supreme clientele

We were really moved by the introduction by jonathan zong 🍊🥄 PHD's advisor, Arvind Satyanarayan, who said interdisciplinary research can be challenging bc it pulls you in different directions & that can come at the cost of depth. But a hallmark of Jonathan’s work is rigor & depth.

.Arvind Satyanarayan also shared that jonathan zong 🍊🥄 PHD helped to shape their MIT lab culture by sharing work-in-progress ideas, which made others feel comfortable sharing their own ideas, in turn, making the lab more collective and less competitive in nature.

Last month, I had a lot of fun giving a lightning talk about some new ideas I'm stewing on regarding generative AI and human agency. It touches on only the first piece of a longer argument we unpack in a recent white paper. youtube.com/watch?v=Do3opA… Summary 🧵👇

Spend the day w/an MIT CSAIL PhD student working in data visualization: bit.ly/3AlY3Zw

Had a blast discussing how mechanistic interpretability can improve AI safety at #NEMI2024 🤖 Thanks to David Bau, Max Tegmark, Koyena Pal, Kenneth Li, Eric J. Michaud & @BrinkmannJannik for bringing us together! And to my amazing co-panelists Hadas Orgad & David Krueger!

Excited to be starting MIT CSAIL! If you’re in the Cambridge area, feel free to reach out :-) would love to chat developer information management 🤖

Doing my PhD alongside jonathan zong 🍊🥄 PHD has been such a wonderful learning experience that I can’t imagine how cool it would be to have him as an advisor

Tired of bad alt text? Want screen reader-friendly diagrams? Join our MIT study on a diagram accessibility tool! Blind and low-vision Mac/Windows screen reader users needed. Test prototypes via Zoom (100 mins) and get $60. Sign up: forms.gle/YhhiChmxC24uzw… Please share!

I’m so enormously grateful and proud of our BostonVIS students! Within hours of #ieeevis going virtual, they jumped on Zoom and brainstormed a set of satellite events. Two days later, we’re delighted to announce an initial schedule!! RSVP + updates: bostonvis.org

In an age of LARGE models, how do we support people in making them SMALLER? Compress and Compare is an interactive visual system tackling this question! Check it out tomorrow IEEE VIS w/ Venkat Sivaraman Yannick Assogba Donghao Ren Dominik Moritz Fred Hohman Apple 🍎machinelearning.apple.com/research/compr…

Code Shaping just won the Best Paper Award at #CHI25!!! 🥳🎉 Thanks for the recognition! If you've read the paper or watched my presentation, I’ve put together some insider scoops and untold stories from the making of this project 😉 👉 ryanyen2.github.io/blog/code-shap…

#CHI2025 paper on human–AI alignment! 🧵 Models can learn the right concepts but still be wrong in how they relate them. ✨Abstraction Alignment✨evaluates whether models learn human-aligned conceptual relationships. It reveals misalignments in LLMs💬 and medical datasets🏥.

I’ll be at #CHI2025 🌸 If you are excited about interpretability and human-AI alignment — let’s chat! And come see Abstraction Alignment ⬇️ in the Explainable AI paper session on Monday at 4:20 JST

“I’m working on a big idea!” But… what is a big idea, really? And are we just telling ourselves that to feel better about not publishing? Or superior than others? Some personal reflections on deep work and big idea: 🔗 ryanyen2.github.io/blog/big-idea/

new charting library is baking