most citedDiffusion Model for Data-Driven Black-Box Optimization

3 citations · 7 across the 7 of their papers we have counts for

collaborators

7 papers

eess.IV2024

SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds

Xiaolong Mao, Hui Yuan, Tian Guo +3

We propose an end-to-end attribute compression method for dense point clouds. The proposed method combines a frequency sampling module, an adaptive scale feature extraction module…

cs.LG20243 cited

Diffusion Model for Data-Driven Black-Box Optimization

Zihao Li, Hui Yuan, Kaixuan Huang +4

Generative AI has redefined artificial intelligence, enabling the creation of innovative content and customized solutions that drive business practices into a new era of efficiency…

cs.LG20232 cited

Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement

Hui Yuan, Kaixuan Huang, Chengzhuo Ni +2

We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measur…

physics.optics20231 cited

600-GHz Fourier Imaging Based on Heterodyne Detection at the 2nd Sub-harmonic

Hui Yuan, Alvydas Lisauskas, Mark D. Thomson +1

Fourier imaging is an indirect imaging method which records the diffraction pattern of the object scene coherently in the focal plane of the imaging system and reconstructs the ima…

cs.LG20231 cited

Adversarial Attacks on Online Learning to Rank with Stochastic Click Models

Zichen Wang, Rishab Balasubramanian, Hui Yuan +3

We propose the first study of adversarial attacks on online learning to rank. The goal of the adversary is to misguide the online learning to rank algorithm to place the target ite…

cs.CV2023

Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation

Zihao Li, Pan Gao, Hui Yuan +2

Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud. Most existing methods focus…