English
Related papers

Related papers: Nonlinear Concept Erasure: a Density Matching Appr…

200 papers

Deep learning models have achieved remarkable success in different areas of machine learning over the past decade; however, the size and complexity of these models make them difficult to understand. In an effort to make them more…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Vikram V. Ramaswamy , Sunnie S. Y. Kim , Nicole Meister , Ruth Fong , Olga Russakovsky

Pre-trained language models have achieved remarkable success across diverse applications but remain susceptible to spurious, concept-driven correlations that impair robustness and fairness. In this work, we introduce CURE, a novel and…

Computation and Language · Computer Science 2025-09-11 Aysenur Kocak , Shuo Yang , Bardh Prenkaj , Gjergji Kasneci

Large multimodal models such as Stable Diffusion can generate, detect, and classify new visual concepts after fine-tuning just a single word embedding. Do models learn similar words for the same concepts (i.e. <orange-cat> = orange + cat)?…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Brandon Trabucco , Max Gurinas , Kyle Doherty , Ruslan Salakhutdinov

Language carries implicit human biases, functioning both as a reflection and a perpetuation of stereotypes that people carry with them. Recently, ML-based NLP methods such as word embeddings have been shown to learn such language biases…

Computation and Language · Computer Science 2022-01-26 Xavier Ferrer-Aran , Tom van Nuenen , Natalia Criado , Jose M. Such

A single text prompt passed to a diffusion model often yields a wide range of visual outputs determined solely by stochastic process, leaving users with no direct control over which specific semantic variations appear in the image. While…

Machine Learning · Computer Science 2026-02-12 Paweł Skierś , Tomasz Trzciński , Kamil Deja

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…

Machine Learning · Computer Science 2025-03-04 David Klindt , Charles O'Neill , Patrik Reizinger , Harald Maurer , Nina Miolane

Interpretability and fairness are critical in computer vision and machine learning applications, in particular when dealing with human outcomes, e.g. inviting or not inviting for a job interview based on application materials that may…

Machine Learning · Computer Science 2019-04-12 Novi Quadrianto , Viktoriia Sharmanska , Oliver Thomas

Tensor decomposition of high-dimensional data often struggles to capture semantically or physically meaningful structures, particularly when relying on reconstruction objectives and fixed-rank constraints. We introduce a no-rank tensor…

Machine Learning · Computer Science 2026-03-03 Maryam Bagherian

Distributed representations provide a vector space that captures meaningful relationships between data instances. The distributed nature of these representations, however, entangles together multiple attributes or concepts of data instances…

Machine Learning · Computer Science 2023-12-04 Somnath Basu Roy Chowdhury , Nicholas Monath , Avinava Dubey , Amr Ahmed , Snigdha Chaturvedi

Text-to-image diffusion models may generate harmful or copyrighted content, motivating research on concept erasure. However, existing approaches primarily focus on erasing concepts from text prompts, overlooking other input modalities that…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Ju-Hsuan Weng , Jia-Wei Liao , Cheng-Fu Chou , Jun-Cheng Chen

The success of diffusion models has raised concerns about the generation of unsafe or harmful content, prompting concept erasure approaches that fine-tune modules to suppress specific concepts while preserving general generative…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Jiahang Tu , Ye Li , Yiming Wu , Hanbin Zhao , Chao Zhang , Hui Qian

Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they rely on expanding the representation dimension, which…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Piotr Kubaty , Patryk Marszałek , Łukasz Struski , Adam Wróbel , Jacek Tabor , Marek Śmieja

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Seung Hyuk Lee , Songkuk Kim

Many works have shown that deep learning-based medical image classification models can exhibit bias toward certain demographic attributes like race, gender, and age. Existing bias mitigation methods primarily focus on learning debiased…

Image and Video Processing · Electrical Eng. & Systems 2022-03-07 Yawen Wu , Dewen Zeng , Xiaowei Xu , Yiyu Shi , Jingtong Hu

To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning,…

Computation and Language · Computer Science 2025-01-30 Jingxuan Xu , Wuyang Chen , Linyi Li , Yao Zhao , Yunchao Wei

Sentence embedding techniques aim to encode key concepts of a sentence's meaning in a vector space. However, the majority of evaluation approaches for sentence embedding quality rely on the use of additional classifiers or downstream tasks.…

Computation and Language · Computer Science 2026-04-24 Paul Keuren , Marc Ponsen , Robert Ayoub Bagheri

Dimensionality reduction is an effective method for learning high-dimensional data, which can provide better understanding of decision boundaries in human-readable low-dimensional subspace. Linear methods, such as principal component…

Machine Learning · Computer Science 2020-07-09 Koji Maruhashi , Heewon Park , Rui Yamaguchi , Satoru Miyano

We investigate the behavior of methods that use linear projections to remove information about a concept from a language representation, and we consider the question of what happens to a dataset transformed by such a method. A theoretical…

Computation and Language · Computer Science 2024-03-26 Richard Johansson

We present a system for bottom-up cumulative learning of myriad concepts corresponding to meaningful character strings, and their part-related and prediction edges. The learning is self-supervised in that the concepts discovered are used as…

Machine Learning · Computer Science 2021-12-20 Omid Madani

Text-to-image diffusion models have achieved remarkable success in generating photorealistic images. However, the inclusion of sensitive information during pre-training poses significant risks. Machine Unlearning (MU) offers a promising…

Machine Learning · Computer Science 2025-03-19 Yongliang Wu , Shiji Zhou , Mingzhuo Yang , Lianzhe Wang , Heng Chang , Wenbo Zhu , Xinting Hu , Xiao Zhou , Xu Yang