Jay Wang
@zijie.wang
Safety researcher at OpenAI 🤖 | ML PhD from GeorgiaTech 🐝 | Researching human-AI interaction 🔍 | Prev. intern GoogleAI, Apple MSR 🌱 | UWMadison '19 🦡
So honored to be named to @Forbes 30 Under 30 in Science this year! Extremely grateful to my mentors, especially @PoloChau, and all my colleagues! ❤️ Thank you @jaemariesolyst for breaking the news to me 😆. https://www.forbes.com/profile/zijie-jay-wang/?list=30under30-science/
February 25, 2025 at 4:58 PM
So honored to be named to @Forbes 30 Under 30 in Science this year! Extremely grateful to my mentors, especially @PoloChau, and all my colleagues! ❤️ Thank you @jaemariesolyst for breaking the news to me 😆. https://www.forbes.com/profile/zijie-jay-wang/?list=30under30-science/
Need recommendation letters for your visa, job, or academic pursuits? 𝗥𝗲𝗰𝗥𝗲𝗰 makes it easy to find potential letter writers who already know your work—based on citations of your papers! Save time and boost your chances! Try it now 👉 https://xiaohk.github.io/recrec/ #PhDLife
February 25, 2025 at 4:58 PM
Need recommendation letters for your visa, job, or academic pursuits? 𝗥𝗲𝗰𝗥𝗲𝗰 makes it easy to find potential letter writers who already know your work—based on citations of your papers! Save time and boost your chances! Try it now 👉 https://xiaohk.github.io/recrec/ #PhDLife
Want to build on-device RAG applications? Look no further than MeMemo! This new JavaScript library makes it super easy to develop scalable in-browser vector databases and fast vector search. 🧑💻 Try out this RAG Playground powered by MeMemo 👉 https://poloclub.github.io/mememo #SIGIR2024
February 25, 2025 at 4:58 PM
Want to build on-device RAG applications? Look no further than MeMemo! This new JavaScript library makes it super easy to develop scalable in-browser vector databases and fast vector search. 🧑💻 Try out this RAG Playground powered by MeMemo 👉 https://poloclub.github.io/mememo #SIGIR2024
The Explainable AI session kicks off with "User Characteristics in Explainable AI: The Rabbit Hole of Personalization?" 🐰 #CHI2024 This paper is from @robertnimmo_, Marios Constantinides, Ke Zhou, @danielequercia, and @DrSimoneStumpf 📝 https://dl.acm.org/doi/10.1145/3613904.3642352
February 25, 2025 at 4:57 PM
The Explainable AI session kicks off with "User Characteristics in Explainable AI: The Rabbit Hole of Personalization?" 🐰 #CHI2024 This paper is from @robertnimmo_, Marios Constantinides, Ke Zhou, @danielequercia, and @DrSimoneStumpf 📝 https://dl.acm.org/doi/10.1145/3613904.3642352
Explore the design space of notebook visualization tools with SuperNOVA! Our interactive browser showcases 160+ notebook vis tools surveyed from 8M+ open-source notebooks, highlighting key design implications and trade-offs. 👉 https://poloclub.github.io/supernova/ #CHI2024
February 25, 2025 at 4:57 PM
Explore the design space of notebook visualization tools with SuperNOVA! Our interactive browser showcases 160+ notebook vis tools surveyed from 8M+ open-source notebooks, highlighting key design implications and trade-offs. 👉 https://poloclub.github.io/supernova/ #CHI2024
How might we promote responsible AI among LLM app developers? Introducing Farsight—in situ widgets that bring responsible AI to early prompt-based AI prototyping. Given a prompt, Farsight highlights relevant AI incidents & potential harms. 👉 https://PAIR-code.github.io/farsight/ #CHI2024
February 25, 2025 at 4:56 PM
How might we promote responsible AI among LLM app developers? Introducing Farsight—in situ widgets that bring responsible AI to early prompt-based AI prototyping. Given a prompt, Farsight highlights relevant AI incidents & potential harms. 👉 https://PAIR-code.github.io/farsight/ #CHI2024
Now you can run open-source LLMs, such as Llama 2 and Phi 2, locally in Wordflow! ✨ With these on-device LLMs, you can privately run AI prompts in Wordflow without worrying about sending sensitive data to external AI services like OpenAI! 👉 https://t.co/eciUcDhRLC https://t.co/XNQVtdllH1
February 25, 2025 at 4:56 PM
Now you can run open-source LLMs, such as Llama 2 and Phi 2, locally in Wordflow! ✨ With these on-device LLMs, you can privately run AI prompts in Wordflow without worrying about sending sensitive data to external AI services like OpenAI! 👉 https://t.co/eciUcDhRLC https://t.co/XNQVtdllH1
#cscw24 #facct24 You can directly use Wordflow to prompt AI models to apply the below guide to your own writing! https://poloclub.github.io/wordflow?prompt=c092bbeb-9120-5960-adaa-50684402d133 https://x.com/snchancellor/status/1744805205391114585
February 25, 2025 at 4:56 PM
#cscw24 #facct24 You can directly use Wordflow to prompt AI models to apply the below guide to your own writing! https://poloclub.github.io/wordflow?prompt=c092bbeb-9120-5960-adaa-50684402d133 https://x.com/snchancellor/status/1744805205391114585
Tired of using chat-based interfaces to polish your #ICML2024, #CSCW2024, and #FAccT2024 papers with LLMs? Try Wordflow, a highly customizable and social AI writing assistant! You can discover and share AI prompts, and run them with various LLM models. 👉https://poloclub.github.io/wordflow/
February 25, 2025 at 4:56 PM
