Yu Lei
@yulei2002.bsky.social
Learn to learn representations and learn to search within and beyond.
Embodied Intelligence, physics, cognitive science. Undergrad @SJTU, Ex-intern@UCSD
https://theknight-z.github.io/
Embodied Intelligence, physics, cognitive science. Undergrad @SJTU, Ex-intern@UCSD
https://theknight-z.github.io/
Very interesting! I do think about something very similar a while ago. I have to take every thought slow afterwards…
"Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms".
interesting approach using 2nd order info to avoid the exploding/vanishing gradients that come from non differentiable relaxations..
www.youtube.com/watch?v=7aFP...
interesting approach using 2nd order info to avoid the exploding/vanishing gradients that come from non differentiable relaxations..
www.youtube.com/watch?v=7aFP...
Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms - NeurIPS2024
YouTube video by Felix Petersen
www.youtube.com
January 6, 2025 at 11:47 AM
Very interesting! I do think about something very similar a while ago. I have to take every thought slow afterwards…
Reposted by Yu Lei
Personal vision tasks–like detecting *your mug*--are hard; they’re data scarce and fine-grained.
In our new paper, we show you can adapt general-purpose vision models to these tasks from just three photos!
📝: arxiv.org/abs/2412.16156
💻: github.com/ssundaram21/...
(1/n)
In our new paper, we show you can adapt general-purpose vision models to these tasks from just three photos!
📝: arxiv.org/abs/2412.16156
💻: github.com/ssundaram21/...
(1/n)
December 23, 2024 at 5:26 PM
Personal vision tasks–like detecting *your mug*--are hard; they’re data scarce and fine-grained.
In our new paper, we show you can adapt general-purpose vision models to these tasks from just three photos!
📝: arxiv.org/abs/2412.16156
💻: github.com/ssundaram21/...
(1/n)
In our new paper, we show you can adapt general-purpose vision models to these tasks from just three photos!
📝: arxiv.org/abs/2412.16156
💻: github.com/ssundaram21/...
(1/n)
Reposted by Yu Lei
How to design your presentation?
Presentation is an essential skill for academics.
After attending so many meetings, prelims, thesis defenses, research talks, and lectures, I’ve realized that I may have been approaching it all wrong ...
Some (bitter) lessons I learned. 👇
Presentation is an essential skill for academics.
After attending so many meetings, prelims, thesis defenses, research talks, and lectures, I’ve realized that I may have been approaching it all wrong ...
Some (bitter) lessons I learned. 👇
December 7, 2024 at 1:11 AM
How to design your presentation?
Presentation is an essential skill for academics.
After attending so many meetings, prelims, thesis defenses, research talks, and lectures, I’ve realized that I may have been approaching it all wrong ...
Some (bitter) lessons I learned. 👇
Presentation is an essential skill for academics.
After attending so many meetings, prelims, thesis defenses, research talks, and lectures, I’ve realized that I may have been approaching it all wrong ...
Some (bitter) lessons I learned. 👇
Reposted by Yu Lei
Introducing Generative Omnimatte:
A method for decomposing a video into complete layers, including objects and their associated effects (e.g., shadows, reflections).
It enables a wide range of cool applications, such as video stylization, compositions, moment retiming, and object removal.
A method for decomposing a video into complete layers, including objects and their associated effects (e.g., shadows, reflections).
It enables a wide range of cool applications, such as video stylization, compositions, moment retiming, and object removal.
November 26, 2024 at 3:55 PM
Introducing Generative Omnimatte:
A method for decomposing a video into complete layers, including objects and their associated effects (e.g., shadows, reflections).
It enables a wide range of cool applications, such as video stylization, compositions, moment retiming, and object removal.
A method for decomposing a video into complete layers, including objects and their associated effects (e.g., shadows, reflections).
It enables a wide range of cool applications, such as video stylization, compositions, moment retiming, and object removal.