It makes me 😭

This is the way Mark! I am encouraging my 30 PhD students and 10 postdocs to draw straws on who can submit. Gotta hit that one million citation marker somehow!

Seems a little unfair given the productivity of your lab. I think they should make exceptions for the very top scholars and cap it at a more reasonable ~50-100 papers. Probably a change.org opportunity here.

Hahah. Indeed! The Google offices in Seattle are so beautiful. This is along the Burke Gilman bike/pedestrian trail along the canal, which connects to the Puget Sound. Feel very fortunate!

Now fixed with new post. Thanks Nuno!

Thanks. Will repost with fixed link!

Thank you Pedro. It has been an incredibly fulfilling project culminating and combining so many different parts of my prior work and built up expertise! 🙏

📄UIST'25 preprint: makeabilitylab.cs.washington.edu/media/public...
🚀 Project page: makeabilitylab.cs.washington.edu/project/stre...

On a personal level, this project was like a sabbatical dream 🦄, I got to reunite with @shaunkane.bsky.social (we first worked together in 2006), collaborate with some incredible Googlers including Alex Fiannaca, Nimer Jaber, and Victor Tsaran, and even write (lots of) code in Google's monorepo 🧑🏽‍💻.

Research challenges ahead:
🧠 Mental models of pedestrian navigation vs. inherent limitations of streetscape imagery
⚠️ Bias towards trusting AI output (even when wrong)
🎧 Interaction design difficulties in creating concise audio feedback
🌐 Improving spatial reasoning and multimodal AI for SV tasks

User feedback from our lab study with 11 blind users:
🚀 "This is a huge leap forward in navigation"
✨ "This is incredible"
😊 "This is going to make a lot of blind people very happy"

A key finding: users overwhelmingly preferred conversing with the AI Chat Agent about the scene & local geography

Thank you Evan. A necessary labor of love. And most certainly a living document that evolves as I and my students continue to learn and grow (and the world changes).