Thrilled to share that this work will appear at #NeurIPS2023. Big thanks to the collaborators. Really appreciated the insightful discussion with the reviewers. Stay tuned for the camera-ready. Preprint: arxiv.org/abs/2306.17194. See y'all in New Orleans!

Jonas is one of the most knowledgeable and kindest researchers I've collaborated with. He knows a lot about various ML research directions and technical details. Check out Jonas Geiping if you're applying for PhD programs. It'd be an incredible journey!

🚨Excited to announce a large-scale comparison of pretrained vision backbones including SSL, vision-language models, and CNNs vs ViTs across diverse downstream tasks ranging from classification to detection to OOD generalization and more! NeurIPS 2023🚨🧵 arxiv.org/abs/2310.19909

📌Happening today at 5:15 pm. Our spot is 📍# 1613, in the innermost row at the Great Hall. See you there!

🚨 Breaking Research Discovery! 🚨 Large Vision Language Models (#VLMs) amaze with coherence but hide risks. 🤯🗡️ 🔍 Meet "Shadowcast"🥷: A stealthy, mind-bending AI data poisoning method. 🕵️‍♂️💻 Project page 🔗: vlm-poison.github.io #LLMs #DataSecurity A 🧵 👇

BLIP3 is here!!!

Excited to share that our newest multi modal foundation model xGen-mm is out and it’s open source! It’s small (<5B models) and shining in both pre-trained and fine-tuned benchmarks. Check it out 👉Hugging Face: tinyurl.com/ybdmf5zs Salesforce AI Research #SalesforceAI #AI #ML

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens abs: arxiv.org/abs/2406.11271 A new interleaved multimodal pretraining dataset, consists of one trillion text tokens and three billion images, a 10x scale-up from existing

MINT-1T is now available on 🤗 huggingface.co/collections/ml…. A large-scale (1T tokens), open-source, interleaved image-text dataset with diverse data sources (HTML, PDFs, and ArXiv papers).

Join us this evening (8 PM PST) for a live discussion on our recent paper and model release 🤗