Bowen Song

I am a Ph.D. candidate in Electrical and Computer Engineering at University of Michigan, Ann Arbor. Previously I worked at Microsoft as an applied scientist.

I obtained my Master’s degree in Computational and Mathematical Engineering from Stanford University, advised by Prof. Lei Xing; Bachelor’s degree in Mathematics and Statistics from University of Illinois, Urbana Champaign.

My research interests lie in applications and theories of generative models and diffusion models. Recently, my projects focus on reliable, controllable and efficient training and inference on high-dimensional data with generative models. My previous projects are also related to test-time adaptation and implicit neural representation learnings.

News

May 2025 — Joined Meta FAIR (now MSL), working on 3D reconstruction models.

Selected Publications

Chart	Paper
	Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation Bowen Song, Zecheng Zhang, Zhaoxu Luo, Jason Hu, Wei Yuan, Jing Jia, Zhengxu Tang, Liyue Shen, Guanyang Wang NeurIPS 2025
	DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction Bowen Song*, Jason Hu*, Zhaoxu Luo, Jeffrey A Fessler, Liyue Shen NeurIPS 2024
	Solving inverse problems with latent diffusion models via hard data consistency Bowen Song*, Soo Min Kwon*, Zecheng Zhang, Xinyu Hu, Qing Qu, Liyue Shen ICLR 2024 (Spotlight)
	CoSIGN: Few-Step Guidance of ConSIstency Model to Solve General INverse Problems Jiankun Zhao*, Bowen Song*, Liyue Shen ECCV 2024
	PINER: Prior-Informed Implicit Neural Representation Learning for Test-Time Adaptation in Sparse-View CT Reconstruction Bowen Song, Liyue Shen*, Lei Xing* WACV 2023
	SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models Bowen Song*, Zhaoxu Luo*, Liyue Shen ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling
	Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing Xinyu Hu, Pengfei Tang, Simiao Zuo, Zihan Wang, Bowen Song, Qiang Lou, Jian Jiao, Denis X Charles ICLR 2024

Blog

In this blog, we will explore interesting stuff here. Topics including: thoughts on technology development and societal impacts, reflection on methodological approach to problem solving, training for physical fitness, recovering from injury, classical music analysis and so on.

Posts

• Aug 15, 2023

  A bug when installing new environment in Conda

• Jul 24, 2023

  Road to Recovery - ACL完全断裂半月板复杂裂1.5年笔记

• Jul 15, 2023

  Domain Adaptation with Latent Diffusion Models for Segmentation and Classification

subscribe via RSS