Andreas Grivas
banner
andreasgrv.bsky.social
Andreas Grivas
@andreasgrv.bsky.social
Postdoc in ML/NLP at the University of Edinburgh.

Interested in Bottlenecks in Neural Networks; Unargmaxable Outputs.

https://grv.unargmaxable.ai/
Just submitted an application, picked up a banana and was greeted by:
October 20, 2025 at 2:51 PM
Then, 5 minutes before the ICLR deadline, it surprised me with motivation in Greek (Ela! means Come on!).
September 25, 2025 at 12:57 PM
The best feature of overleaf is the subliminal messages it produces by choosing how to order the author tiles.

It was a long day, and Overleaf was like, maybe you should go to the pub!
September 25, 2025 at 12:57 PM
February 26, 2025 at 10:02 PM
Milestone: First Probabilistic Circuits meme.
January 29, 2025 at 1:38 PM
📕 ⬇️ My thesis on 🚫unargmaxable outputs is online! Check it out if you want to learn more about how output layers constrain what neural networks can and cannot predict 👉 era.ed.ac.uk/handle/1842/...
January 10, 2025 at 5:14 PM
Have you tried solving [MASK] using GenAI?
January 7, 2025 at 12:18 AM
In the animation, the white plane is the columnspace of a linear map from f: R^2 -> R^4. The plane moves as we change the columnspace. The planes on the right discretise space into regions which correspond to rankings of 4 elements. Intersected regions correspond to realisable rankings.
December 18, 2024 at 4:16 PM
Cover's result is beautiful and still applies widely to today's #ML models: e.g. LLMs cannot rank their vocabulary in all possible ways 📊

Putting aside enumeration, a visual way of thinking about which rankings are realisable is:
December 18, 2024 at 4:16 PM
Oh cool, fontawesome has an argmax emoji 😁
December 3, 2024 at 4:04 PM
Need a prompt version of: imgs.xkcd.com/comics/explo...
November 28, 2024 at 9:43 PM
Post a picture you took (no description) to bring some zen to the timeline
November 17, 2024 at 9:53 PM