Binxu Wang

Analytical Theory of Spectral Bias in Diffusion

Analytical Theory of Spectral Bias in Diffusion
SpectralBias_Schematics
binxu_portrait

I have the honor of being among the inaugural NeuroAI Research Fellows at the newly established Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University, where I started in fall 2023.

I obtained my Ph.D. degree in Neuroscience in August 2023. I was fortunate to be advised by Dr. Carlos Ponce from Harvard's Neurobiology Department. I started my Ph.D. journey in the neuroscience program at Washington University in St. Louis. In fall 2021, I moved with the Ponce lab to Harvard Medical School. 

I'm interested in using optimization, generative models and geometry to understand the representation of visual information in the primate brain and deep neural networks. I hope computation and theory combined with experiments in close-loop will bring us closer to understand the brain. 

My bio sketch.

See also: 
Google Scholar / GitHub / Twitter / Personal Blog / YouTube 

Latest News

More

Recent Publications

Working Paper

Binxu Wang and John Vastola. “Diffusion Models Generate Images Like Painters: An Analytical Theory of Outline First, Details Later”
Binxu Wang and John Vastola. “Diffusion Models Generate Images Like Painters: An Analytical Theory of Outline First, Details Later”

Submitted

Binxu Wang. “An Analytical Theory of Power Law Spectral Bias in the Learning Dynamics of Diffusion Models”. ArXiv Preprint ArXiv:2503.03206
Binxu Wang. “An Analytical Theory of Power Law Spectral Bias in the Learning Dynamics of Diffusion Models”. ArXiv Preprint ArXiv:2503.03206
Binxu Wang and Carlos Ponce. “Neural Dynamics of Object Manifold Alignment in the Ventral Stream”. BioRxiv, Pp. 2024–06
Binxu Wang and Carlos Ponce. “Neural Dynamics of Object Manifold Alignment in the Ventral Stream”. BioRxiv, Pp. 2024–06

2024

Binxu Wang, Jiaqi Shang, and Haim Sompolinsky. 2024. “Do Diffusion Models Generalize on Abstract Rules for Reasoning?”. In 2024 Conference on Cognitive Computational Neuroscience
Binxu Wang, Jiaqi Shang, and Haim Sompolinsky. 2024. “Do Diffusion Models Generalize on Abstract Rules for Reasoning?”. In 2024 Conference on Cognitive Computational Neuroscience
Binxu Wang, Jiaqi Shang, and Haim Sompolinsky. 2024. “Diverse Capability and Scaling of Diffusion and Auto-Regressive Models When Learning Abstract Rules”. In The First Workshop on System-2 Reasoning at Scale, NeurIPS’24
Binxu Wang, Jiaqi Shang, and Haim Sompolinsky. 2024. “Diverse Capability and Scaling of Diffusion and Auto-Regressive Models When Learning Abstract Rules”. In The First Workshop on System-2 Reasoning at Scale, NeurIPS’24
Binxu Wang and John Vastola. 2024. “The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and Its Applications”. Transactions on Machine Learning Research
Binxu Wang and John Vastola. 2024. “The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and Its Applications”. Transactions on Machine Learning Research
More

Visitor Map