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
Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
Cai Zhou, Xiyuan Wang, Muhan Zhang
Closed-Loop Unsupervised Representation Disentanglement with $\beta$-VAE Distillation and Diffusion Probabilistic Feedback
Xin Jin, Bohan Li, BAAO Xie, Wenyao Zhang, Jinming Liu, Ziqiang Li, Tao Yang, Wenjun Zeng
AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error
Jonas Ricker, Denis Lukovnikov, Asja Fischer
Predicting the Future with Simple World Models
Tankred Saanum, Peter Dayan, Eric Schulz
An attempt to generate new bridge types from latent space of energy-based model
Hongjun Zhang
Unsupervised Discovery of Steerable Factors When Graph Deep Generative Models Are Entangled
Shengchao Liu, Chengpeng Wang, Jiarui Lu, Weili Nie, Hanchen Wang, Zhuoxinran Li, Bolei Zhou, Jian Tang
Realizing Disentanglement in LM Latent Space via Vocabulary-Defined Semantics
Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang