English
Related papers

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

200 papers

Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both generating a set of examples and running iterations of…

Computation and Language · Computer Science 2024-06-12 Pratiksha Thaker , Yash Maurya , Shengyuan Hu , Zhiwei Steven Wu , Virginia Smith

Machine unlearning aims to remove specific data influences from trained models, a capability essential for adhering to copyright laws and ensuring AI safety. Current unlearning metrics typically measure success by monitoring the model's…

Cryptography and Security · Computer Science 2025-12-24 Hengrui Jia , Taoran Li , Jonas Guan , Varun Chandrasekaran

Learning complex trajectories from demonstrations in robotic tasks has been effectively addressed through the utilization of Dynamical Systems (DS). State-of-the-art DS learning methods ensure stability of the generated trajectories;…

Robotics · Computer Science 2024-12-10 Andreas Sochopoulos , Michael Gienger , Sethu Vijayakumar

Sparse training is emerging as a promising avenue for reducing the computational cost of training neural networks. Several recent studies have proposed pruning methods using learnable thresholds to efficiently explore the non-uniform…

Machine Learning · Computer Science 2023-04-17 Abhisek Kundu , Naveen K. Mellempudi , Dharma Teja Vooturi , Bharat Kaul , Pradeep Dubey

With rise of machine learning (ML) and the proliferation of smart mobile devices, recent years have witnessed a surge of interest in performing ML in wireless edge networks. In this paper, we consider the problem of jointly improving data…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-03-31 Xin Zhang , Minghong Fang , Jia Liu , Zhengyuan Zhu

In the context of machine unlearning, the primary challenge lies in effectively removing traces of private data from trained models while maintaining model performance and security against privacy attacks like membership inference attacks.…

Machine Learning · Computer Science 2024-06-26 Tao Huang , Ziyang Chen , Jiayang Meng , Qingyu Huang , Xu Yang , Xun Yi , Ibrahim Khalil

The LLM unlearning technique has recently been introduced to comply with data regulations and address the safety and ethical concerns of LLMs by removing the undesired data-model influence. However, state-of-the-art unlearning methods face…

Machine Learning · Computer Science 2025-05-28 Chongyu Fan , Jinghan Jia , Yihua Zhang , Anil Ramakrishna , Mingyi Hong , Sijia Liu

Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading…

Machine Learning · Computer Science 2019-09-05 Jacob Rafati , David C. Noelle

Machine unlearning is the process of efficiently removing the influence of a training data instance from a trained machine learning model without retraining it from scratch. A popular subclass of unlearning approaches is exact machine…

Fine-tuning pretrained self-supervised language models is widely adopted for transfer learning to downstream tasks. Fine-tuning can be achieved by freezing gradients of the pretrained network and only updating gradients of a newly added…

Computation and Language · Computer Science 2023-07-20 James O' Neill , Sourav Dutta

Discrete choice models (DCMs) are used to analyze individual decision-making in contexts such as transportation choices, political elections, and consumer preferences. DCMs play a central role in applied econometrics by enabling inference…

Machine Learning · Statistics 2025-12-19 Daniel F. Villarraga , Ricardo A. Daziano

Digital subtraction angiography (DSA) is a key imaging technique for the auxiliary diagnosis and treatment of cerebrovascular diseases. Recent advancements in gaussian splatting and dynamic neural representations have enabled robust 3D…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Shiyu Zhang , Zhicong Wu , Huangxuan Zhao , Zhentao Liu , Lei Chen , Yong Luo , Lefei Zhang , Zhiming Cui , Ziwen Ke , Bo Du

Classical machine learning models such as deep neural networks are usually trained by using Stochastic Gradient Descent-based (SGD) algorithms. The classical SGD can be interpreted as a discretization of the stochastic gradient flow. In…

Optimization and Control · Mathematics 2023-10-03 Valentin Leplat , Daniil Merkulov , Aleksandr Katrutsa , Daniel Bershatsky , Olga Tsymboi , Ivan Oseledets

In this paper, we investigate the dynamics-aware adversarial attack problem in deep neural networks. Most existing adversarial attack algorithms are designed under a basic assumption -- the network architecture is fixed throughout the…

Computer Vision and Pattern Recognition · Computer Science 2023-01-24 An Tao , Yueqi Duan , He Wang , Ziyi Wu , Pengliang Ji , Haowen Sun , Jie Zhou , Jiwen Lu

Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over training. Sparse Autoencoders (SAEs) have recently shown to be…

Machine Learning · Computer Science 2026-02-09 John Yan , Michael Yu , Yuqi Sun , Alexander Duffy , Tyler Marques , Matthew Lyle Olson

This paper focuses on leveraging deep representation learning (DRL) for speech enhancement (SE). In general, the performance of the deep neural network (DNN) is heavily dependent on the learning of data representation. However, the DRL's…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-28 Yang Xiang , Jesper Lisby Højvang , Morten Højfeldt Rasmussen , Mads Græsbøll Christensen

Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment…

Machine Learning · Computer Science 2025-01-15 Yan Fan , Yu Wang , Pengfei Zhu , Qinghua Hu

Deep learning, as widely known, is vulnerable to adversarial samples. This paper focuses on the adversarial attack on autoencoders. Safety of the autoencoders (AEs) is important because they are widely used as a compression scheme for data…

Computer Vision and Pattern Recognition · Computer Science 2020-03-05 Chengjin Sun , Sizhe Chen , Xiaolin Huang

Deep Reinforcement Learning (DRL) is regarded as a potential method for car-following control and has been mostly studied to support a single following vehicle. However, it is more challenging to learn a stable and efficient car-following…

Systems and Control · Electrical Eng. & Systems 2022-11-21 Tong Liu , Lei Lei , Kan Zheng , Kuan Zhang

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…