research
∙
05/25/2023
DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
Learning from human feedback has been shown to improve text-to-image mod...
share
research
∙
05/05/2023
Disruptive papers in science are losing impact
The impact and originality are two critical dimensions for evaluating sc...
research
∙
03/13/2023
Domain Generalization via Nuclear Norm Regularization
The ability to generalize to unseen domains is crucial for machine learn...
research
∙
01/31/2023
Optimizing DDPM Sampling with Shortcut Fine-Tuning
In this study, we propose Shortcut Fine-tuning (SFT), a new approach for...
research
∙
12/13/2022
Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance
Score-based generative models are shown to achieve remarkable empirical ...
research
∙
08/13/2022
Impactful scientists have higher tendency to involve collaborators in new topics
In scientific research, collaboration is one of the most effective ways ...
research
∙
06/28/2022
POEM: Out-of-Distribution Detection with Posterior Sampling
Out-of-distribution (OOD) detection is indispensable for machine learnin...
research
∙
04/29/2021
Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling
One of the difficulties of conversion rate (CVR) prediction is that the ...
research
∙
06/10/2020
Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
Rich user behavior data has been proven to be of great value for click-t...
research
∙
12/11/2018
Efficient Model-Free Reinforcement Learning Using Gaussian Process
Efficient Reinforcement Learning usually takes advantage of demonstratio...
research
∙
12/10/2018
Increasing trend of scientists to switch between topics
We analyze the publication records of individual scientists, aiming to q...
research
∙
09/11/2018
Deep Interest Evolution Network for Click-Through Rate Prediction
Click-through rate (CTR) prediction, whose goal is to estimate the proba...
research
∙
08/14/2017