Check our recent work on diffusion model acceleration from the perspective of UNet architecture! Our approach can easily be combined with various diffusion model-based tasks (text-to-image, personalized generation, video generation, etc.) to achieve training-free acceleration.
RESEARCH
-
SAS Innovate 2026: AI and Analytics Conference in Las Vegas
By
–
If you are a business leader, technical user, SAS partner, or aspire to become one—SAS Innovate is the place for you! Make your travel plans now to meet us in Las Vegas to dig deep into AI & analytics. Registration is open http://
2.sas.com/6019Rui5z #SASInnovate #MachineLearning -
CFOs Prioritize ESG Metrics Measurement According New Research
By
–
Thanks Hanh @BrownH1967 really appreciate your feedback and just wanted to share this too – some new #research by @Protiviti @ProtivitiUK reflecting how CFOs are now ranking ESG Metrics and Measurement as their leading priority #ESG #CFO
-
GPT Model Hallucinations and Token-Level Confusion Explained
By
–
It’s a hallucination, likely because at the token level, gpt-3.5-turbo and gpt-4.5-turbo would be represented similarly and the model already knows it has gpt-4 access in some cases. Plus we called the new model gpt-4 turbo which has added to the confusion.
-
Prioritizing Current AI Solutions Over Long-term Speculation
By
–
I’m with @ylecun and @AndrewYNg on this. I feel it is more responsible to devote greater effort to solving today’s problems (e.g. climate, health, energy, poverty, safety, communication, bias and discrimination, education) than to cultist AI long term speculation.
-
Opposing AI R&D Regulation: Access and Safety Debate
By
–
Fight people who want to regulate AI R&D by claiming that it's too dangerous for everyone but them to have access to it.
-
Predicting Uncertainty in Discrete Token Probability Distributions
By
–
A prediction problem in a discrete and finite domain is easy because we know how to represent uncertainty in the prediction.
If there are 30,000 possible tokens, we output a 30k-dimensional vector of values between 0 and 1 that sum to 1 (thank you softmax).
We can't output a -
Engineering Over Theory: Building Reliable Systems Without Perfect Proof
By
–
There is no math that proves that there exist a way to make safe and reliable turbojets.
Yet we do make turbojets that are incredibly safe and reliable.
It's called engineering.
You should try it. -
PyTorch Genesis: How Code Sharing Accelerates AI Progress
By
–
The whole genesis, history, and inspirations for PyTorch, in which @soumithchintala demonstrates that the free exchange of ideas and code makes software progress faster. Unlike with technical papers, there is no default citation mechanism for code. But citing sources of
-
History of Deep Learning Software: A Mini-Book Project
By
–
Tianqi, you and I should probably compile a "History of Deep Learning Software" for fun 🙂
it'll be a mini-book, if only for us to keep in our library.