Variational Inference

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer CVPR 2025 SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image Reconstruction AAAI 2025 Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold ICLR 2025 Streamlining Prediction in Bayesian Deep Learning ICLR 2025 Structural Entropy Guided Probabilistic Coding AAAI 2025 Structured IB: Improving Information Bottleneck with Structured Feature Learning AAAI 2025 SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints AAAI 2025 Support is All You Need for Certified VAE Training ICLR 2025 Time Series Supplier Allocation via Deep Black-Litterman Model AAAI 2025 Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction ICLR 2025 Towards Universal AI-Generated Image Detection by Variational Information Bottleneck Network CVPR 2025 Traversing Distortion-Perception Tradeoff using a Single Score-Based Generative Model CVPR 2025 Unbiased Missing-modality Multimodal Learning ICCV 2025 Uncertainty Aware Interest Point Detection and Description WACV 2025 Unity in Diversity: Video Editing via Gradient-Latent Purification CVPR 2025 Unlearning-based Neural Interpretations ICLR 2025 Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noise WACV 2025 USP: Unified Self-Supervised Pretraining for Image Generation and Understanding ICCV 2025 UTBNLP at Semeval-2025 Task 11: Predicting Emotion Intensity with BERT and VAD-Informed Attention. SemEval 2025 VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction COLING 2025 VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in Meteorology ICLR 2025 Variational Bayesian Pseudo-Coreset ICLR 2025 Variational Best-of-N Alignment ICLR 2025 Variational Counterfactual Intervention Planning to Achieve Target Outcomes ICML 2025 Variational Diffusion Posterior Sampling with Midpoint Guidance ICLR 2025