Variational Inference

Improved Video VAE for Latent Video Diffusion Model CVPR 2025 Infant Action Generative Modeling WACV 2025 Injective flows for star-like manifolds ICLR 2025 Interaction Asymmetry: A General Principle for Learning Composable Abstractions ICLR 2025 Interpretable Causal Representation Learning for Biological Data in the Pathway Space ICLR 2025 LangVAE and LangSpace: Building and Probing for Language Model VAEs EMNLP 2025 Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data ICLR 2025 Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation ICLR 2025 LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models ICCV 2025 Learned Image Transmission with Hierarchical Variational Autoencoder AAAI 2025 Learning Robust Multi-view Representation Using Dual-masked VAEs IJCAI 2025 Let's Chorus: Partner-aware Hybrid Song-Driven 3D Head Animation CVPR 2025 Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow AAAI 2025 MPBR: Multimodal Progressive Bidirectional Reasoning for Open-Set Fine-Grained Recognition ICCV 2025 Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational Inference ICML 2025 Multi-Modal Latent Variables for Cross-Individual Primary Visual Cortex Modeling and Analysis AAAI 2025 Multimodal Variational Autoencoder: A Barycentric View AAAI 2025 Multi-Scale Fusion for Object Representation ICLR 2025 Multi-Task Learning of Classification and Generation for Set-Structured Data WACV 2025 Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory Prediction ICLR 2025 On the Trainability and Classical Simulability of Learning Matrix Product States Variationally AAAI 2025 Partial Texture VAE: Color and Texture Encoder for Rock Particle Images WACV 2025 Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach AAAI 2025 Phenotypic Profile-Informed Generation of Drug-Like Molecules via Dual-Channel Variational Autoencoders IJCAI 2025 PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders ICLR 2025