Search Results for author:
Found 10 papers, 6 papers with code
Truncated Consistency Models
Consistency models have recently been introduced to accelerate sampling from diffusion models by directly predicting the solution (i. e., data) of the probability flow ODE (PF ODE) from initial noise.
Ranked #14 on
Image Generation
on ImageNet 64x64
Improving the Training of Rectified Flows
In this work, we propose improved techniques for training rectified flows, allowing them to compete with \emph{knowledge distillation} methods even in the low NFE setting.
Ranked #22 on
Image Generation
on ImageNet 64x64
Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate
Fact-checking research has extensively explored verification but less so the generation of natural-language explanations, crucial for user trust.
Sequential Data Generation with Groupwise Diffusion Process
We present the Groupwise Diffusion Model (GDM), which divides data into multiple groups and diffuses one group at one time interval in the forward diffusion process.
Minimizing Trajectory Curvature of ODE-based Generative Models
Based on the relationship between the forward process and the curvature, here we present an efficient method of training the forward process to minimize the curvature of generative trajectories without any ODE/SDE simulation.
Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis
We further propose a blur diffusion as a special case, where each frequency component of an image is diffused at different speeds.
High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions
Image-based virtual try-on aims to synthesize an image of a person wearing a given clothing item.
Ranked #4 on
Virtual Try-on
on VITON-HD
Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution
Although the goal of training the degradation generator is to approximate the distribution of LR images given a HR image, previous works have heavily relied on the unrealistic assumption that the conditional distribution is a delta function and learned the deterministic mapping from the HR image to a LR image.
Inertial effects on the Brownian gyrator
Another unique feature of the Langevin description is that rotation is maximized at a particular anisotropy while the stability of the rotation is minimized at a particular anisotropy or mass.
Statistical Mechanics
Learning entropy production via neural networks
This Letter presents a neural estimator for entropy production, or NEEP, that estimates entropy production (EP) from trajectories of relevant variables without detailed information on the system dynamics.
