4 papers
Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation
Cai Zhou, Zijie Chen, Zian Li +7
Many generative tasks in chemistry and science involve distributions invariant to group symmetries (e.g., permutation and rotation). A common strategy enforces invariance and equiv…
GR-Diffusion: 3D Gaussian Representation Meets Diffusion in Whole-Body PET Reconstruction
Mengxiao Geng, Zijie Chen, Ran Hong +2
Positron emission tomography (PET) reconstruction is a critical challenge in molecular imaging, often hampered by noise amplification, structural blurring, and detail loss due to s…
More Bang for the Buck: Process Reward Modeling with Entropy-Driven Uncertainty
Lang Cao, Renhong Chen, Yingtian Zou +9
We introduce the Entropy-Driven Uncertainty Process Reward Model (EDU-PRM), a novel entropy-driven training framework for process reward modeling that enables dynamic, uncertainty-…
Conductive and Radiative Heat Transfer Mechanisms Inform Nusselt Number Dependence on Solid Volume Fraction for Granular Flows
Bingjia Li, Zijie Chen, Rohini Bala Chandran
Granular flows with solid particles play an important role in energy and catalysis applications. To predict thermal performance, this study develops a comprehensive discrete partic…