Excited to present at #NeurIPS2024 our work on robust mixture learning! How hard is mixture learning when (a lot of) outliers are present? We show that it's easier than it seems! Join us at the poster session (Wed, 16:30 PT, West Ballroom A-D #5710).

Looking for a more efficient way to estimate treatment effects in your randomized experiment? We introduce H-AIPW: a novel estimator that combines predictions from multiple foundation models with real experimental data. arxiv.org/abs/2502.04262

Eager to hear feedback from anyone who applies causal inference about this recent work with this amazing group of people Piersilvio De Bartolomeis Javier Abad Martinez Guanbo Wang Konstantin Donhauser Ray Duch and Issa Dahabreh.

LLMs accidentally spitting out copyrighted content? We’ve got a fix. Our paper on CP-Fuse—a method to prevent LLMs from regurgitating protected data—got accepted as an Oral at #ICLR2025! 👇Check it out! 📄 arxiv.org/pdf/2412.06619 🤖 github.com/jaabmar/cp_fuse

Very shortly at AAAI , Alexandru Tifrea and I will be giving a Tutorial on the impact of Quality and availability of labels and data for Privacy, Fairness, and Robustness of ML algorithms See here amartya18x.github.io/files/Tutorial… Machine Learning Section @UCPH DIKU - Department of Computer Science, UCPH Google DeepMind

Presenting our work at #ICLR this week! Come by the poster or oral session to chat about copyright protection and AI/LLM safety 📌 𝐏𝐨𝐬𝐭𝐞𝐫: Friday, 10 a.m. – 12.30 p.m. | Booth 537 📌 𝐎𝐫𝐚𝐥: Friday, 3.30 – 5 p.m. | Room Peridot Francesco Pinto @ Neurips 2024 Konstantin Donhauser Fanny Yang

Landed in Singapore for #ICLR—excited to see old & new friends! I’ll be presenting: 📌 RAMEN @ Main Conference on Saturday 10 am (Javier Abad Martinez Yixin Wang Fanny Yang) 📌 Causal Lifting @ XAI4Science Workshop on Sunday (Riccardo Cadei Ilker Demirel Francesco Locatello )

Presenting 2 posters today at ICLR. Come check them out! 10am ➡️ #502: Scalable Extraction of Training Data from Aligned, Production Language Models 3pm ➡️ #324: Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI

Advertising an Open Postdoc position in learning theory/ privacy/ robustness/ unlearning or any related topics with me and others in University of Copenhagen, Denmark. If you think you would be a good candidate, send me an email amartya18x.github.io/hiring/

What if learning and unlearning happen simultaneously, with unlearning requests between updates? Check out our work on online learning and unlearning-algorithms with certified unlearning, low computational overhead and almost no additional regret. arxiv.org/abs/2505.08557

Register now (first-come first-served) for the "Math of Trustworthy ML workshop" at #LagoMaggiore, Switzerland, Oct 12-16 this year, with a great speaker lineup and the opportunity to present your work as a poster session or contributed talk. Details @ mmlworkshop.ethz.ch

Introducing AI 𝐅𝐨𝐫𝐦𝐚𝐭𝐭𝐢𝐧𝐠 𝐢𝐧 𝐄𝐱𝐜𝐞𝐥 🤯 Tracelight Watch Tracelight format 908 cells in just 39 seconds. Right inside of Excel. 👀 Excel formatting is a huge waste of human talent. We've finally fixed it. Tracelight understands your financial model's existing

Today, I’m proud to announce our $3.6m seed round, and launch Tracelight to the world. Tracelight is the best AI agent for spreadsheet tasks. No waitlist - use Tracelight today. We’re giving away a month of our pro plan for free - comment and we will send you a code.

LEAF-CLIP 🍃📎 has been accepted in NeurIPS 2025! 🤩 You can find our robust CLIP models in huggingface.co/LEAF-CLIP