Andreas Grivas

At #ACL2025NLP and on the job market (NLP + AI Safety) 💼

It's great to see growing interest in safety/alignment, but we often miss the social context.

Come to our @woahworkshop.bsky.social Friday to dive deeper into safe safety research!

A quiet token from the biggest @aclmeeting.bsky.social ⬇️

Next week I will be in 🌴 Rio 🌴 attending (and helping organizing) UAI 2025 and TPM 2025.

If you are also attending and want to talk science (e.g. probabilistic generative models, causality, multi-objective machine learning, etc) or just hang out, not everything is work, feel free to reach me out!

by applying a QR decomposition, any matrix can be written as a QR code multiplied by an upper triangular matrix

Postdoc in Natural Language Processing

📢I am hiring a Postdoc to work on post-training methods for low-resource languages. Apply by August 15 employment.ku.dk/faculty/?sho....
Let's talk at #ACL2025NLP in Vienna if you want to know more about the position and life in Denmark.

"in 2025 we will have flying cars" 😂😂😂

this profile is impersonating me on X and scamming people. And it got verified...! (*)

golden rule: it is not me on social media if you don't see a ☠️.

(*) please help me report this profile, if you are still on X

How Bees, Beer Cans and Data Solve the Same Packing Problem (Gift Article) Trying to fit it all in? There’s a trick to it, even in 24 dimensions.

Dear #mathsky, if you repost this, it will let people see the article for free. Thanks!

www.nytimes.com/interactive/...

☀️ I will be in Edinburgh this summer (Jun-Aug) at @edinburgh-uni.bsky.social, visiting the group of Antonio Vergari (@nolovedeeplearning.bsky.social) to work on #neurosymbolic #AI and #probabilistic #ML

If you are around and want to chat about these topics, let's meet for coffee!

🚀 By *learning* to compress the KV cache in Transformer LLMs, we can generate more tokens for the same compute budget.

This unlocks *inference-time hyper-scaling*

For the same runtime or memory load, we can boost LLM accuracy by pushing reasoning even further!

I will be in London tomorrow, at @imperialcollegeldn.bsky.social and @imperial-ix.bsky.social , hosted by @e-giunchiglia.bsky.social to talk about #neurosymbolic #AI #reliability #probabilistic #reasoning

Ping me if you want to chat ∧∨ grab coffee!

⏳⏳⏳ One more day to the NeSy abstract submission! Don't miss it!

Full timeline at: 2025.nesyconf.org/call-for-pap...

🚨🚨 Last I-X Seminar of the Year!

Don’t miss Dr Antonio Vergari (@nolovedeeplearning.bsky.social) on Logically-Consistent Deep Learning — a crucial topic at the intersection of logic & neural networks! 🌟

We have extended the submission deadline for TPM to the 2nd of June!

Remember that **we accept recently accepted works that fit in topic,** so if you want to travel to Rio and share your work it's a no brainer imho 🌴🌴

🗓️ Deadline extended: 💥2nd June 2025!💥

We are looking forward to your works on:

🔌 #circuits and #tensor #networks 🕸️
⏳ normalizing #flows 💨
⚖️ scaling #NeSy #AI 🦕
🚅 fast and #reliable inference 🔍
...& more!

please share 🙏

Rio is looking forward to seeing all your works on #fast #reliable #tractable #models #circuits #tensor #networks #flows!

please share!

I-X Seminar: Logically-Consistent Deep Learning with Dr Antonio Vergari In this talk, Dr Antonio Vergari (University of Edinburgh) will speak about logically-consistent deep learning.

Join us for our next I-X seminar with Dr Antonio Vergari @nolovedeeplearning.bsky.social titled "Logically-Consistent Deep Learning".

🕓 13:00 - 14:00 (GMT)
📅 Thursday, 5 June
📍 Hybrid (White City Campus / Microsoft Teams)

Register via link below.
www.imperial.ac.uk/events/19426...

We propose Neurosymbolic Diffusion Models! We find diffusion is especially compelling for neurosymbolic approaches, combining powerful multimodal understanding with symbolic reasoning 🚀

Read more 👇

docstring of class Altman?

This year I am co-organizing the 8th iteration of the Tractable Probabilistic Modeling #TPM workshop at #UAI2025 🌴 Rio de Janeiro edition 🌴

🌐 lnkd.in/dDK8T5Au
⏰ Submission deadline: May 23th AoE
🌴 Date: July 15th

🧵👇

PhD Timeline xkcd.com/3081

Sparse attention is one of the most promising strategies to unlock long-context processing and long-generation reasoning in LLMs.

We performed the most comprehensive study on training-free sparse attention to date.

Here is what we found:

great to have David Watson (dswatson.github.io) visiting us today and talking about #trustworthy #AI #ML for tabular data with #trees and #circuits

with connections to #generative modeling, #causality and #fast inference!

Great quote (and great talk) by @nolovedeeplearning.bsky.social at #GeMMS2025

Have work on the actionable impact of interpretability findings? Consider submitting to our Actionable Interpretability workshop at ICML! See below for more info.

Website: actionable-interpretability.github.io
Deadline: May 9

🚀 Excited to welcome Dr. @edoardo-ponti.bsky.social to #ADSAI2025! Lecturer in NLP @edinburghuni.bsky.social , Affiliated Lecturer @cambridgeuni.bsky.social & Visiting Prof NVIDIA.
🎟️ Tickets for Advances in Data Science & AI Conference 2025 are live!
🔗Secure your spot: tinyurl.com/yurknk7y
#AI

Image illustrating that ALM can enable Ensembling, Transfer to Bytes, and general Cross-Tokenizer Distillation.

We created Approximate Likelihood Matching, a principled (and very effective) method for *cross-tokenizer distillation*!

With ALM, you can create ensembles of models from different families, convert existing subword-level models to byte-level and a bunch more🧵

I found some time to upload causalflows to PyPI :)

If you want to use the library now it is as simple as running
> pip install causalflows

or, if you are riding the uv wave,
> uv add causalflows

Enjoy!

Live from the CoLoRAI workshop at AAAI
(april-tools.github.io/colorai/)

Nadav Cohen is now giving his talk on "What Makes Data Suitable for Deep Learning?"

Tools from quantum physics are shown to be useful in building more expressive deep learning models by changing the data distribution.

YouTube video by april lab [CoLoRAI] FinLoRA: Finetuning Quantized Financial Large Language Models Using Low-Rank Adaptation

we're almost ready for the @realaaai.bsky.social #AAAI25 Workshop on Connecting Low-rank Representations in #AI (#CoLoRAI) tomorrow!

we also have video presentations for some of the accepted papers you can already check (👉 april-tools.github.io/colorai/acce...)!

📽️ www.youtube.com/watch?v=JlVd...

Check out Lorenzo's cool work on 🆘 circuits!