Mike Spaner
mspan.bsky.social
Mike Spaner
@mspan.bsky.social
Engineering at the intersection of industrial AI, autonomous systems, optimization, and old school data science.
Reposted by Mike Spaner
FOLKS! Go follow @python.org!!
November 26, 2024 at 5:14 PM
Reposted by Mike Spaner
Hello @bsky.app from the #JuliaLang community!

We're excited to start posting here on Bluesky in addition to our other social media, all of which can be found here: julialang.org

We'll keep you updated on our fantastic community, our conferences, #JuliaLang updates, and more on this profile!
November 25, 2024 at 4:26 PM
Looks great! Just about every real world industrial problems are “too complex”… I am looking forward learning more about Amortized Bayesian Inference/ BayesFlow!
The beta version of BayesFlow 2.0 is becoming more powerful and stable by the day. If you are curious about Amortized Bayesian Inference, give BayesFlow a try!
github.com/bayesflow-or...
GitHub - bayesflow-org/bayesflow at dev
A Python library for amortized Bayesian workflows using generative neural networks. - GitHub - bayesflow-org/bayesflow at dev
github.com
November 22, 2024 at 9:53 AM
Reposted by Mike Spaner
Lets fill out the multi-agent systems starter pack. RL, learning in games, certain kinds of HCI, collective intelligence, etc.
go.bsky.app/9gsefkW
November 21, 2024 at 3:01 PM
Reposted by Mike Spaner
Now I have like a gazillion new Bluesky followers, posting a link again to a blog post about my #EMNLP2024 and EMNLP 2022 papers. It’s a fun 10 minute read about our ideas on interpretable neural architectures.

❤️ to my fantastic collaborators

www.marekrei.com/blog/creatin...
Creating Interpretable Models with Atomic Inference - Marek Rei
This is a guest post from Joe Stacey about our quest to create interpretable Natural Language Inference (NLI) models. In this post he will share…
www.marekrei.com
November 20, 2024 at 11:35 AM
SQL! SQL. JUST USE SQL
November 20, 2024 at 2:51 AM
❤️ complex emergent systems
A really intriguing set of findings of AI researchers that needs more exploration, replication, and expansion: AI agents given personalities and backgrounds, and placed into a virtual formal organization (with CEOs, VPs, etc.) outperform normal AI in doing complex tasks.
November 19, 2024 at 4:06 PM
Data curation matters
🧵We’ve spent the last few months at @datologyai.bsky.social
building a state-of-the-art data curation pipeline and I’m SO excited to share our first results: we curated image-text pretraining data and massively improved CLIP model quality, training speed, and inference efficiency 🔥🔥🔥
November 19, 2024 at 1:25 PM