AI tasks encompass a wide range of domains and fields. While numerous AI...
Fusing camera with LiDAR is a promising technique to improve the accurac...
Diffusion models have emerged as a powerful tool for point cloud generat...
Deep generative models have shown success in generating 3D shapes with
d...
We propose a family of First Hitting Diffusion Models (FHDM), deep gener...
AI-based molecule generation provides a promising approach to a large ar...
Diffusion-based generative models have achieved promising results recent...
Mixture of Experts (MoE) is able to scale up vision transformers effecti...
Although traditional optimization methods focus on finding a single opti...
Generating images from natural language instructions is an intriguing ye...
Self-attention, as the key block of transformers, is a powerful mechanis...
We propose firefly neural architecture descent, a general framework for
...
Despite the great success of deep learning, recent works show that large...
We propose signed splitting steepest descent (S3D), which progressively ...
Designing energy-efficient networks is of critical importance for enabli...
We develop a progressive training approach for neural networks which
ada...
Optimizing a network of maps among a collection of objects/domains (or m...