🔥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

About a year ago we put "A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision" on arxiv. We call it "LiT-decoder". It's been rejected (NoT sOtA!!1) but the lessons learned have guided us, and we've use it as a benchmark in many works. A🧶about the lessons

And of course, it's multilingual! 🗺️

PaliGemma - Open Vision Model from Google! 💎 > 3B parameter model - SigLiP + Gemma 2B > Supports images upto 896 x 896 resolution > Capable of Document understanding, Image detection, visual question answering, captioning and more > In addition to general purpose checkpoints

PSA: Stop pretraining your VLMs on EN-filtered data, even if it improves ImageNet and COCO‼️ Doing so impairs the model's understanding of non-English cultures❗️ I argued for years, now finally publish concrete results for this (imo) intuitively obvious recommendation A🧾🧶

Embrace cultural diversity in your large-scale data! 🌎🌍🌏 Angéline Pouget’s study shows that (quantitatively) you have no reason not to 🌸

Day 2 starts in a few hours, let's go! #cardiffnlpworkshop

Our team at Google DeepMind is seeking a Research Scientist with a strong publication record (multiple first-author papers) on multi-modal LLMs in top ML venues like NeurIPS, ICLR, CVPR. Email me at [email protected] Cordelia Schmid

📢#ACL2025 is inviting nominations and self-nominations to the ACL 2025 programme committee (reviewers or area chair) ➡️ forms.gle/Yu34Z13YzQ3sM8… deadline for nominations 🗓️ 16 Dec 2024. 🙏

🚀🚀PaliGemma 2 is our updated and improved PaliGemma release using the Gemma 2 models and providing new pre-trained checkpoints for the full cross product of {224px,448px,896px} resolutions and {3B,10B,28B} model sizes. 1/7

Want to work on the future of multimodal AI? Our Google DeepMind team in Grenoble, led by Cordelia Schmid, is hiring interns for multimodal AI research (long-video understanding and visual reasoning in 2D and 3D). Email [email protected] or find me at #NeurIPS2024!

📢 Have you been wondering what workshops are brewing in the *ACL venues in 2025? The list that we've been waiting for in here. Feel free to tag or repost with the organisers. Below are ACL 2025 workshops: #ACL2025NLP #NLProc #workshop 🧵

📢#ACL2025NLP This year we received 8276 submissions 👏 which is the highest number in the history of ACL conferences 🙌 If you are not yet involved as a reviewer, AC or SAC, we would encourage you to volunteer as an (emergency) AC or reviewer forms.gle/u5C2Daq1Mz9kXw… 🙏

You gotta check out this giraffe's flow! 🎤 #veo3