TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper
•
2512.16093
•
Published
•
72
Juanxi Tian
Juanxi
AI & ML interests
Efficient AI & Gen AI
Recent Activity
upvoted
a
paper
about 4 hours ago
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
upvoted
a
paper
1 day ago
Latent Implicit Visual Reasoning
Organizations
upvoted
a
paper
about 4 hours ago
upvoted
a
paper
1 day ago
upvoted
a
paper
4 days ago
liked
a
model
6 days ago
commented on
Backbone-Optimizer Coupling Bias: The Hidden Co-Design Principle
8 days ago
commented on
Backbone-Optimizer Coupling Bias: The Hidden Co-Design Principle
8 days ago
commented on
Backbone-Optimizer Coupling Bias: The Hidden Co-Design Principle
8 days ago
Hi, guys! We are exploring the intrinsic coupling relationship between neural network architectures and optimizers. Drawing on community discussions around nested learning and modular duality, we have further refined the concept of “Backbone-Optimizer Coupling Bias” (BOCB) as a universal framework. This framework enables the derivation of systematic co-design principles for unified learning systems. We welcome everyone to join the discussion and follow the ScalingOpt project. We would be most grateful if you could star🌟 the project!
https://github.com/tianshijing/ScalingOpt
upvoted
an
article
8 days ago
Article
Backbone-Optimizer Coupling Bias: The Hidden Co-Design Principle
•
3
published
an
article
8 days ago
Article
Backbone-Optimizer Coupling Bias: The Hidden Co-Design Principle
•
3
upvoted
2
papers
8 days ago
reacted to
their
post with ❤️👍🤗🔥
19 days ago
Post
2599
ScalingOpt is continuously evolving! We are steadily expanding the Community section with new content. For our Blog, we've launched by featuring work from Jianlin Su and are actively translating insightful posts from scientific communities into English to share on ScalingOpt (we'll keep curating excellent community blogs and providing English versions alongside the originals).
We operate under the Creative Commons Attribution-NonCommercial principle, sharing knowledge freely and openly. We welcome your ideas, suggestions, and feedback to help shape ScalingOpt's future.
If you find this initiative valuable, please consider following and starring the project to show your support. Thank you!
We operate under the Creative Commons Attribution-NonCommercial principle, sharing knowledge freely and openly. We welcome your ideas, suggestions, and feedback to help shape ScalingOpt's future.
If you find this initiative valuable, please consider following and starring the project to show your support. Thank you!
- 2 replies
posted
an
update
19 days ago
Post
2599
ScalingOpt is continuously evolving! We are steadily expanding the Community section with new content. For our Blog, we've launched by featuring work from Jianlin Su and are actively translating insightful posts from scientific communities into English to share on ScalingOpt (we'll keep curating excellent community blogs and providing English versions alongside the originals).
We operate under the Creative Commons Attribution-NonCommercial principle, sharing knowledge freely and openly. We welcome your ideas, suggestions, and feedback to help shape ScalingOpt's future.
If you find this initiative valuable, please consider following and starring the project to show your support. Thank you!
We operate under the Creative Commons Attribution-NonCommercial principle, sharing knowledge freely and openly. We welcome your ideas, suggestions, and feedback to help shape ScalingOpt's future.
If you find this initiative valuable, please consider following and starring the project to show your support. Thank you!
-
- 2 replies
liked
a
model
24 days ago
upvoted
2
papers
24 days ago
reacted to
their
post with 😎
24 days ago
Post
2010
ScalingOpt | Welcome to join and co-build the Optimization Community!
ScalingOpt is a professional platform focusing on optimization for large-scale deep learning, aiming to advocate for "Optimization at Scale," which means verifiable and scalable optimization algorithms.
This community platform is dedicated to gathering, discovering, comparing, and contributing various cutting-edge optimizers and optimization algorithms.
It's not just a simple Awesome List, it also includes:
Visualizations: Covers visualization scripts for the Rosenbrock Function and the Rastrigin Function for users to freely explore.
Benchmark: We recommend Algoperf as the primary source, along with other verifiable benchmarks and analysis articles, for users to reference the best optimizer.
Papers & Blogs Recommendation: The platform summarizes high-quality papers and blogs from recent years, and continuously adds the latest papers based on daily arXiv updates, currently totaling nearly a hundred articles.
Tutorials Sharing: The platform collects quality resources from the community and is independently producing a "From Classical to Modern Optimizers" Tutorial Series, which is expected to be updated by the end of the month.
We welcome everyone to use it and provide valuable feedback. We also welcome you to join us in co-building the community and focusing on the latest developments in optimization algorithms. The ScalingOpt community platform will be continuously updated.
We hope everyone can give ScalingOpt a star ⭐️. Thank you very much 🙏
Website: https://tianshijing.github.io/ScalingOpt
Github: https://github.com/tianshijing/ScalingOpt
ScalingOpt is a professional platform focusing on optimization for large-scale deep learning, aiming to advocate for "Optimization at Scale," which means verifiable and scalable optimization algorithms.
This community platform is dedicated to gathering, discovering, comparing, and contributing various cutting-edge optimizers and optimization algorithms.
It's not just a simple Awesome List, it also includes:
Visualizations: Covers visualization scripts for the Rosenbrock Function and the Rastrigin Function for users to freely explore.
Benchmark: We recommend Algoperf as the primary source, along with other verifiable benchmarks and analysis articles, for users to reference the best optimizer.
Papers & Blogs Recommendation: The platform summarizes high-quality papers and blogs from recent years, and continuously adds the latest papers based on daily arXiv updates, currently totaling nearly a hundred articles.
Tutorials Sharing: The platform collects quality resources from the community and is independently producing a "From Classical to Modern Optimizers" Tutorial Series, which is expected to be updated by the end of the month.
We welcome everyone to use it and provide valuable feedback. We also welcome you to join us in co-building the community and focusing on the latest developments in optimization algorithms. The ScalingOpt community platform will be continuously updated.
We hope everyone can give ScalingOpt a star ⭐️. Thank you very much 🙏
Website: https://tianshijing.github.io/ScalingOpt
Github: https://github.com/tianshijing/ScalingOpt
-
- 1 reply