4 papers
From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
Haozhe Huang, Yudong Xu, Abhijoy Mandal +1
Discrete diffusion models offer a powerful framework for solving complex reasoning tasks, particularly through compositional generation, which combines multiple pre-trained experts…
De novo molecular generation with optical property preconditioning at the token level
Haozhe Huang, Manuel Gonzalez Lastre, Hyun Suk Park +3
Designing OLED molecules with targeted optical properties remains challenging due to the scarcity of high-quality data and the limited reliability of conditional control in generat…
Quantum circuits as a game: A reinforcement learning agent for quantum compilation and its application to reconfigurable neutral atom arrays
Kouhei Nakaji, Jonathan Wurtz, Haozhe Huang +4
We introduce the "quantum circuit daemon" (QC-Daemon), a reinforcement learning agent for compiling quantum device operations aimed at efficient quantum hardware execution. We appl…
Symmetry From Scratch: Group Equivariance as a Supervised Learning Task
Haozhe Huang, Leo Kaixuan Cheng, Kaiwen Chen +1
In machine learning datasets with symmetries, the paradigm for backward compatibility with symmetry-breaking has been to relax equivariant architectural constraints, engineering ex…