Just one week till our NeurIPS Conference social on ML and climate change! We’ll have icebreaker bingo, roundtable discussions and a friendly atmosphere. sighellan.github.io/climate-ml-soc…

🚨Parameter Efficient Fine-Tuning has been well researched for NLP, vision, and cross-modal tasks. So why should MedAI be left behind? Presenting the first evaluation on PEFT for medical AI - arxiv.org/abs/2305.08252 16 PEFT methods, 5 datasets including a text-to-image task 🔥

Interested in Bayesian optimisation and how it can be applied against climate change? Check out our new short survey. We look at material discovery, wind farm layout planning, optimal renewable control and environmental monitoring. For each we suggest a benchmark to get started.

Finding yourself repeatedly training your ML model because you’ve collected more data? Not sure what to do with the hyperparameters? We investigated for you! Check out the paper arxiv.org/abs/2306.16916 with the wonderful Huibin Shen, François-Xavier Aubet, David Salinas and Aaron Klein

📢New work on Self-Supervised Representation Learning📢 🎯Rather than using data augmentations to induce invariance, we use them to separate/disentangle. ➡️Improves performance* on downstream tasks, since one task's "style" may be another's "content". arxiv.org/abs/2311.08815

🚨New TACL paper 🚨 Can we use explicit latent variable alignment for cross-lingual transfer? Minotaur uses optimal transport for explicit alignment across languages. w/ Tom Hosking, Mirella Lapata. To be presented EMNLP 2025 + Meral Yıldız in-person 🇸🇬 doi.org/10.1162/tacl_a…

Excited to have been part of DemoFusion, bringing UHD generation to SDXL on your desktop with no training! With Ruoyi Du Yi-Zhe Song Dongliang Chang Project: ruoyidu.github.io/demofusion/dem…, paper: arxiv.org/abs/2311.16973 #GenerativeAI

🚨FairTune: Optimizing PEFT for Fairness in Medical Image Analysis A new framework to finetune your large vision models that improves downstream fairness. Accepted in #ICLR2024 ✨ With: Ondrej Bohdal Sotirios (Sotos) Tsaftaris Timothy Hospedales CC: Vivek Natarajan Javier Alvarez Valle Fernando Pérez-García Bo Wang UKRI Centre for Doctoral Training in Biomedical AI

I'm happy to announce the first competition of the #AutoML conference 2024 (automl.cc). Neural architecture search #NAS is one of the most well-known fields of AutoML and has enabled fantastic achievements in the last few years.

Delighted to share that my work on establishing the first extensive benchmark for PEFT in Medical Imaging has been accepted in @midl-conference.bky.social with scores 4,4,5🥳 Link: openreview.net/forum?id=LVRhX… cc: Timothy Hospedales Sotirios (Sotos) Tsaftaris Pedro P. Sanchez Linus Ericsson UKRI Centre for Doctoral Training in Biomedical AI

🚨 MemControl: Mitigating Memorization in Medical Diffusion Models via Automated Parameter Selection A new strategy to mitigate memorization in Diffusion models Arxiv: arxiv.org/abs/2405.19458 Work done with Pedro P. Sanchez Ondrej Bohdal Sotirios (Sotos) Tsaftaris Timothy Hospedales UKRI Centre for Doctoral Training in Biomedical AI 🧵👇

Check out our new work on NAS search spaces! We have created einspace, a new expressive search space that unifies many architectural families, including convnets, transformers and mlp-only architectures. paper: arxiv.org/abs/2405.20838 project page: linusericsson.github.io/einspace/

Pretty cool place you know bsky.app/profile/linuse… #NeurIPS2024 #neurips