๐จIs complex query answering really complex?๐จ
unfortunately not!
the current benchmarks boil down to link prediction 98% of the time...
how to fix this???
๐๐๐
๐https://t.co/djQpupNqBK
with @c_gregucci@BoXiongs@loreloc_@PMinervini @ststaab
We are going to present our poster "Sum of Squares Circuits" at AAAI in Philadelphia today
Hall E 12:30pm-14:00pm poster #840
We trace expressiveness connections of different types of additive and subtractive deep mixture models and tensor networks
๐ https://t.co/GpELxOl2OU
Finally, LOgically COnsistent (LoCo) LLaMas can outperform solver-based baselines and SFT! I thank @tetraduzione and @looselycorrect for the guidance in realizing this project, get in touch or come to chat in Singapore!
https://t.co/YXGg38mIon
Many people are in the middle of the @CVPR deadline. So I'm sharing my guide to writing a CVPR paper (or any paper). My students have had this for years but I haven't shared it publicly before. I hope you find it useful and write a great paper. #CVPR2025 https://t.co/RAvnQFnuLQ
๐จIs complex query answering really complex?๐จ
unfortunately not!
the current benchmarks boil down to link prediction 98% of the time...
how to fix this???
๐๐๐
๐https://t.co/djQpupNqBK
with @c_gregucci@BoXiongs@loreloc_@PMinervini @ststaab
We learn more expressive mixture models that can subtract probability density by squaring them
๐จWe show squaring can reduce expressiveness
To tackle this we build sum of squares circuits๐
๐We explain why complex parameters help, and show an expressiveness hierarchy around๐
An Italian university is offering a 1-year research contract for 19,400 euros, post-doc preferred. That's actually a standard remuneration for this kind of contracts in Italy. No wonder you find so many Italian researchers outside of Italy.