English
Related papers

Related papers: Denoising Concept Vectors with Sparse Autoencoders…

200 papers

Sparse Attention Vectors (SAVs) have emerged as an excellent training-free alternative to supervised finetuning or low-rank adaptation to improve the performance of Vision Language Models (VLMs). At their heart, SAVs select a few accurate…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Pierre Musacchio , Jaeyi Jeong , Dahun Kim , Jaesik Park

Variational autoencoders (VAEs) typically encode images into a compact latent space, reducing computational cost but introducing an optimization dilemma: a higher-dimensional latent space improves reconstruction fidelity but often hampers…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Xunzhi Xiang , Xingye Tian , Guiyu Zhang , Yabo Chen , Shaofeng Zhang , Xuebo Wang , Xin Tao , Qi Fan

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like text, but their output may not be aligned with the user or even produce harmful content. This paper presents a novel approach to detect and…

Computation and Language · Computer Science 2024-12-06 Ruben Härle , Felix Friedrich , Manuel Brack , Björn Deiseroth , Patrick Schramowski , Kristian Kersting

Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in…

Computation and Language · Computer Science 2026-02-03 Jiaqian Li , Yanshu Li , Kuan-Hao Huang

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…

Machine Learning · Computer Science 2026-05-13 Hyeonjin Kim , Hangyeol Jung , Heechan Yun , Sungjun Yun , Dong-Jun Han

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

Computation and Language · Computer Science 2025-10-24 Agam Goyal , Vedant Rathi , William Yeh , Yian Wang , Yuen Chen , Hari Sundaram

Recent work leverages Vision Foundation Models as image encoders to boost the generative performance of latent diffusion models (LDMs), as their semantic feature distributions are easy to learn. However, such semantic features often lack…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Siyu Liu , Chujie Qin , Hubery Yin , Qixin Yan , Zheng-Peng Duan , Chen Li , Jing Lyu , Chun-Le Guo , Chongyi Li

A key barrier to interpreting large language models is polysemanticity, where neurons activate for multiple unrelated concepts. Sparse autoencoders (SAEs) have been proposed to mitigate this issue by transforming dense activations into…

Machine Learning · Computer Science 2025-10-20 Moghis Fereidouni , Muhammad Umair Haider , Peizhong Ju , A. B. Siddique

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

Computation and Language · Computer Science 2023-05-05 Ghazi Felhi

Standard high-dimensional regression methods assume that the underlying coefficient vector is sparse. This might not be true in some cases, in particular in presence of hidden, confounding variables. Such hidden confounding can be…

Methodology · Statistics 2020-08-19 Domagoj Ćevid , Peter Bühlmann , Nicolai Meinshausen

While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but which remains underexplored in vision. We address this gap by…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Sonia Joseph , Praneet Suresh , Ethan Goldfarb , Lorenz Hufe , Yossi Gandelsman , Robert Graham , Danilo Bzdok , Wojciech Samek , Blake Aaron Richards

Recent work on generative modeling of text has found that variational auto-encoders (VAE) incorporating LSTM decoders perform worse than simpler LSTM language models (Bowman et al., 2015). This negative result is so far poorly understood,…

Neural and Evolutionary Computing · Computer Science 2017-06-20 Zichao Yang , Zhiting Hu , Ruslan Salakhutdinov , Taylor Berg-Kirkpatrick

We aim to separate the generative factors of data into two latent vectors in a variational autoencoder. One vector captures class factors relevant to target classification tasks, while the other vector captures style factors relevant to the…

Machine Learning · Computer Science 2020-03-17 Bo-Kyeong Kim , Sungjin Park , Geonmin Kim , Soo-Young Lee

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

Self-supervised disentangled representation learning is a critical task in sequence modeling. The learnt representations contribute to better model interpretability as well as the data generation, and improve the sample efficiency for…

Machine Learning · Computer Science 2021-10-26 Junwen Bai , Weiran Wang , Carla Gomes

The Key-Value (KV) cache is the primary memory bottleneck in long-context Large Language Models, yet it is typically treated as an opaque numerical tensor. In this work, we propose \textbf{STA-Attention}, a framework that utilizes Top-K…

Machine Learning · Computer Science 2025-12-12 Qingsen Ma , Dianyun Wang , Jiaming Lyu , Yaoye Wang , Lechen Ning , Sujie Zhu , Zhenbo Xu , Liuyu Xiang , Huining Li , Huijia Wu , Zhaofeng He

Dynamic head pruning in Vision Transformers (ViTs) improves efficiency by removing redundant attention heads, but existing pruning policies are often difficult to interpret and control. In this work, we propose a novel framework by…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Yousung Lee , Dongsoo Har

Neural conversation models such as encoder-decoder models are easy to generate bland and generic responses. Some researchers propose to use the conditional variational autoencoder(CVAE) which maximizes the lower bound on the conditional…

Computation and Language · Computer Science 2019-11-25 Jun Gao , Wei Bi , Xiaojiang Liu , Junhui Li , Guodong Zhou , Shuming Shi

Accurately predicting counterfactual user feedback is essential for building effective recommender systems. However, latent confounding bias can obscure the true causal relationship between user feedback and item exposure, ultimately…

Information Retrieval · Computer Science 2025-05-23 Jianfeng Deng , Qingfeng Chen , Debo Cheng , Jiuyong Li , Lin Liu , Shichao Zhang

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically rely solely on…

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