roberto corizzo

computer science researcher | @AmericanU

[roberto corizzo @robcorizzo]

https://t.co/XO00mJx4jd

[roberto corizzo @robcorizzo]

Only a few days left to submit to the Open World Anomaly Detection Workshop @ IEEE ICDM 2025!
🗓️ Deadline: Aug 29
📍 Workshop: Nov 12 | Washington, DC (hybrid)

🔗 Link to the workshop's website in the comment
#ICDM2025 #AnomalyDetection #ML #AI #CallForPapers

[roberto corizzo @robcorizzo]

📢 Just one month left to submit!

Our Open World Anomaly Detection (OWAD) workshop is coming to #ICDM2025 this November in DC.

Topics include anomaly detection, continual learning, LLMs, and more.

📅 Submit by Aug 29
🔗 CfP: https://t.co/ULbOp3hfqH

#MachineLearning #AI

[Pasquale Minervini @PMinervini]

Still ~10 days to apply! Fully funded until 2029, and includes access to our HPC infra and some amazing teams! @EdinburghNLP

[antonio vergari ⚔️ @tetraduzione]

great talk by @EmtiyazKhan at @CoLLAs_Conf and this slide in particular on the future of #continual learning

"order matters"

we cannot agree more, and in fact in a poster with @robcorizzo we investigate curriculum learning over challenging tasks

👉https://t.co/xpdEuQwuhq

👇👇

[antonio vergari ⚔️ @tetraduzione]

we evaluate #continual learning models on "baby" benchmarks, where it is easy to show no catastrophic forgetting!

we propose a new simple benchmark that glues simple but still challenging tasks in a curriculum: from MNIST to Imagenet and back!

📜https://t.co/xpdEuQwuhq

[antonio vergari ⚔️ @tetraduzione]

fun work done with Kamil, Dominik, Marcin, Nathalie, and @robcorizzo, accepted at @MLJ_Social and to be presented also at @CoLLAs_Conf in a month!

📜https://t.co/xpdEuQwuhq
🖥️https://t.co/xG4TVRzQWl

[Machine Learning Journal (@[email protected]) @MLJ_Social]

And a second #DS 2022 special issue paper, this one #OA: "Distributed and explainable GHSOM for anomaly detection in sensor networks" by Paolo Mignone, Roberto Corizzo & Michelangelo Ceci (https://t.co/2JbAQvDnBy)

[roberto corizzo @robcorizzo]

@tetraduzione @v_lomonaco @AvalancheLib @acarta7 well deserved! 🚀

[antonio vergari ⚔️ @tetraduzione]

I have fully-funded PhD positions (3.5 yrs) for troublemakers in #ML #AI who want to design the next gen of #probabilistic #models and #programs that are provably #reliable and #efficient

Join @InfAtEd @EdinburghUni

Email me! ✉️
Please share! 🔁

Apply 👉https://t.co/ReIiIshYy7

[antonio vergari ⚔️ @tetraduzione]

It's hard to assess #Continual #Learning models and disentangle #hype from #progress, as the eval landscape is fragmented.

Even when learning from #MNIST to tiny #ImageNet (and back) #sota models tend to #catastrophic #forget a lot!

cc @ContinualAI

👉https://t.co/HWHPu6PIIo