on input. Despite their promise, MoEs face challenges, particularly in terms…

Computation and Language · Computer Science 2024-04-09 Alexandre Muzio , Alex Sun , Churan He

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Leander Girrbach , Zeynep Akata

Sparse additive models have attracted much attention in high-dimensional data analysis due to their flexible representation and strong interpretability. However, most existing models are limited to single-level learning under the…

Machine Learning · Computer Science 2026-04-23 Xuelin Zhang , Xinyue Liu , Lingjuan Wu , Hong Chen

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Machine Learning · Computer Science 2025-07-30 Viktoria Schuster

Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model without additional training. Despite extensive research, task interference remains a major…

Machine Learning · Computer Science 2026-02-25 Longhua Li , Lei Qi , Qi Tian , Xin Geng

Sparse autoencoders (SAEs) have emerged as a promising approach for learning interpretable features from neural network activations. However, the optimization landscape for SAE training can be challenging due to correlations in the input…

Machine Learning · Computer Science 2025-11-19 Ashwin Saraswatula , David Klindt

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation…

Machine Learning · Computer Science 2026-01-29 Longteng Zhang , Sen Wu , Shuai Hou , Zhengyu Qing , Zhuo Zheng , Danning Ke , Qihong Lin , Qiang Wang , Shaohuai Shi , Xiaowen Chu

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

Equation discovery is a fundamental learning task for uncovering the underlying dynamics of complex systems, with wide-ranging applications in areas such as brain connectivity analysis, climate modeling, gene regulation, and physical…

Machine Learning · Computer Science 2026-01-29 Jiaqiang Li , Jianbin Tan , Xueqin Wang

Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…

Computation and Language · Computer Science 2026-03-31 Mingyang Song , Mao Zheng

The growing demand for sparse tensor algebra (SpTA) in machine learning and big data has driven the development of various sparse tensor accelerators. However, most existing manually designed accelerators are limited to specific scenarios,…

Machine Learning · Computer Science 2025-08-19 Boran Zhao , Haiming Zhai , Zihang Yuan , Hetian Liu , Tian Xia , Wenzhe Zhao , Pengju Ren

Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit preference instability, producing contradictory preference assignments in response to subtle,…

Machine Learning · Computer Science 2026-05-19 Shunchang Liu , Xin Chen , Belen Martin Urcelay , Francesco Croce

In recent years, a large amount of multi-disciplinary research has been conducted on sparse models and their applications. In statistics and machine learning, the sparsity principle is used to perform model selection---that is,…

Computer Vision and Pattern Recognition · Computer Science 2014-12-09 Julien Mairal , Francis Bach , Jean Ponce

Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of…

Machine Learning · Computer Science 2025-09-29 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Elena Tutubalina , Ivan Oseledets