Turnitin
降AI改写
早检测系统
早降重系统
Turnitin-UK版
万方检测-期刊版
维普编辑部版
Grammarly检测
Paperpass检测
checkpass检测
PaperYY检测
Generative flows on discrete state-spaces: Enabling multimodal flows with applications to protein co-design
Combining discrete and continuous data is an important capability for generative models.
We present Discrete Flow Models (DFMs), a new flow-based model of discrete data that …
We present Discrete Flow Models (DFMs), a new flow-based model of discrete data that …
View-decoupled transformer for person re-identification under aerial-ground camera network
Existing person re-identification methods have achieved remarkable advances in
appearance-based identity association across homogeneous cameras such as ground …
appearance-based identity association across homogeneous cameras such as ground …
Tackling the singularities at the endpoints of time intervals in diffusion models
Most diffusion models assume that the reverse process adheres to a Gaussian distribution.
However this approximation has not been rigorously validated especially at singularities …
However this approximation has not been rigorously validated especially at singularities …
Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces
Energy-based models (EBMs) offer a flexible framework for probabilistic modelling across
various data domains. However, training EBMs on data in discrete or mixed state spaces …
various data domains. However, training EBMs on data in discrete or mixed state spaces …
Discrete Modeling via Boundary Conditional Diffusion Processes
We present an novel framework for efficiently and effectively extending the powerful
continuous diffusion processes to discrete modeling. Previous approaches have suffered …
continuous diffusion processes to discrete modeling. Previous approaches have suffered …
Solving Prior Distribution Mismatch in Diffusion Models via Optimal Transport
In recent years, the knowledge surrounding diffusion models (DMs) has grown significantly,
though several theoretical gaps remain. Particularly noteworthy is prior error, defined as the …
though several theoretical gaps remain. Particularly noteworthy is prior error, defined as the …
Exploring Straighter Trajectories of Flow Matching with Diffusion Guidance
Flow matching as a paradigm of generative model achieves notable success across various
domains. However, existing methods use either multi-round training or knowledge within …
domains. However, existing methods use either multi-round training or knowledge within …
Elucidating Flow Matching ODE Dynamics with respect to Data Geometries
Diffusion-based generative models have become the standard for image generation. ODE-
based samplers and flow matching models improve efficiency, in comparison to diffusion …
based samplers and flow matching models improve efficiency, in comparison to diffusion …
Gradient-Free Analytical Fisher Information of Diffused Distributions
Diffusion models (DMs) have demonstrated powerful distributional modeling capabilities by
matching the first-order score of diffused distributions. Recent advancements have explored …
matching the first-order score of diffused distributions. Recent advancements have explored …