Molecular generation with diffusion models has emerged as a promising direction for AI-driven drug discovery and materials science. While graph diffusion models have been widely adopted due to the discrete nature of 2D molecular graphs, existing models suffer from low chemical validity and struggle to meet the desired properties compared to 1D modeling. In this work, we introduce MolHIT, a powerful molecular graph generation framework that overcomes long-standing performance limitations in existing methods. MolHIT is based on the Hierarchical Discrete Diffusion Model, which generalizes discrete diffusion to additional categories that encode chemical priors, and decoupled atom encoding that splits the atom types according to their chemical roles. Overall, MolHIT achieves new state-of-the-art performance on the MOSES dataset with near-perfect validity for the first time in graph diffusion, surpassing strong 1D baselines across multiple metrics. We further demonstrate strong performance in downstream tasks, including multi-property guided generation and scaffold extension.
DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces
University of Science and Technology of China(中国科学技术大学);Shanghai Jiao Tong University(上海交通大学);Zhejiang University(浙江大学);East China Normal University(华东师范大学);Peking University(北京大学);Emory University(埃默里大学);Hefei University of Technology(合肥工业大学);Jianghuai Advance Technology Center(江淮先进技术中心);Anhui Provincial Key Laboratory of Humanoid Robots(安徽省人形机器人重点实验室)
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
Shanghai Innovation Institute(上海创新研究院);Fudan University(复旦大学);University of Science and Technology of China(中国科学技术大学);Shanghai Jiao Tong University(上海交通大学);Zhejiang University(浙江大学);Westlake University(西湖大学);Nanjing University(南京大学);University of Southern California(南加州大学)