English
Related papers

Related papers: SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sp…

200 papers

Existing work in continual learning (CL) focuses on mitigating catastrophic forgetting, i.e., model performance deterioration on past tasks when learning a new task. However, the training efficiency of a CL system is under-investigated,…

Machine Learning · Computer Science 2022-09-21 Zifeng Wang , Zheng Zhan , Yifan Gong , Geng Yuan , Wei Niu , Tong Jian , Bin Ren , Stratis Ioannidis , Yanzhi Wang , Jennifer Dy

Modern machine learning is trained by stochastic gradient descent (SGD), whose performance critically depends on how the learning rate (LR) is adjusted and decreased over time. Yet existing LR regimes may be intricate, or need to tune one…

Machine Learning · Computer Science 2025-08-20 Zhuang Yang

Fast and safe voltage regulation algorithms can serve as fundamental schemes for achieving a high level of renewable penetration in the modern distribution power grids. Faced with uncertain or even unknown distribution grid models and…

Systems and Control · Electrical Eng. & Systems 2021-12-01 Yize Chen , Yuanyuan Shi , Daniel Arnold , Sean Peisert

This paper proposes a sparse Bayesian treatment of deep neural networks (DNNs) for system identification. Although DNNs show impressive approximation ability in various fields, several challenges still exist for system identification…

Systems and Control · Electrical Eng. & Systems 2022-06-02 Hongpeng Zhou , Chahine Ibrahim , Wei Xing Zheng , Wei Pan

Goal-conditioned reinforcement learning is a crucial yet challenging algorithm which enables agents to achieve multiple user-specified goals when learning a set of skills in a dynamic environment. However, it typically requires millions of…

Robotics · Computer Science 2022-03-01 Zhifeng Qian , Mingyu You , Hongjun Zhou , Bin He

Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder-Denoised Concept Vectors (SDCV), which selectively keep the…

Computation and Language · Computer Science 2025-07-31 Haiyan Zhao , Xuansheng Wu , Fan Yang , Bo Shen , Ninghao Liu , Mengnan Du

This work delves into the complexities of machine unlearning in the face of distributional shifts, particularly focusing on the challenges posed by non-uniform feature and label removal. With the advent of regulations like the GDPR…

Machine Learning · Computer Science 2024-03-14 Ling Han , Nanqing Luo , Hao Huang , Jing Chen , Mary-Anne Hartley

Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features not prevalent in their training corpora. This paper…

Machine Learning · Computer Science 2025-07-18 Nikita Koriagin , Yaroslav Aksenov , Daniil Laptev , Gleb Gerasimov , Nikita Balagansky , Daniil Gavrilov

Machine unlearning is a process of removing the impact of some training data from the machine learning (ML) models upon receiving removal requests. While straightforward and legitimate, retraining the ML model from scratch incurs a high…

Machine Learning · Computer Science 2022-09-20 Min Chen , Zhikun Zhang , Tianhao Wang , Michael Backes , Mathias Humbert , Yang Zhang

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows…

Machine Learning · Computer Science 2025-01-31 Gonçalo Paulo , Nora Belrose

Gradient descent algorithm is the most utilized method when optimizing machine learning issues. However, there exists many local minimums and saddle points in the loss function, especially for high dimensional non-convex optimization…

Machine Learning · Computer Science 2021-07-19 Zhicheng Cai

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…

Machine Learning · Computer Science 2025-09-24 Dong Shu , Xuansheng Wu , Haiyan Zhao , Daking Rai , Ziyu Yao , Ninghao Liu , Mengnan Du

Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both Large Language Models (LLMs) and Vision Transformers (ViTs). By decomposing polysemantic…

Machine Learning · Computer Science 2026-05-11 Jakub Stępień , Marcin Mazur , Jacek Tabor , Przemysław Spurek

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

Machine unlearning aims to remove the influence of a designated forget set from a trained model while preserving utility on the retained data. In modern deep networks, approximate unlearning frequently fails under large or adversarial…

Machine Learning · Computer Science 2026-02-11 Mohammad Partohaghighi , Roummel Marcia , Bruce J. West , YangQuan Chen

Reward models (RMs) are critical components of alignment pipelines, yet they exhibit biases toward superficial stylistic cues, preferring better-presented responses over semantically superior ones. Existing debiasing methods typically…

Computation and Language · Computer Science 2026-03-16 Mengyuan Sun , Zhuohao Yu , Weizheng Gu , Shikun Zhang , Wei Ye

Deep reinforcement learning (DRL) agents are trained through trial-and-error interactions with the environment. This leads to a long training time for dense neural networks to achieve good performance. Hence, prohibitive computation and…

Machine Learning · Computer Science 2022-05-09 Ghada Sokar , Elena Mocanu , Decebal Constantin Mocanu , Mykola Pechenizkiy , Peter Stone

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Machine Learning · Computer Science 2025-06-09 Yin Lu , Xuening Zhu , Tong He , David Wipf

A key challenge in the continual learning setting is to efficiently learn a sequence of tasks without forgetting how to perform previously learned tasks. Many existing approaches to this problem work by either retraining the model on…

Machine Learning · Computer Science 2024-01-12 Weijieying Ren , Vasant G Honavar

Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM…

Machine Learning · Computer Science 2024-11-04 Aashiq Muhamed , Mona Diab , Virginia Smith
‹ Prev 1 4 5 6 7 8 10 Next ›