🔥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

ImageNet is the new CIFAR! My students made FFCV (ffcv.io), a drop-in data loading library for training models *fast* (e.g., ImageNet in half an hour on 1 GPU, CIFAR in half a minute). FFCV speeds up ~any existing training code (no training tricks needed) (1/3)

Super thrilled to have our work "MEME" on multimodal VAE accepted to ICLR as a spotlight paper! ICLR 2026

I just got a hardcopy of my own book - it finally feels real :) I'm very happy with the print quality (see attached photo) - but you can still get the pdf for free from probml.ai if you prefer.

I am fundraising for Oxford Health Charity. Check out my JustGiving page and please donate if you can. Thank you! #JustGiving justgiving.com/fundraising/Fu…

Oxford Torr Vision Group will be presenting 5 papers in this year's NeurIPS. Congratulations to all members involved!

Oxford Torr Vision Group will be presenting 5 papers in ECCV 2022. Drop by our posters to know more! Congratulations to all members and collaborators!

Researchers want good out-of-distribution robustness. But what is OOD? We explain why standard def doesn’t work and propose ‘OOD cards’ to improve research. 1/7 w/ 🐶 Virtual Poster Friday 9:40CT/15:40GMT neurips2022.mlsafety.org Paper: openreview.net/forum?id=XCS_z… w/ Yarin

It took us some time to collect the list but it's finally here! In 2022, we have 38 papers, including collaborations, in 16 ML and CV venues. Have a look at this thread to find more! Congratulations to all the authors!

7 papers, 3 of which are accepted as highlights (top 2.5% of all submissions), in CVPR 23! Congratulations to all authors and collaborators! Jishnu Mukhoti Adel Bibi Ameya P. @ ICML 2025 Puneet Dokania A. Tuan Nguyen Pau de Jorge Kejie Li

Quite a bummer that even with #CVPR2025 & Nicole Finn's efforts to move things forward, visa applications for presenters are stuck, & emails/messages/web-forms to IRCC all seem to fall on deaf ears. With dates fast approaching, are we then supposed to just give up?

And next up: come to # 362 for "Deep Deterministic Uncertainty: A New Simple Baseline" by Jishnu Mukhoti, yours truly, Joost van Amersfoort, Phil Torr & Yarin. Another highlight imo 🤗 See you all in a bit! OATML_Oxford Oxford Torr Vision Group #CVPR2023 cvpr2023.thecvf.com/virtual/2023/p…

I have worked with both Puneet Dokania and Prof Phil Torr and can attest to them being superb mentors. Apply!!

Very excited about this! Looking forward to working and building together at Finster AI!

Quick self indulgent tweet: Given we’ve done p little branding/pr (so far), it’s always nice to see Finster AI turn up on a list this early :) Tis customers, product, revenue in that order of prioritisation so far. stay tuned for lots of updates in the summer hopefully!

Wanna know how finetuning makes a foundation model forget and how to avoid it? Have a look at our paper accepted Transactions on Machine Learning Research! 📜 Paper: arxiv.org/abs/2308.13320 Work done with amazing co-authors: Yarin philip Puneet Dokania OATML_Oxford Oxford Torr Vision Group!

Fine-tuning can cripple your foundation model; preserving features may be the solution Jishnu Mukhoti, Yarin Gal, Philip Torr, Puneet K. Dokania. Action editor: Marcus Rohrbach. openreview.net/forum?id=kfhoe… #forgetting #learned #concepts

Quite exciting how far we have come in the last couple months... stay tuned for more!

Analysts often track metrics like Net revenue retention (NRR) for SaaS companies that aren't listed in an income statement or balance sheet and require manually going through filings and earnings calls. With Finster, you can use a single instruction to extract these metrics

Don't miss our workshop on Uncertainty Quantification in Computer Vision European Conference on Computer Vision #ECCV2026 on Mon 30 Sep AM in room Brown3. We have an exciting speaker panel Gilles Louppe Polina Kirichenko Jishnu Mukhoti, fun papers & posters, the reveal of BRAVO challenge results. Join us! #ECCV2024 #UNCV2024

Thanks for organizing the workshop and inviting me to give a talk! Loved the experience! Andrei Bursuc, Andrea Pilzer, Gianni Franchi and other organizers European Conference on Computer Vision #ECCV2026 ! #UNCV2024 #ECCV2024