Search Results for author:
Found 4 papers, 3 papers with code
Constant Acceleration Flow
Moreover, we propose two techniques to further improve estimation accuracy: initial velocity conditioning for the acceleration model and a reflow process for the initial velocity.
Ranked #15 on
Image Generation
on ImageNet 64x64
Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems
Recent studies on inverse problems have proposed posterior samplers that leverage the pre-trained diffusion models as powerful priors.
Ranked #1 on
Image Super-Resolution
on ImageNet
(using extra training data)
A Comprehensive Survey of Compression Algorithms for Language Models
How can we compress language models without sacrificing accuracy?
DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
Arguably, this architecture limits the expressive power of generative models and results in low-quality INR generation.
Ranked #3 on
Video Generation
on Sky Time-lapse
