🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

That's how you do it...

2025 is … a perfect square 45 x 45 = 2025.   a sum of cubes: 1³ + 2³ + 3³ + ... + 9³ = 2025 a perfect square when you add 1 to each digit: 3136 = 56² a perfect square when you increase the first digit by 1: 3025 = 55² Maybe the only number with all these properties

Join our robust Android malware detection competition at SaTML Conference - Deadline March 31, 2025 ramd-competition.github.io We're looking forward to test your robust detectors!

Michael Jordan gave a short, excellent, and provocative talk recently in Paris - here's a few key ideas - It's all just machine learning (ML) - the AI moniker is hype - The late Dave Rumelhart should've received a Nobel prize for his early ideas on making backprop work 1/n

I'm at AAAI #AAAI2025 - going to present our poster tomorrow :) attackbench.github.io w/ Antonio Cinà

Tomorrow at #AAAI2025 poster session. Come say hi! w/ Antonio Cinà

To see more details, have a look at this nice paper by Dmitry Kobak (Dmitry Kobak) et al. that works exclusively with the linear model. They have code for the experiments too 9/9

Thanks Matteo Tiezzi !

TL;DR Scaling laws are very very important (figs from the llama3 paper) Imagine you want to train a $100M model over several months. How do you pick model size, nb of tokens, learning rate and batch size? You cannot "grid search" at this scale. 1/4

Heading to Singapore for #ICLR, where I and Antonio Cinà will present our poster on sigma0, an L0-norm attack to compute sparse adversarial examples. Drop me a line if you want to catch up! 🔥🔥🔥

🚀 Exciting Announcement! 🚀 Get ready for the 18th ACM Workshop on Artificial Intelligence and Security (AISec 2025)! 📍Co-located: ACM CCS 2024 🗓️ Deadline: June 20th, 2025 🌐 Website: aisec.cc w/ Ruoxi Jia and Matthew Jagielski

Last week, I shared two #ICLR2025 papers that were recognized by their Award committee. Reflecting on the outcome, I thought it might be interesting to share that both papers were previously rejected by #NeurIPS2024. I found the dramatic difference in reviewer perception of

2. I was traveling when I got this, and replied on mobile that we could explore. They sent a calendly link and I booked a slot for 2 weeks ahead. 3. The meeting would be yesterday, and one hour before the meeting time I received an email with the link to join. It was on this

NeurIPS submission counter over 22K 😂😂😂🔥🔥🔥

NeurIPS has a record-breaking number of 25,000 submissions this year already. It's crazy but not entirely unexpected. Here is the scaling over the years, with a conservative projection. How do we even run a conference and review at this massive scale?

5. Random seed selection. A thing of beauty. 6/6

Can we compress neural networks while preserving robustness against adversarial attacks? Yes — that’s the goal of Adversarial Pruning (AP) methods. But here’s the catch 👇

📢 New Publication in Pattern Recognition – Volume 168 We’re pleased to share that our partner, @Università degli Studi di Cagliari (Italy), has published important new research on adversarial pruning methods in Pattern Recognition! Recent years have seen the rise of pruning