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…
Cusuh retweeted
Poster will be presented at:
🗓️ Poster Session 2 on Friday, June 4
📍Poster #378, Exhibit Hall A
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,
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
Cusuh retweeted
Modulating Pretrained Diffusion Models for Multimodal Image Synthesis
abs: arxiv.org/abs/2302.12764
project page: mcm-diffusion.github.io/
Cusuh retweeted
CoGS: Controllable Generation and Search from
Sketch and Style
abs: arxiv.org/abs/2203.09554
Cusuh retweeted
Have some cool sketch-related research you'd like to show off? We just extended the paper submission deadline for the CVPR SketchDL workshop: sketchdl.github.io/
Cusuh retweeted
ML@GT Ph.D. student @cusuh_ is a world traveler focused on understanding uncertainty in machine learning. She's also been an incredible resource for new ML students. We may be celebrating her for #WomensHistoryMonth, but her future sure is bright 😎
bit.ly/3b9XiAU
Cusuh retweeted
I'm looking for PhD student summer interns at @argoai. Past interns have done some great research, like creating Argoverse and getting best paper awards cs.cmu.edu/~mengtial/proj/st… . Let me know if you're interested, or if you know someone who might be a good fit.
Cusuh retweeted
Lana Lazebnik’s short course on “Computer Vision: Looking Back to Look Forward” from when she was visiting Georgia Tech.
Amazing resource! Will give you a fresh perspective over only reading papers from the last few years or months or weeks :)
slazebni.cs.illinois.edu/spr…
Cusuh retweeted
This drone footage shows a long line of voters waiting to cast ballots in Atlanta on Tuesday. Georgia election officials, poll workers and voters have reported major trouble with voting in Atlanta and elsewhere.
Read the latest. nyti.ms/2An0SLp
Cusuh retweeted
Atlanta Humane Society let puppies roam the Georgia Aquarium. This might be the best thing you watch today..
Cusuh retweeted
Cusuh Ham is a first-year machine learning Ph.D. student who hopes to live abroad after graduation and ultimately become a professor. Get to know more about her in the March edition of Meet ML@GT!
📝: bit.ly/3b9XiAU
Cusuh retweeted
I can finally confirm we will be moving to online/distance instruction after spring break. We encourage all students who are able to stay away from campus until the end of the month, but we will accommodate those who can’t. Details to follow.
Cusuh retweeted
An exciting mini-course on #computervision starts next week! Led by @GTrobotics visiting faculty fellow Svetlana Lazebnik, the two-week course will cover topics like the connections to cognitive science and psychophysics and future trends.
🗓️: robotics.gatech.edu/faculty/…
