16 citations · 26 across the 12 of their papers we have counts for
12 papers
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Ye Yuan, Weien Li, Rui Song +20
Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and ite…
Evaluating the Diversity of AI-Generated Content with Diversity Profiles
Xiuyuan Hu, Xuege Hou, Guoqing Liu +6
Diversity is a fundamental criterion for evaluating generative artificial intelligence (AI) systems, yet its measurement remains inherently ambiguous. Existing approaches typically…
CycleChemist: A Dual-Pronged Machine Learning Framework for Organic Photovoltaic Discovery
Hou Hei Lam, Jiangjie Qiu, Xiuyuan Hu +5
Organic photovoltaic (OPV) materials offer a promising path toward sustainable energy generation, but their development is limited by the difficulty of identifying high performance…
Leveraging Reference Documents for Zero-Shot Ranking via Large Language Models
Jieran Li, Xiuyuan Hu, Yang Zhao +2
Large Language Models (LLMs) have demonstrated exceptional performance in the task of text ranking for information retrieval. While Pointwise ranking approaches offer computational…
Accelerating High-Efficiency Organic Photovoltaic Discovery via Pretrained Graph Neural Networks and Generative Reinforcement Learning
Jiangjie Qiu, Hou Hei Lam, Xiuyuan Hu +5
Organic photovoltaic (OPV) materials offer a promising avenue toward cost-effective solar energy utilization. However, optimizing donor-acceptor (D-A) combinations to achieve high…
TransDiffSBDD: Causality-Aware Multi-Modal Structure-Based Drug Design
Xiuyuan Hu, Guoqing Liu, Can Chen +3
Structure-based drug design (SBDD) is a critical task in drug discovery, requiring the generation of molecular information across two distinct modalities: discrete molecular graphs…
3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery
Xiuyuan Hu, Guoqing Liu, Can Chen +3
Structure-based drug discovery, encompassing the tasks of protein-ligand docking and pocket-aware 3D drug design, represents a core challenge in drug discovery. However, no existin…
When Will Gradient Regularization Be Harmful?
Yang Zhao, Hao Zhang, Xiuyuan Hu
Gradient regularization (GR), which aims to penalize the gradient norm atop the loss function, has shown promising results in training modern over-parameterized deep neural network…
Empirical Evidence for the Fragment level Understanding on Drug Molecular Structure of LLMs
Xiuyuan Hu, Guoqing Liu, Yang Zhao +1
AI for drug discovery has been a research hotspot in recent years, and SMILES-based language models has been increasingly applied in drug molecular design. However, no work has exp…
De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
Xiuyuan Hu, Guoqing Liu, Yang Zhao +1
De novo drug design is a pivotal issue in pharmacology and a new area of focus in AI for science research. A central challenge in this field is to generate molecules with specific…
Randomized Sharpness-Aware Training for Boosting Computational Efficiency in Deep Learning
Yang Zhao, Hao Zhang, Xiuyuan Hu
By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algori…
Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning
Yang Zhao, Hao Zhang, Xiuyuan Hu
How to train deep neural networks (DNNs) to generalize well is a central concern in deep learning, especially for severely overparameterized networks nowadays. In this paper, we pr…