Jan Kautz

Latest

• DiffiT: Diffusion Vision Transformers for Image Generation
• A Variational Perspective on Solving Inverse Problems with Diffusion Models
• Learning to Jointly Understand Visual and Tactile Signals
• PhysDiff: Physics-Guided Human Motion Diffusion Model
• SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models
• Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation
• Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models
• Online Consistent Video Depth using Continuous Geometric Representations
• Pseudoinverse-Guided Diffusion Models for Inverse Problems
• LANA: Latency Aware Network Acceleration
• A-ViT: Adaptive Tokens for Efficient Vision Transformer
• Neural Interferometry: Image Reconstruction from Astronomical Interferometers using Transformer-Conditioned Neural Fields
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• Score-based Generative Modeling in Latent Space
• See through Gradients: Image Batch Recovery via GradInversion
• Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models
• VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
• NVAE: A Deep Hierarchical Variational Autoencoder
• Contrastive Learning for Weakly Supervised Phrase Grounding
• UNAS: Differentiable Architecture Search Meets Reinforcement Learning