🔥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

github.com/mbzuai-oryx/Vi…

🚨 New blog post alert🚨: On the Convergence of the Unadjusted Langevin Algorithm fa.bianp.net/blog/2023/ulaq/ The Langevin algorithm is a marvel of optimization: it allows to solve an infinite-dimensional problem (approximating a probability distributions) in finite time.

We're organizing a tutorial on Prompting in Vision at #CVPR2023 w/ Ziwei Liu Phillip Isola Hyojin Bahng Ludwig Schmidt Sarah Pratt Denny Zhou Please visit our website at prompting-in-vision.github.io to know more about this event

If you're interested in how image diffusion can be adapted to learn about the 3D world, don't miss our poster (25) presentation this afternoon at #CVPR2023.

📢📢📢 Job Opportunity! Join Dr Elliot J. Crowley and the Bayesian and Neural Systems Group as a postdoc in NAS and AutoML at the University of Edinburgh. 24-month funded position starting Autumn 2023. PhD in ML or related field required. Apply now: elxw.fa.em3.oraclecloud.com/hcmUI/Candidat…

Four papers accepted to #ICCV2023! 3/4 Agile Modeling: From Concept to Classifier in Minutes We empower any user to develop a classifier for a subjective visual concept in under 30 minutes. arxiv.org/abs/2302.12948 With O.Strech, E.Vendrow, and many others

Four papers accepted to #ICCV2023! 2/4 CAD-Estate: Large-scale CAD Model Annotation in RGB Videos >100k 3D objects annotated on RGB videos of complex scenes Dataset release coming soon! arxiv.org/abs/2306.09011 Stefan Popov, Kevis-Kokitsi Maninis, Matthias Niessner

Interested in practical uncertainty quantification? Our new Bayesian NN library from Samsung AI Cambridge scales to large VITs! One line of code wraps any architecture with no modifying your model definition! arxiv.org/abs/2309.12928 github.com/SamsungLabs/Ba… Minyoung Kim

🚨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

What role does 3D have in learning robust representations of the visual world and can we develop scalable ways to inject 3D priors into our 2D self-supervised learning algorithms? If you are interested in these questions, and looking for a postdoc position, please read on. #job

Build what you need and use what you build. This is a core philosophy of my research. It shifts the focus away from publishing “papers” to what really matters — impact. This thread unpacks why I think this is a successful approach to science. 1/10 Or see: perceiving-systems.blog/en/post/build-…

The physical 3D world affords inherent & implicit consistency across various computer vision tasks. Come see how our #ICLR2024 work leverages differentiable neural volume rendering and 3D structure to improve multitask learning. Tue 3.30-5.30pm(BST) Led by the awesome Wei-Hong Li

Thanks Steven! I am excited to present our 3D-aware Multi-task Learning paper tomorrow (Tue) 4:30-6:30pm (local time) in Hall B. Looking forward to meeting new friends! iclr.cc/virtual/2024/p…

Why are reps converging? We suggest a few possibilities, including: As we train on more tasks, there are fewer reps that can satisfy all, leading to an Anna Karenina scenario (arxiv.org/abs/2106.07682): all strong models are alike, each weak model is weak in its own way. 3/8

🚨 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/

I will present our work with Oisin Mac Aodha "SAOR: Single-View Articulated Object Reconstruction" on Thursday morning at #CVPR2024! mehmetaygun.github.io/saor Come to our poster (THU-AM: Poster 68) to learn more about it, below are some hints about what you can expect!

We are releasing 4M-21 with a permissive license, including its source code and trained models. It's a pretty effective multimodal model that solves 10s of tasks & modalities. See the demo code, sample results, and the tokenizers of diverse modalities on the website. IMO, the

🎉 Excited to share Clarity, an open-source website template I designed to better present and visualise AI research! If you appreciate the minimalist design and want to use it in your own projects, please check it out here: shikun.io/projects/clari…

🚀 The next generation of AI models must go beyond creating pixels - it needs to build and understand worlds. At SpAItial, we're developing foundation models that are physically grounded by design. Excited to share what we've been building with an incredible team!