I’m thrilled to start my little book tour at the place where I wrote a good chunk of the book! 📚☕️👩‍💻

The CHI video 🎥 deadline is Sept 18th. To help, check out our lab's "How to Video" guide: docs.google.com/presentation...

We'd love to feature more videos, especially 30 sec previews. Don't be shy in promoting your own work! 🍿

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!

Who is this guy? And what's he doing in Google Street View?!

www.google.com/maps/@47.648...

Now fixed with new post. Thanks Nuno!

With the CHI deadline fast approaching, I'm resharing our lab's resource on making figures for HCI papers: docs.google.com/presentation...

New content suggestions always appreciated. Don't be shy to promote your own work!

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

I have had the incredible privilege to spend my sabbatical at Google Research. What have I been up to? Attempting to make Street View accessible to all! 🌍✨

StreetViewAI is a new, accessible street view prototype using context-aware, real-time AI & voice interaction.

youtu.be/wY_2vfDikkQ

We're launching RampNet, an open-source AI that helps detect curb ramps with near-human accuracy.

The most amazing part? The entire project was conceived of and led by high school student John O'Meara.

🧵 A thread on what we built and why it matters.

A friend posted a photo, sunbathing from Scandanavia a little bit ago, captioned "60 degrees at 60 degrees!" That made me wonder how often that really happens -- where on earth is the temperature the same as the latitude, and how often? I answered that at danyel.github.io/degree-degree

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).

📢 Breaking news: we have extended the Extended Abstract deadline for our ICCV AI+Accessibility workshop to Aug 6th. You've got this 💪🏽!

Send in those submissions: cv4a11y.github.io/ICCV2025/ind...

#ICYMI, two #UWAllen Ph.D. graduates were recognized by @acm.org for their research in #AI #NLP: Ashish Sharma, senior applied scientist at @microsoft.com, and @sewonm.bsky.social, research scientist at @ai2.bsky.social and incoming faculty at UC Berkeley. www.geekwire.com/2025/extreme... #ThisIsUW

This saddens me deeply. I have greatly benefited from working w/extraordinary international students; they have brought me & my lab incredible energy, ideas, & helped create some of the most gratifying & important breakthroughs in my career. They are in fear. Not OK! www.nytimes.com/live/2025/05...

This workshop is organized by Professors Yapeng Tian, Yuhang Zhao, @jonfroehlich.bsky.social and PhD students @chimichurrichu.bsky.social and Yuheng Wu.

📢 We are delighted to announce our ICCV 2025 workshop on "Vision Foundation Models and Generative AI for Accessibility: Challenges & Opportunities"!

Two submission tracks: extended abstracts and full papers—the latter published in the ICCV workshop proceedings.

cv4a11y.github.io/ICCV2025/ind...

[1/2] We've released the code for LegoGPT. Our autoregressive model generates physically stable and buildable designs from text prompts by integrating physics laws and assembly constraints into LLM training and inference.

Code: github.com/AvaLovelace1...
Website: avalovelace1.github.io/LegoGPT/

Double bonus! Makeability Lab PhD student @arnavick.bsky.social (co-advised by Prof Wobbrock) is at #CHI2025 presenting her MS work from Columbia: "'It Brought Me Joy': Opportunities for Spatial Browsing in Desktop Screen Readers." This is research with her MS advisor Prof. Brian Smith. Go Arnavi!

Horrible. So sorry. 😢