Learned so much from participating in the The ML Reproducibility Challenge and feel so lucky to have done it with this dream team 😊

Can’t wait to talk about the method behind these vibrant diagrams tomorrow! 🌈

And the winners are in! The The Brown Institute is proud to announce the winners of its 2022-2023 Magic Grant competition! Some teams are proposing tools to stretch our creativity, and others are developing new technologies for reporting on important social and political situations.

And to show new work on inferring shade trees (discrete structure and continuous parameters) from images. w/ Chen Geng, Hong-Xing Yu, sharon z. and Jiajun Wu chen-geng.com/inv-shade-tree…

Maybe you've heard of #ControlNet for controlling text-to-image diffusion models. At #ICCV2023, lllyasviel will explain how it works and present more of the behind the scenes details. arXiv: arxiv.org/abs/2302.05543 A111 webui plugin: github.com/Mikubill/sd-we…

How to understand visual appearances in an easily interpretable way? Check out our #ICCV2023 work on tree-structured shading decomposition from images! Easy understanding and editing for appearances even for novice users. Project Page: chen-geng.com/inv-shade-trees

Excited to be sharing this at SIGGRAPH Asia at the end of the year! Check out more at sxzhang25.github.io/publications/m…

I will be presenting this work today at 2:20pm at #UIST2023 in the Gold Room. Hope to see many of you there! If you want a quick break in between talks, check out some result videos of this work at hci.stanford.edu/research/lyric…

Happening tomorrow! And if you have any questions you can find me at the discussion session afterwards at 11:30am in Room C4.1 🗣️

We introduce MoVer, a Motion Verification DSL that automatically checks if AI-generated motion graphics animations match your text prompts! We make it easy for designers to specify and verify complex animations with LLM-powered iterative refinement. Catch our #SIGGRAPH2025 talk: