Grace Luo
I am a second year PhD student at BAIR advised by Professor Trevor Darrell. My research interests lie in multimodal vision and language models. Recently, I’ve been interested in analyzing the internal representations of generative models, including controlling their properties and distilling them for discriminative tasks.

Email / Google Scholar / Github
Research
(*) denotes equal contribution
Readout Guidance: Learning Control from Diffusion Features
Grace Luo, Trevor Darrell, Oliver Wang, Dan B Goldman, Aleksander Holynski
arXiv 2023
Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
Grace Luo, Lisa Dunlap, Dong Huk Park, Aleksander Holynski, Trevor Darrell
NeurIPS 2023
Shape-Guided Diffusion with Inside-Outside Attention
Dong Huk Park*, Grace Luo*, Clayton Toste, Samaneh Azadi, Xihui Liu, Maka Karalashvili, Anna Rohrbach, Trevor Darrell
WACV 2024
G^3: Geolocation via Guidebook Grounding
Grace Luo*, Giscard Biamby*, Trevor Darrell, Daniel Fried, Anna Rohrbach
Findings of EMNLP 2022
Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation
Giscard Biamby*, Grace Luo*, Trevor Darrell, Anna Rohrbach
NAACL 2022
NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media
Grace Luo, Trevor Darrell, Anna Rohrbach
EMNLP 2021 (Oral Presentation)
Investigative Reporting

Misc