Variational Inference

Posterior and Variational Inference for Deep Neural Networks with Heavy-Tailed Weights JMLR 2025 Preference Diffusion for Recommendation ICLR 2025 Progressive Compression with Universally Quantized Diffusion Models ICLR 2025 Prototype Conditioned Generative Replay for Continual Learning in NLP NAACL 2025 QuantileFormer: Probabilistic Time Series Forecasting with a Pattern-Mixture Decomposed VAE Transformer IJCAI 2025 Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder CoNLL 2025 Rapid Mismatch Estimation via Neural Network Informed Variational Inference CoRL 2025 RapVerse: Coherent Vocals and Whole-Body Motion Generation from Text ICCV 2025 Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models CVPR 2025 REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents ICCV 2025 Regularized Rényi Divergence Minimization through Bregman Proximal Gradient Algorithms JMLR 2025 REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers ICCV 2025 Representing 3D Shapes with 64 Latent Vectors for 3D Diffusion Models ICCV 2025 Repulsive Latent Score Distillation for Solving Inverse Problems ICLR 2025 Residual Deep Gaussian Processes on Manifolds ICLR 2025 Revisiting Unbiased Implicit Variational Inference ICML 2025 Reviving Poor Object Segmentations in OOD Medical Images using Variational-Deep-PCA Modeling on Segmentation Maps with Sampling-Free Learning WACV 2025 Robust Multimodal Survival Prediction with Conditional Latent Differentiation Variational AutoEncoder CVPR 2025 S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling ACL 2025 Scalable and Efficient Probabilistic Inference for Bayesian Deep Learning and Generative Modeling AAAI 2025 Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction ICLR 2025 SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning ICCV 2025 Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions CVPR 2025 Socially-Informed Reconstruction for Pedestrian Trajectory Forecasting WACV 2025 SoftCVI: Contrastive variational inference with self-generated soft labels ICLR 2025