🔥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

Looking to recruit "one" PhD student (in either ECE + CS @ UIUC) with STRONG interests in ML+Systems+Security, or demystifying foundation models. Deadline: Dec 15. Ping with any questions. Please RT and help amplify?

We're hiring new PhD students! Yves-A. de Montjoye is an amazing supervisor to work with, and the whole team is really great!

Join us for Charles River Privacy Day on Nov 22nd! Featuring talks by Gautam Kamath, Jalaj Upadhyay, Virginia Smith, and Priyanka Nanayakkara Registration is free! bostondataprivacy.github.io/privacy-day.ht…

We’re excited to announce that the AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-25) is back! 🔗 ppai-workshop.github.io Please share widely! 🙏 Hosted at the 39th AAAI Conference on Artificial Intelligence (AAAI-25), this workshop will bring together AI

ELLIS PhD position open in my group Finnish Center for AI 🦣 @[email protected] and upcoming ELLIS Institute Finland in differentially private machine learning in collaboration with Nokia Bell Labs. Apply here by 15 Nov: ellis.eu/news/ellis-phd…

@fraboeni is giving a talk on „Finding NeMo: localizing memorizing neurons in Diffusion Models” at #MLinPL

Ended up using the nanoGPT codebase, train on shakespeare char or fineweb and evaluate on hellaswag. For synthetic tasks the transformer 'unit test' is the copy task and long context variants (like mamba) are tested on associative recall.

if academics are so smart why can't they connect to eduroam?

Introducing DP Wizard - a just released interactive tool to help explore different parameter choices and implement them with the OpenDP Library!  Read more about the tool in the blog below and please send us your feedback! opendp.org/blog/dp-wizard…

Spending the summer with the OpenDP team was an incredible experience—I highly recommend it! Feel free to reach out if you have any questions!

🚨 We’ve trained on the entire web—now what? 🚨 Synthetic data holds promise as the next frontier but with caveats. Join us at the ICLR'25 workshop, "Will Synthetic Data Finally Solve the Data Access Problem?" this April in Singapore to discuss challenges and opportunities!

This is an interesting summary of the OpenDP workshop "Differential Privacy Beyond Algorithms"!

Excited to be in Singapore for ICLR, presenting our work on privacy auditing (w/ Aurélien & Nicolas Papernot). If you are interested in differential privacy/privacy auditing/security for ML, drop by (#497 26 Apr 10-12:30 pm) or let's grab a coffee! ☕ openreview.net/forum?id=xzKFn…

SAVE THE DATE for the 2025 OpenDP Community Meeting on September 19th in Dublin, Ireland! We are thrilled to co-locate with the Eyes-Off Data Summit (Oblivious) and can't wait to share more information on the agenda in the coming weeks - stay tuned 👀 sites.harvard.edu/opendp/events/…

My team is hiring a Research Engineer!! If you would like to work with me on agentic privacy, apply here in the next two weeks job-boards.greenhouse.io/deepmind/jobs/…

Without its international students, Harvard is not Harvard. hrvd.me/IntStudents25t

RAGs are extremely useful, and yet there isn't an opensource RAG system for wikipedia (or I couldn't find it). So I built WikiRAG, a simple open-source github + hugging repo✨ Spin up your own RAG server for wikipedia in a single line. 🚗💨

Learned a lot by working through this! Check out Sham's tweet summarizing our work and the full note

ICML's election for their board of directors has begun. I've thrown my hat in the ring. Please consider voting for Gautam Kamath. I have experience with the governance of TMLR, COLT, and ALT, and I think I've demonstrated myself as a consciencious and engaged community member.

New paper: Conformal prediction for long-tailed classification🐒 arxiv.org/abs/2507.06867 🧑‍🌾 (plant enthusiast): Help me identify plants! 🤖 (existing conformal algs): Do you want sets that never include rare plants or sets that contain 100s of labels? 🧑‍🌾: Uhh… neither? A🧵(1/n)