Research Scientist @ Adobe | ML PhD from Georgia Tech | previously Google Research, MPI
Joined April 2010
- Tweets141
- Following205
- Followers874
- Likes901
Cusuh retweeted
Students sometimes ask me if it still makes sense, in this accelerating age, to pursue a PhD in AI.
Perhaps counterintuitively, I think it's a great time to do so.
I wrote up some thoughts on this here: web.mit.edu/phillipi/www/wri…
Poster session starting now!!
Poster will be presented at:
🗓️ Poster Session 2 on Friday, June 4
📍Poster #378, Exhibit Hall A
Cusuh retweeted
Poster will be presented at:
🗓️ Poster Session 2 on Friday, June 4
📍Poster #378, Exhibit Hall A
Exciting work on fine-grained visual similarity, led by my intern, Julia.
Come by the afternoon poster session on Friday to say hi and learn more! #CVPR2026
Excited to share ID-Sim, our identity-focused similarity metric, presenting at #CVPR2026 this week in Denver! 🎉
Humans are remarkably good at distinguishing highly similar objects across different contexts.
We asked: can we train a metric that does the same?
MotionCanvas presents a method for scene-aware, decoupled object and camera motion control for image-to-video generation.
Come by the #SIGGRAPH2025 Video Generation session tomorrow @ 10:45am in West Building, Rooms 118-120 to learn more!
motion-canvas25.github.io/
Great work from our intern, Jinbo, in collaboration with Long, Gabriel, Aniruddha, Chi-Wing, Tien-Tsin, and Feng
@CUHKofficial, @AdobeResearch, @MonashUni
Cusuh retweeted
I've had so much fun experimenting with our latest @Adobe Firefly Video model - coming from a background in film, I've loved exploring the world of generative cinematography. A few of my favorite shots:
Cusuh retweeted
We’re excited to share progress on the all-new Firefly Video Model with Text to Video & Image to Video capabilities across @creativecloud, @AdobeExpCloud & @AdobeExpress workflows - all designed to be commercially safe & available in beta later this year. adobe.ly/4eebxFi
Cusuh retweeted
After a nearly 20 month journey we are finally going public with our work on video generative models at Adobe! This work started in Adobe Research and then became a collaboration with the Adobe Firefly team who brought it over the finish line. Super proud of everyone involved,
I'll be presenting our work tomorrow (6/19) 5-630pm in Arch 4A-E (poster #329)!
#CVPR2024
In our latest work, we introduce personalized residuals for efficient personalization of T2I diffusion models and localized attention-guided sampling that dynamically blends the learned concept into new contexts. #CVPR2024
cusuh.github.io/personalized…
In our latest work, we introduce personalized residuals for efficient personalization of T2I diffusion models and localized attention-guided sampling that dynamically blends the learned concept into new contexts. #CVPR2024
cusuh.github.io/personalized…
Cusuh retweeted
Personalized Residuals for Concept-Driven Text-to-Image Generation
We present personalized residuals and localized attention-guided sampling for efficient concept-driven generation using text-to-image diffusion models. Our method first represents concepts by freezing the
PS I'm looking to hire a research intern for summer 2024 to work on image/video generation or multimodal learning. If you're interested, please apply online and send me an email :) bit.ly/46Usi4J
MCM will part of the "Diffusion for Geometry" session tomorrow (Wed 8/9) at 9am in room 502 AB. Hope to see you there! :)
#SIGGRAPH2023
I'll be presenting our work on multimodal conditioning modules (MCM) at #SIGGRAPH2023 this week! MCM is a small network that enables multimodal image synthesis using pretrained diffusion models without any direct updates to the diffusion model parameters.
mcm-diffusion.github.io
I'll be presenting our work on multimodal conditioning modules (MCM) at #SIGGRAPH2023 this week! MCM is a small network that enables multimodal image synthesis using pretrained diffusion models without any direct updates to the diffusion model parameters.
mcm-diffusion.github.io
Thank you to my collaborators (@jhhays, Cynthia, Krishna, Zhifei, and Tobias)!
@mlatgt @AdobeResearch