Tired of using chat-based interfaces to polish your #ICML2024, #CSCW2024, and #FAccT2024 papers with LLMs? Try Wordflow, a highly customizable and social AI writing assistant! You can discover and share AI prompts, and run them with various LLM models. 👉https://poloclub.github.io/wordflow/
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: https://poloclub.github.io/wizmap/
February 25, 2025 at 4:55 PM
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: https://poloclub.github.io/wizmap/
Want to explain transformers directly in web browsers? WebSHAP comes to the rescue! With this JavaScript library, you can explain any machine learning models anywhere! 💻📱📺 👉 Check out demos explaining transformers, XGBoost, CNNs at https://poloclub.github.io/webshap/. #TheWebConf2023
February 25, 2025 at 4:54 PM
Want to explain transformers directly in web browsers? WebSHAP comes to the rescue! With this JavaScript library, you can explain any machine learning models anywhere! 💻📱📺 👉 Check out demos explaining transformers, XGBoost, CNNs at https://poloclub.github.io/webshap/. #TheWebConf2023
ML recourse helps users alter unfavorable ML decisions by changing input variables, but existing techniques assume developers know what variables can be changed. Our #CHI2023 work ✨GAM Coach✨ creates a new paradigm that enables users to interactively customize recourse plans!
February 25, 2025 at 4:54 PM
ML recourse helps users alter unfavorable ML decisions by changing input variables, but existing techniques assume developers know what variables can be changed. Our #CHI2023 work ✨GAM Coach✨ creates a new paradigm that enables users to interactively customize recourse plans!
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 @huggingface Datasets now:
https://t.co/X6FWdcQyRs https://t.co/hQ4D3...
https://t.co/X6FWdcQyRs https://t.co/hQ4D3...
February 25, 2025 at 4:54 PM
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 @huggingface Datasets now:
https://t.co/X6FWdcQyRs https://t.co/hQ4D3...
https://t.co/X6FWdcQyRs https://t.co/hQ4D3...
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 @huggingface Datasets: https://t.co/X6FWdcQ11U
February 25, 2025 at 4:53 PM
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 @huggingface Datasets: https://t.co/X6FWdcQ11U
How to compare thousands of decision trees? TimberTrek comes to help! This interactive tool summarizes 1k+ almost-equally-accurate sparse decision trees and helps you explore, compare, and curate models that meet your needs. Try it now at https://poloclub.github.io/timbertrek! #IEEEVIS
February 25, 2025 at 4:53 PM
How to compare thousands of decision trees? TimberTrek comes to help! This interactive tool summarizes 1k+ almost-equally-accurate sparse decision trees and helps you explore, compare, and curate models that meet your needs. Try it now at https://poloclub.github.io/timbertrek! #IEEEVIS
Want to align ML models' behaviors with your knowledge and values? With GAM Changer, you can easily do that! This interactive tool allows you to edit a GAM’s learned weights, monitor the impacts of edits, identify correlated features, and keep track of editing history! #KDD2022
February 25, 2025 at 4:53 PM
Want to align ML models' behaviors with your knowledge and values? With GAM Changer, you can easily do that! This interactive tool allows you to edit a GAM’s learned weights, monitor the impacts of edits, identify correlated features, and keep track of editing history! #KDD2022
Tired of scrolling back and forth in your long and messy Jupyter notebooks? StickyLand comes to the rescue! With this Jupyter extension, you can drag-and-drop to create sticky cells, auto-run cells, and even build a full-fledged dashboard to interpret your ML models! #CHI2022
February 25, 2025 at 4:52 PM
Tired of scrolling back and forth in your long and messy Jupyter notebooks? StickyLand comes to the rescue! With this Jupyter extension, you can drag-and-drop to create sticky cells, auto-run cells, and even build a full-fledged dashboard to interpret your ML models! #CHI2022
Excited to announce Dodrio, an interactive visualization tool designed to help NLP researchers and practitioners analyze and compare attention weights in transformer-based models with linguistic knowledge! Try Dodrio in your browser: https://poloclub.github.io/dodrio/ #ACL2021NLP #NLProc
February 25, 2025 at 4:52 PM
Excited to announce Dodrio, an interactive visualization tool designed to help NLP researchers and practitioners analyze and compare attention weights in transformer-based models with linguistic knowledge! Try Dodrio in your browser: https://poloclub.github.io/dodrio/ #ACL2021NLP #NLProc
Our new preprint "CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization" is live on arXiv! https://arxiv.org/abs/2004.15004 Try our interactive visualization in your browser to learn more about CNNs: http://poloclub.github.io/cnn-explainer/
February 25, 2025 at 4:51 PM
Our new preprint "CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization" is live on arXiv! https://arxiv.org/abs/2004.15004 Try our interactive visualization in your browser to learn more about CNNs: http://poloclub.github.io/cnn-explainer/