English
Related papers

Related papers: Emergence and Evolution of Interpretable Concepts …

200 papers

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…

The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content's structure through statistical learning alone. This…

Sound · Computer Science 2026-03-03 Nikhil Singh , Manuel Cherep , Pattie Maes

Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learned by these models remain an enigma. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Hila Chefer , Oran Lang , Mor Geva , Volodymyr Polosukhin , Assaf Shocher , Michal Irani , Inbar Mosseri , Lior Wolf

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior.…

Machine Learning · Computer Science 2026-02-06 Xu Wang , Bingqing Jiang , Yu Wan , Baosong Yang , Lingpeng Kong , Difan Zou

Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches offer potential solutions but often lack transparency, making…

Machine Learning · Computer Science 2025-05-23 Bartosz Cywiński , Kamil Deja

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…

Machine Learning · Computer Science 2025-07-14 Stepan Shabalin , Ayush Panda , Dmitrii Kharlapenko , Abdur Raheem Ali , Yixiong Hao , Arthur Conmy

Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Matthew Lyle Olson , Musashi Hinck , Neale Ratzlaff , Changbai Li , Phillip Howard , Vasudev Lal , Shao-Yen Tseng

Diffusion Transformers (DiTs) are a powerful yet underexplored class of generative models compared to U-Net-based diffusion architectures. We propose TIDE-Temporal-aware sparse autoencoders for Interpretable Diffusion transformErs-a…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Victor Shea-Jay Huang , Le Zhuo , Yi Xin , Zhaokai Wang , Fu-Yun Wang , Yuchi Wang , Renrui Zhang , Peng Gao , Hongsheng Li

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-10 Philippe Gonzalez , Zheng-Hua Tan , Jan Østergaard , Jesper Jensen , Tommy Sonne Alstrøm , Tobias May

Diffusion-based models have gained significant popularity for text-to-image generation due to their exceptional image-generation capabilities. A risk with these models is the potential generation of inappropriate content, such as biased or…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Hang Li , Chengzhi Shen , Philip Torr , Volker Tresp , Jindong Gu

Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and race. These biases…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Yingdong Shi , Changming Li , Yifan Wang , Yongxiang Zhao , Anqi Pang , Sibei Yang , Jingyi Yu , Kan Ren

While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature requires compression that obscures semantic meaning, and…

Machine Learning · Computer Science 2025-10-31 Nathan Paek , Yongyi Zang , Qihui Yang , Randal Leistikow

Text-to-image diffusion models generate images through an iterative denoising process, so internal neural layers produce trajectories of activations rather than single static representations. Sparse autoencoders (SAEs) have recently been…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Calvin Yeung , Prathyush Poduval , Ali Zakeri , Zhuowen Zou , Mohsen Imani

RFdiffusion is a popular and well-established model for generation of protein structures. However, this generative process offers limited insight into its internal representations and how they contribute to the final protein structure.…

Quantitative Methods · Quantitative Biology 2025-12-01 Wojciech Zarzecki , Paulina Szymczak , Ewa Szczurek , Kamil Deja

Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of fine-tuning pre-trained models using domain-specific text-to-image datasets.…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Mischa Dombrowski , Hadrien Reynaud , Johanna P. Müller , Matthew Baugh , Bernhard Kainz

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

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…

Taking advantage of the many recent advances in deep learning, text-to-image generative models currently have the merit of attracting the general public attention. Two of these models, DALL-E 2 and Imagen, have demonstrated that highly…

Computer Vision and Pattern Recognition · Computer Science 2022-09-23 Robin Zbinden

Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show…

Machine Learning · Computer Science 2026-04-03 Lingjing Kong , Shaoan Xie , Guangyi Chen , Yuewen Sun , Xiangchen Song , Eric P. Xing , Kun Zhang

This survey reviews the progress of diffusion models in generating images from text, ~\textit{i.e.} text-to-image diffusion models. As a self-contained work, this survey starts with a brief introduction of how diffusion models work for…

Computer Vision and Pattern Recognition · Computer Science 2024-11-11 Chenshuang Zhang , Chaoning Zhang , Mengchun Zhang , In So Kweon , Junmo Kim
‹ Prev 1 2 3 10 Next ›