🚨🚨We are hosting "Frontier Topics in Generative AI" Seminar Series at @ASU . This series delves into the cutting-edge of GenAI, exploring key areas like large-language models, text-to-image, video generation, and more. We have our first speaker this week.

ByteDance announces Diffusion Model with Perceptual Loss paper page: https://t.co/mBYXqlsLul Diffusion models trained with mean squared error loss tend to generate unrealistic samples. Current state-of-the-art models rely on classifier-free guidance to improve sample quality,

Adversarial learning + Bayesian CNNs = ⬆️single-source domain generalization tasks. Joint work with Sheng Cheng, @trgokhale, and from @ApgAsu ArXiv: https://t.co/rVQEnR5dFi To 📢 @ICCVConference PS: I still think this paper could be with just three sentences... 🤠

🎓 Defended my thesis today! 🌟 Big shout out to my advisor Dr. Hanghang Tong, and my thesis committee: Dr. Jiawei Han, Dr. Ross Maciejewski and Dr. Han Zhao (@hanzhao_ml)! 🙌 Thank you all to my friends, collaborators and family who supported me in this journey.

1. https://t.co/Nc4RG1r9hP. We introduce a new multimodal-query retrieval benchmark with an end-to-end multimodal retriever, ReMuQ dataset is available online: https://t.co/CaXh3hxlfH. It is a collaboration with @Jacob292020 @trgokhale @Yezhou_Yang @chittabaral

🎉Thrilled to share that our paper "World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models" was selected for the outstanding paper award at #ACL2023NLP! Thanks @aclmeeting :-) Let's take grounding seriously in VLMs because... 🧵[1/n]

"WOUAF"🐺modifies generative models by each user's unique digital fingerprint, imprinting an identifier onto the resultant content. 🐺incorporates fine-tuning into T2I (Stable Diffusion Model) and demonstrates near-perfect attribution accuracy with a minimal impact on quality.

Tired of fine-tuning image generation models on each subject you care to generate? Today, we release SuTI, a zero-shot subject-driven text-to-image generator that operates fully in-context without tuning. One SuTI model is all you need! Website: https://t.co/xheWkQjOr8

Anti-DreamBooth: Protecting users from personalized text-to-image synthesis abs: https://t.co/34UcWcIUax project page: https://t.co/QGx0vIcs9S github: https://t.co/5H738ujk8j

For anyone who isn't already aware of it, Tiled VAE is a way to create giant (4k+) images in automatic1111 without any kind of visible seams or lots of complicated steps. Info in comments. #AIArt #StableDiffusion2 / #StableDiffusion

📽️Text-to-Video? It could revolutionize entertainment as we know it. Here's Phenaki, a model that can synthesize realistic videos from text prompt sequences. More examples below ↓

OpenAI just dropped a prototype of 3D DALLE (called “Point-E”) 👀. It isn’t as good as Google’s DreamFusion, but blazing fast! Like ~600x faster to generate 😮. 2D DALLE has already turned the creative world upside down. How will 3D DALLE disrupt games, VR, metaverse, …? 🤯

ODRUM for #CVPR2023 🍻😄 This time we booked a complete day✌️

Objaverse: A Universe of Annotated 3D Objects 800K+ 3D models with descriptive captions arxiv: https://t.co/kWWxDCSSKL website: https://t.co/BMHqJwrUmd

✨ Introducing Imagine 3D: a new way to create 3D with text! Our mission is to build the next generation of 3D and Imagine will be a big part of it. Today Imagine is in early access and as we improve we will bring it to everyone https://t.co/VIdilw7kpa

I am on the academic job market this year. I study data mining, machine learning and trustworthy AI, especially for graphs and multimedia with applications to network science, healthcare, cybersecurity and social good. Please find out more information at

We are excited to announce the release of Stable Diffusion Version 2! Stable Diffusion V1 changed the nature of open source AI & spawned hundreds of other innovations all over the world. We hope V2 also provides many new possibilities! Link → https://t.co/QOSSmSRKpG

Excited to share our #EMNLP2022 paper, “CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering” — w/ @trgokhale , @cbaral , and @Yezhou_Yang . Arxiv: https://t.co/NMsHzgy138 Demo: https://t.co/6tb7YffBSk 🧵1/

We desperately need to build a diffusion model to do this. Please cite this twit when it's on Arxiv.

Played with optimizing Neural Atlases through Stable Diffusion. So much fun! Here are a few examples of video edits: @RafailFridman @DanahYatim