🔥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

So excited about this work (also in collaboration with Duen Horng "Polo" Chau) and the potential impact for victims of human sex trafficking! Check out the conference talk if you missed it youtu.be/d2RLrPhhjjw or paper catvajiac.me/files/trafficv… for more info! #ieeevis

DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models abs: arxiv.org/abs/2210.14896 github: github.com/poloclub/diffu…

Want to study prompts? We introduce DiffusionDB, the first large-scale text-to-image prompt dataset, containing 2 million Stable Diffusion generated images and their prompts specified by real users. DiffusionDB is publicly available Hugging Face Datasets: huggingface.co/datasets/poloc…

Hugging Face Big thanks to fantastic GaTech CSE and Machine Learning at Georgia Tech collaborators Evan Montoya, David, Alex Yang, Ben Hoover and Duen Horng "Polo" Chau. 📖 Paper: arxiv.org/abs/2210.14896 🔎 Homepage: poloclub.github.io/diffusiondb/ 💻 Code ⤵ github.com/poloclub/diffu…

DiffusionDB is now 7 times larger, with 14 MILLION image-prompt pairs! It also includes more data attributes—such as timestamp, creator ID, and image size—opening up new exciting research opportunities!! Explore DiffusionDB on Hugging Face Datasets now: huggingface.co/datasets/poloc…

14 million text-to-image prompt dataset with their hyperparameters (DiffusionDB dataset from @polodataclub) Quite useful for both research & product at the same time huggingface.co/datasets/poloc…

Diffusion-based Generation, Optimization, and Planning in 3D Scenes abs: arxiv.org/abs/2301.06015 project page: scenediffuser.github.io

Awards galore! ML PhD student Zijie (Jay) Wang is a recipient of the 2023 Apple Scholars in AI/ML PhD fellowship! Wang is one of only 22 young scholars from the around the world to receive the fellowship! Congratulations, Zijie Jay Wang! machinelearning.apple.com/updates/apple-…

🎉Best thing being Georgia Tech prof is working with amazing students. Congrats to Alex Yang for Best 1st Yr MS Pratham Mehta for Best 2nd Yr Leadership @KevinYLi_ for Provost’s Academic Excellence & Best Senior in Biomedical Eng Nilaksh Das for Best Doctoral Dissertation

Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion abs: arxiv.org/abs/2305.03509 paper page: huggingface.co/papers/2305.03…

Want to make sense of large embeddings? WizMap it!📍 WizMap is an interactive visualization tool for exploring embeddings. Seamlessly navigate through millions of points, while gaining valuable insights from multi-resolution summaries!! 👉 Try it now: poloclub.github.io/wizmap/

📢 Georgia Tech's School of Computational Science and Engineering has multiple faculty openings! cse.gatech.edu/faculty-hiring Join us at the coolest CSE department in the world! GaTech CSE Georgia Tech Computing Machine Learning at Georgia Tech

😎 Our paper on the LLM safety landscape has been accepted at NeurIPS Conference 2024! #Safety #LLM #MachineLearning

Hello, #ieeevis! We're excited to share our work from Georgia Tech at this year's IEEE VIS conference. Check out our papers, posters, and more at #VIS2024

CSE Prof. Duen Horng "Polo" Chau and his group are presenting two papers and two posters this week at IEEE VIS! Check out the interactive graphic 🔗👇 for a peek of all Georgia Tech research presented this week, including award-winning work on Transformer Explainer! public.tableau.com/views/VIS2024/…

Two papers in the same session IEEE VIS. Great collaborations with Xiaojuan Ma's lab HKUST, particularly Qian Zhu, who is leading the composite vis. Tao Lu presenting. +Sungwon, Chris North Virginia Tech Computer Science, Tica Lin Hanspeter Pfister Harvard VCG and DoD for embodied data transformation!

Introducing KnowledgeVIS! 🧠 KnowledgeVIS is a #visualization tool that compares fill-in-the-blank LLM prompts, revealing stereotypes & biases 💯 Paper: arxiv.org/abs/2403.04758 Code: github.com/AdamCoscia/Kno… Check out how KnowledgeVIS helps NLP practitioners evaluate LLMs: 🧵

🎉The coolest #CSE school in the world is hiring multiple faculty members! Application link below👇

Trustworthy machine learning focuses on building AI systems people can rely on: fair, transparent, secure, and aligned with human values. 🛡️ Learn more about our NeurIPS '24 joint research Georgia Tech & IBM Research , introducing the 'safety basin' concept, in the thread! 👇

“I did it to make my presentations look humorous. Nobody at MIT taught us DEI or respect.” - Excuse given by MIT Media Lab researcher who has received many recognitions. NOTE: Most MIT Media Lab researchers I know are highly respectful and morally upright.