🔥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

OATML_Oxford group members and collaborators are proud to present 6 papers at NeurIPS 2022 main conference, and 8 workshop papers. Come chat to us at the poster sessions! oatml.cs.ox.ac.uk/blog/2022/11/2…

**Call open for the Schmidt AI in Science Postdoctoral Fellowship Program** @schmidtfutures University of Oxford Have you completed a PhD in an area of mathematical, physical, or life sciences? Do you have a vision for transformational research in your field using tools from ML/AI?

OATML_Oxford is co-hosting Schmidt AI in Science Fellows to work cutting-edge AI to tackle the big scientific questions of our time. Take a look at some of the research we've done with collaborators in the sciences: nature.com/articles/s4158…

We have a PhD studentship co-supervised between me OATML_Oxford and Alessandro Abate Oxford Comp Sci!

📢 We are presenting our TranceptEVE preprint at the LMRL workshop today (4-5pm ET, poster # C-48) 📢

How can we measure how uncertain LLMs are about their generations? In our spotlight at #iclr2023 with Yarin & Sebastian Faray, we introduce "semantic entropy", the entropy over meanings rather than sequences, and show that it reliably measures LM uncertainty🧵arxiv.org/abs/2302.09664

I'm very proud that my collaboration w NASA Ames & the The SETI Institute is finally published in Nature Astronomy We show a framework to search for life on another planet in a data-driven fashion, starting from orbit & all the way through to a rover's view nature.com/articles/s4155…

Our awesome Project Manager at our AI/ML research group OATML_Oxford (based at Oxford Comp Sci University of Oxford) will leave us soon :( We're looking for someone to take the role: if you know anyone who's interested, please forward the job advert! closing 21/4 cs.ox.ac.uk/news/2152-full…

We’ve updated our EVEscape paper with more SARS2 retrospective evaluation and potential use-cases! biorxiv.org/content/10.110… Collaborators Sarah Gurev Pascal Notin Noor Youssef Nathanael Rollins Chris Sander aka cscbio Yarin (OATML_Oxford), Debora Marks, 🧵1/4

New AI tool could help predict viral outbreaks ox.ac.uk/news/2023-10-1… OATML_Oxford #AI

We’re organising a virtual open day! 📅 4-5:30 PM GMT on 22 Nov 2023 Anyone interested in joining OATML_Oxford 🥣🌾for a PhD is welcome! Come to meet OATMLers, get a feel for our group, and ask any questions you may have! ✏️ Sign Up: forms.gle/MSMwp3wvUR9Cnc…

Registration for OATML’s Virtual Open Day closes tomorrow. If you are interested in joining for a PhD, we encourage you to register and join us 22 Nov from 4-5:30GMT! Sign-up: docs.google.com/forms/d/e/1FAI… Group members attending:

📢Competition results! 📢 Very excited to announce TextCAVs, an adaptation of TCAV which can provide concept-based explanations for deep learning models with no data. In the #SaTML2024 competition we found all four secret trojans and came third in the rediscovery benchmark! 🎉

📢 New Paper Alert! 📝 "Explaining Explainability: Understanding Concept Activation Vectors" 📄arxiv.org/abs/2404.03713 What does it mean to represent a concept as a vector? We explore three key properties of concept vectors and how they can affect model interpretations. 🧵(1/5)

Very interesting paper about unlearning for AI Safety, a subject that deserves more attention. ⬇️

📣 New paper AI gov. frameworks are being designed to rely on rigorous assessments of capabilities & risks. But risk evals are [still] pretty bad – they regularly fail to find overtly harmful behaviors that surface post-deployment. Model tampering attacks can help with this.

Defending against adversarial prompts is hard; defending against fine-tuning API attacks is much harder. In our new AI Security Institute pre-print, we break alignment and extract harmful info using entirely benign and natural interactions during fine-tuning & inference. 😮 🧵 1/10

We have a postdoc position available (closing 17th March) to lead work on Generative AI. Please share with anyone you think this might be relevant to! my.corehr.com/pls/uoxrecruit…