conceptofmind
@conceptofmind.bsky.social
Awesome to see @nvidia @NVIDIAAI using our research for their open-source long-context models.
April 13, 2025 at 6:19 PM
Awesome to see @nvidia @NVIDIAAI using our research for their open-source long-context models.
Talking about DeepSeek and their connection to Tsinghua. Tsinghua and CMU have an older (2017) but still great series on high-performance parallel computing. The playlist can be found here: https://buff.ly/4gktKSd
January 26, 2025 at 7:49 PM
Talking about DeepSeek and their connection to Tsinghua. Tsinghua and CMU have an older (2017) but still great series on high-performance parallel computing. The playlist can be found here: https://buff.ly/4gktKSd
I have an extremely easy evaluation that currently all top models achieve a 0% on. This is the easiest set of evaluations in our entire suite. AGI would be able to solve the hardest problems effortlessly. Once o3 becomes available in the API, I will put out a public baseline.
December 21, 2024 at 7:31 PM
I have an extremely easy evaluation that currently all top models achieve a 0% on. This is the easiest set of evaluations in our entire suite. AGI would be able to solve the hardest problems effortlessly. Once o3 becomes available in the API, I will put out a public baseline.
Does anyone have any ideas why T5 or CLIP is being used for text encoding in diffusion training instead of a much stronger encoder or embedding model?
December 15, 2024 at 8:19 PM
Does anyone have any ideas why T5 or CLIP is being used for text encoding in diffusion training instead of a much stronger encoder or embedding model?
There is absolutely no shortage of pre-training data.
December 15, 2024 at 12:24 AM
There is absolutely no shortage of pre-training data.
AWS ParallelCluster is honestly such an incredibly useful tool for large-scale distributed training:
GitHub - aws/aws-parallelcluster: AWS ParallelCluster is an AWS supported Open Source cluster management tool to deploy and manage HPC clusters in the AWS cloud.
AWS ParallelCluster is an AWS supported Open Source cluster management tool to deploy and manage HPC clusters in the AWS cloud. - aws/aws-parallelcluster
buff.ly
December 14, 2024 at 4:25 AM
AWS ParallelCluster is honestly such an incredibly useful tool for large-scale distributed training:
Be sure to check out this awesome work by @stefanabaumann.bsky.social, @rmsnorm.bsky.social, and @koljabauer.bsky.social.
🤔 Why do we extract diffusion features from noisy images? Isn’t that destroying information?
Yes, it is - but we found a way to do better. 🚀
Here’s how we unlock better features, no noise, no hassle.
📝 Project Page: compvis.github.io/cleandift
💻 Code: github.com/CompVis/clea...
🧵👇
Yes, it is - but we found a way to do better. 🚀
Here’s how we unlock better features, no noise, no hassle.
📝 Project Page: compvis.github.io/cleandift
💻 Code: github.com/CompVis/clea...
🧵👇
December 5, 2024 at 5:26 PM
Be sure to check out this awesome work by @stefanabaumann.bsky.social, @rmsnorm.bsky.social, and @koljabauer.bsky.social.