These will be awesome workshops on robustness and reliability in ML and LLM specifically. Please consider submitting poster and registering :)

Looking forward to attending these two workshops, will be awesome!

Our new #ICLR2024 paper shows how LLMs can successfully check their own change of thought reasoning without any fine-tuning or even examples, using an approach we call SelfCheck.

Join me at poster 125 this afternoon to learn more

Paper: openreview.net/forum?id=pTHfA…

#ICLR2024
Hi all,

Presenting tomorrow NEVIS’22, a new benchmark developed using 30 years of computer vision research for evaluating AI models which can continually build on their knowledge to learn future tasks more efficiently!

Halle B, poster #279, 10:45am. ➡️

#ICLR2024
Struggle with non-stationary classification? We might have a solution for you!

Check out our ICLR2024 paper on using Kalman fitler together with Neural Networks which adapts to non-stationarity arxiv.org/abs/2306.08448

Halle B poster #188, Friday 10th of May, 10:45am

🔥 We're organizing two robustness workshops this year! 🔥
📢 Registration is now open for both.
Don't miss this chance to explore the latest in robust ML and LLMs with leading researchers in the field!
⬇️ Details below ⬇️

🚨 Registration is now open! 🚨

Join us for two ELLIS Robust Machine Learning Workshops in 2024:

1⃣ Robust ML Workshop, June 27-28 (Helsinki, Finland)
Register: elomake.helsinki.fi/lomakkeet/1297…
2⃣ Robust LLMs Workshop, July 29-30 (Oxford, UK)
Register: oxforduniversitystores.co.uk/conferences-an…

Let the celebration begin
Our position paper 'Bayesian Deep Learning in the Age of Large-Scale AI' is accepted ICML Conference
Kudos to all coauthors Michael A Osborne Emtiyaz Khan Konstantina Palla Max Welling Wilson Andrew Gordon Wilson Yee Whye Teh Jose Miguel Hernández-Lobato and more
Enjoy
arxiv.org/pdf/2402.00809

The infini-gram paper is updated with the incredible feedback from the online community 🧡 We added references to papers of Jeff Dean (@🏡) Yee Whye Teh Ehsan Shareghi Edward Raff et al.

arxiv.org/abs/2401.17377

Also happy to share that the infini-gram API has served 30 million queries!

DEADLINE March 29: prepare and submit your application for EEML 2024, Novi Sad, Serbia eeml.eu 🇷🇸. Topics: Basics of ML, Multimodal learning, NLP, Advanced DL architectures, Generative models, AI for Science. Check our stellar speakers! Scholarships available! 🎉

There's only ~2 days to go to send your application to this year's EEML Summer School, proudly hosted in Novi Sad 🇷🇸

Our team is working hard behind the scenes to make it an event to remember. The speaker list speaks for itself 🤩 I really hope to see you there!

📢 We are back! 🎇 Following the success of our Robust ML Workshop in 2023, we are organising not one, but two workshops this year:
ELLIS Robust ML Workshop 2024: June 27-28, Helsinki 🇫🇮
ELLIS Robust LLMs Workshop 2024: July 29-30, Oxford 🇬🇧

Congrats mrinank ⭐️ learning about love I will miss your unique combination of love and AI.

May you soar high in the big blue California sky!

Just got back from vacation, and super excited to finally release Griffin - a new hybrid LLM mixing RNN layers with Local Attention - scaled up to 14B params!

arxiv.org/abs/2402.19427

My co-authors have already posted about our amazing results, so here's a 🧵on how we got there!

Want to keep your LLM up-to-date without expensive re-training? ➡️We introduce a new, easy-to-use retrieval method that allows Q&A on thousands of new documents without any parameter updates during inference. ⏲️

📰 Paper: arxiv.org/abs/2403.04317
🔗 Code: github.com/jihoontack/MAC

Linear RNNs/state-space models for language modelling! Congrats Soham De Sam Smith and team! Such a journey :)

🚨 Model-based methods for offline RL aren’t working for the reasons you think! 🚨

In our new work, led by Anya Sims, we uncover a hidden “edge-of-reach” pathology which we show is the actual reason why offline MBRL methods work or fail!

Let's dive in! 🧵

[1/N]

Please apply if you are a UK undergraduate from under-represented backgrounds interested in exploring what a career in AI research is like. Deadline Feb 17!
Google DeepMind has kindly supported the AI internship projects UNIQ+, University of Oxford, thank you!