English
Related papers

Related papers: SAE-FD: Sparse Autoencoder Feature Distillation fo…

200 papers

Dataset distillation seeks to synthesize a highly compact dataset that achieves performance comparable to the original dataset on downstream tasks. For the classification task that use pre-trained self-supervised models as backbones,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Qianxin Xia , Jiawei Du , Xin Zhang , Yuhan Zhang , Jielei Wang , Guoming Lu

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

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…

Machine Learning · Computer Science 2025-02-25 Subhash Kantamneni , Joshua Engels , Senthooran Rajamanoharan , Max Tegmark , Neel Nanda

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

Computation and Language · Computer Science 2025-07-10 Shun Wang , Tyler Loakman , Youbo Lei , Yi Liu , Bohao Yang , Yuting Zhao , Dong Yang , Chenghua Lin

Continued self-supervised (SSL) pre-training for adapting existing SSL models to the target domain has shown to be extremely effective for low-resource Automatic Speech Recognition (ASR). This paper proposes Stable Distillation, a simple…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-21 Ashish Seth , Sreyan Ghosh , S. Umesh , Dinesh Manocha

(This paper was written in November 2011 and never published. It is posted on arXiv.org in its original form in June 2016). Many recent object recognition systems have proposed using a two phase training procedure to learn sparse…

Computer Vision and Pattern Recognition · Computer Science 2016-06-07 Kevin Jarrett , Koray Kvukcuoglu , Karol Gregor , Yann LeCun

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Machine Learning · Computer Science 2026-03-03 Shruti Joshi , Andrea Dittadi , Sébastien Lachapelle , Dhanya Sridhar

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability research for large language models; however, the state-of-the-art method of using $k$-sparse autoencoders lacks a theoretical grounding for selecting the…

Machine Learning · Computer Science 2025-08-11 Sewoong Lee , Adam Davies , Marc E. Canby , Julia Hockenmaier

Autoencoders are certainly among the most studied and used Deep Learning models: the idea behind them is to train a model in order to reconstruct the same input data. The peculiarity of these models is to compress the information through a…

Machine Learning · Computer Science 2023-09-06 Gabriele Martino , Davide Moroni , Massimo Martinelli

Catastrophic forgetting has been a major challenge in continual learning, where the model needs to learn new tasks with limited or no access to data from previously seen tasks. To tackle this challenge, methods based on knowledge…

Machine Learning · Computer Science 2023-06-29 Qiao Gu , Dongsub Shim , Florian Shkurti

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

Computation and Language · Computer Science 2026-02-27 Usha Bhalla , Alex Oesterling , Claudio Mayrink Verdun , Himabindu Lakkaraju , Flavio P. Calmon

Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments. Continual learning is a growing field of research that examines how AI…

Computer Vision and Pattern Recognition · Computer Science 2021-08-06 Minha Kim , Shahroz Tariq , Simon S. Woo

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each…

The process of tuning the size of the hidden layers for autoencoders has the benefit of providing optimally compressed representations for the input data. However, such hyper-parameter tuning process would take a lot of computation and time…

Machine Learning · Computer Science 2025-07-08 Sarthak Ketanbhai Modi , Zi Pong Lim , Yushi Cao , Yupeng Cheng , Yon Shin Teo , Shang-Wei Lin

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Computation and Language · Computer Science 2020-10-30 Alexander Lin , Jeremy Wohlwend , Howard Chen , Tao Lei

Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning…

Computation and Language · Computer Science 2021-07-27 Nithin Holla , Pushkar Mishra , Helen Yannakoudakis , Ekaterina Shutova

Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has played an important role for on-device ASR applications. In…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-13 Sankaran Panchapagesan , Daniel S. Park , Chung-Cheng Chiu , Yuan Shangguan , Qiao Liang , Alexander Gruenstein

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

Machine Learning · Computer Science 2024-05-17 Zenglin Shi , Pei Liu , Tong Su , Yunpeng Wu , Kuien Liu , Yu Song , Meng Wang

Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Seanie Lee , Minki Kang , Juho Lee , Sung Ju Hwang , Kenji Kawaguchi

The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper presents a novel framework that leverages sparse autoencoders…

Machine Learning · Computer Science 2025-02-18 Zirui He , Haiyan Zhao , Yiran Qiao , Fan Yang , Ali Payani , Jing Ma , Mengnan Du