Zijie Jay Wang

Safety researcher @OpenAI 🤖 | ML PhD @GeorgiaTe 🐝 | Researching human-AI interaction 🔍 | Prev. intern @GoogleAI @Apple @MSFTResearch 🌱 | @UWMadison '19 🦡

[Zijie Jay Wang @Jay4w]

Today we're sharing updates that help ChatGPT better recognize context in sensitive conversations and respond safely in rare but important cases. We built these improvements with input from mental health experts, grounding the work in clinical expertise.

[Declan Grabb, MD @declangrabbmd]

sharing out new work that helps ChatGPT better recognize context in sensitive conversations and respond safely in these complex/nuanced scenarios-- both within long conversations and across separate conversations!

see blog post for details: https://t.co/SHAm6318dp

[Zijie Jay Wang @Jay4w]

Read more in our blog post: https://t.co/xlXYz8Hefn

[Zijie Jay Wang @Jay4w]

Today we're sharing updates that help ChatGPT better recognize context in sensitive conversations and respond safely in rare but important cases. We built these improvements with input from mental health experts, grounding the work in clinical expertise.

[Cameron Raymond @CJKRaymond]

one of my top 3 most used internal tools

[Boaz Barak @boazbaraktcs]

I have found Euphony so useful internally! Glad it's now open source!

[Zijie Jay Wang @Jay4w]

https://t.co/0wt9skM97W

[Zijie Jay Wang @Jay4w]

Try Euphony to visualize your chat data and codex sessions!

[OpenAI Developers @OpenAIDevs]

Introducing Euphony, an open-source tool for visualizing chat data and Codex session logs.

Paste in a public URL or upload a local file, and Euphony turns the raw data into an easy-to-browse view. It supports translation, filtering, editing, and more.

[GaTech CSE @GTCSE]

#CHI2025 began this past weekend where alum Zijie (Jay) Wang received an Outstanding Dissertation Award! It is the latest accolade in a career of achievement for @Jay4w that you can learn more about in the 🔗👇!

Congratulations on the honor, Jay! 🥳🏆

https://t.co/iox34WcB27

[Zijie Jay Wang @Jay4w]

Incredible honor to be recognized with ACM SIGCHI Outstanding Dissertation Award. Deepest thanks to all my collaborators and mentors—this wouldn’t have been possible without your support and guidance! ❤️

[ACM SIGCHI @sigchi]

🎉 We're delighted to announce the recipients of the 2025 ACM SIGCHI Awards! Congratulations to these incredible awardees!

[Zijie Jay Wang @Jay4w]

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://t.co/zvdusVu3In

[Upol Ehsan @UpolEhsan]

All AI systems make mistakes.

🧐 What if users could leverage AI flaws to understand it & take informed actions?

🚀 Our #CSCW2024 paper on Seamful XAI offers a process to foresee, locate, & leverage AI flaws—boosting user understanding & agency.

But why should you care?⤵️
1/n

[Parul Pandey @pandeyparul]

Such a great use case - When you need recommendation letters for a visa, job, or academic purposes, this tool - (RecRec )makes it easier by finding the most suitable writers who are already familiar with your work through paper citations - by @Jay4w

[Zijie Jay Wang @Jay4w]

Shout out to @gneubig for the inspiration!! 🙌

https://t.co/gc85ceEFFc

[Graham Neubig @gneubig]

Researchers often have to ask for recommendation letters for visa/job applications, etc.

I wrote a script that allows you to find who cites your papers frequently to create a list of potential letter writers: https://t.co/96nDCt0epQ

Hope it's helpful, improvements are welcome!

[Zijie Jay Wang @Jay4w]

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://t.co/kyKk4Rpssd

#PhDLife

[Zijie Jay Wang @Jay4w]

RecRec is open-source and available at https://t.co/DVAxiyyyO2.

Feature requests and feedback will be highly appreciated!

[AK @_akhaliq]

Transformer Explainer

Interactive Learning of Text-Generative Models

discuss: https://t.co/p1GMsyhsEI

Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2 model. Our tool helps users understand complex Transformer concepts by integrating a model overview and enabling smooth transitions across abstraction levels of mathematical operations and model structures. It runs a live GPT-2 instance locally in the user's browser, empowering users to experiment with their own input and observe in real-time how the internal components and parameters of the Transformer work together to predict the next tokens. Our tool requires no installation or special hardware, broadening the public's education access to modern generative AI techniques.

[Tianqi Chen @tqchenml]

WebLLM based RAG playground in browser

[Zijie Jay Wang @Jay4w]

@domoritz We used gte-small for the RAG Playground demo! The embedding quality is decent, with the quantized model weight coming in at only ~34MB. Depending on how you chunk your paper text, I guess the embeddings will be a few MBs.

https://t.co/ADRKxowUpE

[Zijie Jay Wang @Jay4w]

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://t.co/LkU63AaPDf

#SIGIR2024

[Zijie Jay Wang @Jay4w]

MeMemo adapts the fast KNN search HNSW to browsers.

With #WebLLM, we envision MeMemo as a cornerstone for future on-device LLM apps!

Thanks to @PoloChau, @GTCSE, @ApacheTVM!

📘 Paper: https://t.co/8KdnlPiIcJ
💻 Code: https://t.co/MyEdfZF2A3
🚀 Demo ⤵ https://t.co/hiuFLtPXU0