English
Related papers

Related papers: Conceptualizing Embeddings: Sparse Disentanglement…

200 papers

Recent advances in multimodal Parameter-Efficient Fine-Tuning (PEFT) have significantly improved performance on downstream tasks such as few-shot retrieval. However, most existing approaches focus on task-specific gains while neglecting the…

Artificial Intelligence · Computer Science 2025-08-20 Thye Shan Ng , Caren Soyeon Han , Eun-Jung Holden

Pre-trained vision-language models, e.g., CLIP, have been successfully applied to zero-shot semantic segmentation. Existing CLIP-based approaches primarily utilize visual features from the last layer to align with text embeddings, while…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Yunheng Li , ZhongYu Li , Quansheng Zeng , Qibin Hou , Ming-Ming Cheng

Vision-language models such as CLIP have shown impressive capabilities in encoding texts and images into aligned embeddings, enabling the retrieval of multimodal data in a shared embedding space. However, these embedding-based models still…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Timothy Ossowski , Ming Jiang , Junjie Hu

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

This paper introduces VLAP, a novel approach that bridges pretrained vision models and large language models (LLMs) to make frozen LLMs understand the visual world. VLAP transforms the embedding space of pretrained vision models into the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Jungin Park , Jiyoung Lee , Kwanghoon Sohn

Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently been shown that SAEs…

Machine Learning · Computer Science 2025-05-23 Soham Gadgil , Chris Lin , Su-In Lee

Contemporary deep learning architectures lack principled means for capturing and handling fundamental visual concepts, like objects, shapes, geometric transforms, and other higher-level structures. We propose a neurosymbolic architecture…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Krzysztof Krawiec , Antoni Nowinowski

Sparse autoencoders (SAEs) have emerged as powerful techniques for interpretability of large language models (LLMs), aiming to decompose hidden states into meaningful semantic features. While several SAE variants have been proposed, there…

Machine Learning · Computer Science 2025-10-03 Xudong Zhu , Mohammad Mahdi Khalili , Zhihui Zhu

Enabling Visual Semantic Models to effectively handle multi-view description matching has been a longstanding challenge. Existing methods typically learn a set of embeddings to find the optimal match for each view's text and compute…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Yang Liu , Wentao Feng , Zhuoyao Liu , Shudong Huang , Jiancheng Lv

Vision-and-language (V-L) tasks require the system to understand both vision content and natural language, thus learning fine-grained joint representations of vision and language (a.k.a. V-L representations) is of paramount importance.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Fenglin Liu , Xian Wu , Shen Ge , Xuancheng Ren , Wei Fan , Xu Sun , Yuexian Zou

Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks, primarily large language models, into sets of interpretable features. However, adapting them to domains beyond language, such as…

Machine Learning · Computer Science 2025-11-13 Ege Erdogan , Ana Lucic

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

Autoencoding has achieved great empirical success as a framework for learning generative models for natural images. Autoencoders often use generic deep networks as the encoder or decoder, which are difficult to interpret, and the learned…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Xili Dai , Ke Chen , Shengbang Tong , Jingyuan Zhang , Xingjian Gao , Mingyang Li , Druv Pai , Yuexiang Zhai , XIaojun Yuan , Heung-Yeung Shum , Lionel M. Ni , Yi Ma

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

Computer Vision and Pattern Recognition · Computer Science 2017-06-06 Dong Li , Hsin-Ying Lee , Jia-Bin Huang , Shengjin Wang , Ming-Hsuan Yang

Learning continuous representations of discrete objects such as text, users, movies, and URLs lies at the heart of many applications including language and user modeling. When using discrete objects as input to neural networks, we often…

Machine Learning · Computer Science 2021-03-12 Paul Pu Liang , Manzil Zaheer , Yuan Wang , Amr Ahmed

We introduce Sparse Concept Anchoring, a method that biases latent space to position a targeted subset of concepts while allowing others to self-organize, using only minimal supervision (labels for <0.1% of examples per anchored concept).…

Machine Learning · Computer Science 2026-04-28 Sandy Fraser , Patryk Wielopolski

CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Rui Xiao , Sanghwan Kim , Mariana-Iuliana Georgescu , Zeynep Akata , Stephan Alaniz

Recently introduced Contrastive Language-Image Pre-Training (CLIP) bridges images and text by embedding them into a joint latent space. This opens the door to ample literature that aims to manipulate an input image by providing a textual…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Chenliang Zhou , Fangcheng Zhong , Cengiz Oztireli

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Machine Learning · Computer Science 2026-05-19 Katarzyna Filus , Kamil Faber , Roberto Corizzo , Christopher Kanan

Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks. While existing methods are effective at mitigating biases by linear projection, such methods are too…

Computation and Language · Computer Science 2021-09-14 Sunipa Dev , Tao Li , Jeff M Phillips , Vivek Srikumar