Bingliang Zhang (@bingliangzhang) 's Twitter Profile
Bingliang Zhang

@bingliangzhang

Ph.D. student at @Caltech working with Katie Bouman, Yisong Yue, and Yang Song

ID: 1497656573061120000

linkhttps://zhangbingliang2019.github.io/ calendar_today26-02-2022 19:37:35

2 Tweet

8 Followers

18 Following

Yisong Yue (@yisongyue) 's Twitter Profile Photo

We present InverseBench, a framework for benchmarking plug-and-play diffusion approaches for inverse problems in physical sciences. (#ICLR2025 Spotlight) PnP diffusion approaches are attractive for scientific inverse problems because they offer flexibility in incorporating

We present InverseBench, a framework for benchmarking plug-and-play diffusion approaches for inverse problems in physical sciences.  (#ICLR2025 Spotlight)

PnP diffusion approaches are attractive for scientific inverse problems because they offer flexibility in incorporating
Yisong Yue (@yisongyue) 's Twitter Profile Photo

TLDR: if you can train video diffusion priors, then solving video inverse problems can be done much simpler and more accurately than heavily engineered approaches based on image diffusion priors. Examples below for black hole video reconstruction and dynamic MRI.

Bingliang Zhang (@bingliangzhang) 's Twitter Profile Photo

If you're attending CVPR 2025, please join our talk and poster session on Sunday, June 15 (the final day)! 🗣️ Oral Session 5A: Generative AI 📍 Karl Dean Grand Ballroom | 🕘 9:00 AM 📌 Poster Session #200 📍 Exhibit Hall D | 🕥 10:30 AM – 12:30 PM