Latent Space
Latent space refers to a lower-dimensional representation of high-dimensional data, aiming to capture essential features while reducing computational complexity and improving interpretability. Current research focuses on developing efficient algorithms and model architectures, such as variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models, to learn and manipulate these latent spaces for tasks ranging from anomaly detection and image generation to controlling generative models and improving the efficiency of autonomous systems. This work has significant implications across diverse fields, enabling advancements in areas like drug discovery, autonomous driving, and cybersecurity through improved data analysis, model efficiency, and enhanced control over generative processes.
Papers
FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space
Shengzhong Liu, Tomoyoshi Kimura, Dongxin Liu, Ruijie Wang, Jinyang Li, Suhas Diggavi, Mani Srivastava, Tarek Abdelzaher
Conditional Unscented Autoencoders for Trajectory Prediction
Faris Janjoš, Marcel Hallgarten, Anthony Knittel, Maxim Dolgov, Andreas Zell, J. Marius Zöllner
Learning Low-Rank Latent Spaces with Simple Deterministic Autoencoder: Theoretical and Empirical Insights
Alokendu Mazumder, Tirthajit Baruah, Bhartendu Kumar, Rishab Sharma, Vishwajeet Pattanaik, Punit Rathore
IA Para el Mantenimiento Predictivo en Canteras: Modelado
Fernando Marcos, Rodrigo Tamaki, Mateo Cámara, Virginia Yagüe, José Luis Blanco
Learning Dynamics in Linear VAE: Posterior Collapse Threshold, Superfluous Latent Space Pitfalls, and Speedup with KL Annealing
Yuma Ichikawa, Koji Hukushima
Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space
Hengrui Zhang, Jiani Zhang, Balasubramaniam Srinivasan, Zhengyuan Shen, Xiao Qin, Christos Faloutsos, Huzefa Rangwala, George Karypis
Learning In-between Imagery Dynamics via Physical Latent Spaces
Jihun Han, Yoonsang Lee, Anne Gelb
Explorable Mesh Deformation Subspaces from Unstructured Generative Models
Arman Maesumi, Paul Guerrero, Vladimir G. Kim, Matthew Fisher, Siddhartha Chaudhuri, Noam Aigerman, Daniel Ritchie
Exploring Social Motion Latent Space and Human Awareness for Effective Robot Navigation in Crowded Environments
Junaid Ahmed Ansari, Satyajit Tourani, Gourav Kumar, Brojeshwar Bhowmick