Latest

• DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
• Fast Training of Diffusion Models with Masked Transformers
• Differentially Private Diffusion Models
• PhysDiff: Physics-Guided Human Motion Diffusion Model
• Fast Sampling of Diffusion Models via Operator Learning
• I^2SB: Image-to-Image Schrödinger Bridge
• Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation
• Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
• Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models
• Pseudoinverse-Guided Diffusion Models for Inverse Problems
• GENIE: Higher-Order Denoising Diffusion Solvers
• LION: Latent Point Diffusion Models for 3D Shape Generation
• LANA: Latency Aware Network Acceleration
• Diffusion Models for Adversarial Purification
• A-ViT: Adaptive Tokens for Efficient Vision Transformer
• Score-Based Generative Modeling with Critically-Damped Langevin Diffusion
• Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• Controllable and Compositional Generation with Latent-Space Energy-Based Models
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
• Score-based Generative Modeling in Latent Space
• See through Gradients: Image Batch Recovery via GradInversion
• VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
• NVAE: A Deep Hierarchical Variational Autoencoder
• On the Distance between Two Neural Networks and the Stability of Learning
• Contrastive Learning for Weakly Supervised Phrase Grounding
• Undirected Graphical Models as Approximate Posteriors
• Semi-Supervised Semantic Image Segmentation with Self-correcting Networks
• UNAS: Differentiable Architecture Search Meets Reinforcement Learning