Tag
DeepRHP is a hybrid variational autoencoder that guides the design of random heteropolymers as protein mimics, demonstrated by stabilizing membrane proteins like Aquaporin Z in non-native environments.
This paper presents a Mahalanobis-guided latent out-of-distribution detection method using a VAE to switch between a reinforcement learning controller and an extremum seeking controller in time-varying systems, validated in particle accelerator control.
This paper introduces GNOVA, a GRU-Neural ODE Variational Autoencoder framework for reconstructing and forecasting Alzheimer's disease cognitive trajectories from routine clinical data without expensive neuroimaging or biomarkers, achieving low error and uncertainty estimation on the ADNI dataset.
This paper presents a probabilistic post-processing framework using conditional variational autoencoders (cVAEs) to bias-adjust seasonal forecasts of Arctic sea ice, improving calibration, sharpness, and spectral power over standard methods.
This paper introduces the neural codebook channel diagnostic for VAEs, which measures encoder-decoder disagreement and provides a certificate bounded by the variational gap, enabling detection of mismatched decoding in deep generative models.
This paper presents Conv-VaDE, a variational deep embedding model for interpretable EEG microstate discovery that jointly learns topographic reconstruction and probabilistic soft clustering. It includes a systematic architecture search evaluated on resting-state EEG data to determine optimal model configurations for stability and interpretability.
Qwen-Image-VAE-2.0 is a high-compression Variational Autoencoder suite that improves reconstruction fidelity and diffusability through enhanced architecture, large-scale training, and semantic alignment strategies.
This paper introduces a two-stage neuro-symbolic framework that uses weak supervision (as little as 1% labels) with a slot-based VAE to learn interpretable symbols for object-centric visual reasoning, outperforming foundation models in domain generalization.
OpenAI researchers present a Variational Lossy Autoencoder (VLAE) that combines VAEs with neural autoregressive models (RNN, MADE, PixelRNN/CNN) to learn controllable global representations, achieving state-of-the-art results on MNIST, OMNIGLOT, and Caltech-101 Silhouettes density estimation tasks.