research
∙
05/02/2023
DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning
Compositional Zero-shot Learning (CZSL) aims to recognize novel concepts...
share
research
∙
10/03/2022
Omnigrok: Grokking Beyond Algorithmic Data
Grokking, the unusual phenomenon for algorithmic datasets where generali...
research
∙
09/22/2022
Poisson Flow Generative Models
We propose a new "Poisson flow" generative model (PFGM) that maps a unif...
research
∙
05/20/2022
Towards Understanding Grokking: An Effective Theory of Representation Learning
We aim to understand grokking, a phenomenon where models generalize long...
research
∙
03/23/2022
AI Poincaré 2.0: Machine Learning Conservation Laws from Differential Equations
We present a machine learning algorithm that discovers conservation laws...
research
∙
06/08/2020
