English
Related papers

Related papers: ShaLa: Multimodal Shared Latent Space Modelling

200 papers

The manifold hypothesis states that high-dimensional data can be modeled as lying on or near a low-dimensional, nonlinear manifold. Variational Autoencoders (VAEs) approximate this manifold by learning mappings from low-dimensional latent…

Machine Learning · Statistics 2021-03-03 Marissa C. Connor , Gregory H. Canal , Christopher J. Rozell

Vision-Language-Action (VLA) models have emerged as a promising approach for general-purpose robot manipulation. However, their generalization is inconsistent: while these models can perform impressively in some settings, fine-tuned…

Robotics · Computer Science 2026-03-20 Aiden Swann , Lachlain McGranahan , Hugo Buurmeijer , Monroe Kennedy , Mac Schwager

Language models can be equipped with multimodal capabilities by fine-tuning on embeddings of visual inputs. But how do such multimodal models represent images in their hidden activations? We explore representations of image concepts within…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Achyuta Rajaram , Sarah Schwettmann , Jacob Andreas , Arthur Conmy

Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Clément Cornet , Romaric Besançon , Hervé Le Borgne

Multi-modal data-sets are ubiquitous in modern applications, and multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. However, existing approaches suffer…

Machine Learning · Computer Science 2023-12-19 Mustapha Bounoua , Giulio Franzese , Pietro Michiardi

Multimodal AI models have achieved impressive performance in tasks that require integrating information from multiple modalities, such as vision and language. However, their "black-box" nature poses a major barrier to deployment in…

Artificial Intelligence · Computer Science 2026-02-18 Zhanliang Wang , Kai Wang

Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs for interleaved cross-modal reasoning is more promising and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Jiachun Jin , Zetong Zhou , Xiao Yang , Hao Zhang , Pengfei Liu , Jun Zhu , Zhijie Deng

Multimodal datasets contain an enormous amount of relational information, which grows exponentially with the introduction of new modalities. Learning representations in such a scenario is inherently complex due to the presence of multiple…

Machine Learning · Computer Science 2019-09-24 Devanshu Arya , Stevan Rudinac , Marcel Worring

Multimodal learning has mainly focused on learning large models on, and fusing feature representations from, different modalities for better performances on downstream tasks. In this work, we take a detour from this trend and study the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-08 Yifeng Shi , Marc Niethammer

In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enable such functionality, existing methods mainly rely on either…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Yuhuan Yang , Chaofan Ma , Chen Ju , Fei Zhang , Jiangchao Yao , Ya Zhang , Yanfeng Wang

Learning shared representations is a primary area of multimodal representation learning. The current approaches to achieve a shared embedding space rely heavily on paired samples from each modality, which are significantly harder to obtain…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Amitai Yacobi , Nir Ben-Ari , Ronen Talmon , Uri Shaham

Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on discrete reasoning representations that mismatch continuous perception and control. We…

Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…

Machine Learning · Computer Science 2019-04-24 Lijiang Guo

We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural…

Computer Vision and Pattern Recognition · Computer Science 2012-07-09 Jonathan Masci , Michael M. Bronstein , Alexander A. Bronstein , Jürgen Schmidhuber

Multimodal learning enhances the performance of various machine learning tasks by leveraging complementary information across different modalities. However, existing methods often learn multimodal representations that retain substantial…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Tong Zhang , Shu Shen , C. L. Philip Chen

Despite progress, Vision-Language-Action models (VLAs) are limited by a scarcity of large-scale, diverse robot data. While human manipulation videos offer a rich alternative, existing methods are forced to choose between small,…

Robotics · Computer Science 2026-02-26 Hao Luo , Ye Wang , Wanpeng Zhang , Haoqi Yuan , Yicheng Feng , Haiweng Xu , Sipeng Zheng , Zongqing Lu

Multimodal variational autoencoders (VAEs) aim to capture shared latent representations by integrating information from different data modalities. A significant challenge is accurately inferring representations from any subset of modalities…

Machine Learning · Computer Science 2024-10-16 Yuta Oshima , Masahiro Suzuki , Yutaka Matsuo

Multimodal Sentiment Analysis is an active area of research that leverages multimodal signals for affective understanding of user-generated videos. The predominant approach, addressing this task, has been to develop sophisticated fusion…

Computation and Language · Computer Science 2020-10-20 Devamanyu Hazarika , Roger Zimmermann , Soujanya Poria

Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored reverse transitions ignoring cross-token dependencies and…

Machine Learning · Computer Science 2026-05-14 Dario Shariatian , Alain Durmus , Umut Simsekli , Stefano Peluchetti

Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high cost of retraining. While parameter-efficient tuning methods…

Machine Learning · Computer Science 2026-02-06 Prakhar Kaushik , Ankit Vaidya , Shravan Chaudhari , Rama Chellappa , Alan Yuille