latent representation

Learning topology-preserving data representations ICLR 2023 LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification ICLR 2023 Marginalization is not Marginal: No Bad VAE Local Minima when Learning Optimal Sparse Representations ICML 2023 Modality-Agnostic Variational Compression of Implicit Neural Representations ICML 2023 MultiMoDN—Multimodal, Multi-Task, Interpretable Modular Networks NeurIPS 2023 Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve ICLR 2023 Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes NeurIPS 2023 Neural Video Compression With Diverse Contexts CVPR 2023 QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity CVPR 2023 Raw Image Reconstruction With Learned Compact Metadata CVPR 2023 ReEnFP: Detail-Preserving Face Reconstruction by Encoding Facial Priors WACV 2023 RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability NeurIPS 2023 Robot Learning with Sensorimotor Pre-training CoRL 2023 Robust Variational Autoencoding with Wasserstein Penalty for Novelty Detection AISTATS 2023 Self-Supervised Solution to the Control Problem of Articulatory Synthesis Interspeech 2023 SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series ICML 2023 TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization ICLR 2023 The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models EMNLP 2023 Trading Information between Latents in Hierarchical Variational Autoencoders ICLR 2023 Understanding Self-Predictive Learning for Reinforcement Learning ICML 2023 Unscented Autoencoder ICML 2023 Unsupervised Opinion Summarization Using Approximate Geodesics EMNLP 2023 Vacant holes for unsupervised detection of the outliers in compact latent representation UAI 2023 Vector Quantized Wasserstein Auto-Encoder ICML 2023 VISinger2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer Interspeech 2023