Jeremy Warner

Some late #UIST2023 reflections/pics - super grateful to have UIST in the Bay Area just as I was wrapping up grad school. Always great to meet so many inspirational, thoughtful researchers and enjoy catching up with old friends :)

[3] Rambler: Supporting Writing With Speech via LLM-Assisted Gist Manipulation, presented by @susan_birdy and @jdzamfi, asks how we might construct better dictation-based mobile writing interfaces.

[1] Generating Automatic Feedback on UI Mockups with Large Language Models, presented by Peitong Duan, asks the question: Can LLMs provide useful automatic Heuristic Evaluations of UIs?

A first for me - I have a piece accepted for exhibition in a fine art show! (I’ve been in math art events before, but this is my first in a gallery) It’s rotating with other works on a virtual display at the ARC Gallery in SF, until early June. 🎉

my #CHI24 keynote sketch-notes 🖼️🖌️ thank you native Hawaiian poet and practitioner Kalama Cabigon for the beautiful opening and @katecrawford for the awesome keynote!! @acm_chi

I'm delighted to see that my PhD co-advisor @bjo3rn was inducted into the SIGCHI Academy!! Congratulations, Björn 🥳✨🎉

My team at Apple  is hiring a Senior (or Staff) engineer to work on ML Developer Tools (HCI + ML). Look for candidates with 5+ year industry experience (or PhD with 2+ year industry). This is NOT junior or internship position. Details in image⬇️

Rambler: Supporting Writing With Speech via LLM-Assisted Gist Manipulation paper page: huggingface.co/papers/2401.10… Dictation enables efficient text input on mobile devices. However, writing with speech can produce disfluent, wordy, and incoherent text and thus requires heavy…

Video from this talk is available here: youtube.com/watch?v=I4s6q2…

What if machines could learn to use UIs like humans do: by interacting with apps to explore their functionality? We introduce the Never-ending UI Learner, an app crawler that installs+learns from real apps to continually updates a set of ML models that extract UI semantics.

Hello #UIST2023 - I'll be presenting work w/ @kwkfred & @bjo3rn on interactive, flexible style transfer for vector graphics today at 10:50am in the Venetian room, come check it out! More info here: jeremywrnr.com/vst/

Will be back in SF / the Bay for #UIST2023. 🌷🐕 This was my first time being on an organizing committee as a web chair, and I got to work on the logo with @jeremywrnr . Since it involved generative tools (my research area), I thought I would share a snippet of the process.

Will you be at UIST 2023 in SF? Come meet us at Berkeley! RSVP here: docs.google.com/forms/d/e/1FAI…

Life update: I've graduated from UC Berkeley and will start work at Apple in Cupertino as an ML Engineer on the Video Computer Vision team with @xiaoyiz_uw later this month. Thanks to the many mentors (esp. @bjo3rn), supporters, and friends who helped along the way!

Jeremy Warner’s paper covers Vector Layout Transfer, a tool that provides new techniques for flexible transfer of layouts between visual designs. It provides designers with multiple levels of interactive, semantic layout editing controls. people.eecs.berkeley.edu/~bjoern/papers…

presented our icml 2023 poster and workshop paper on optimizing design layout transfer in hawaii; more here - jeremywrnr.com/vlt/

Had a blast visiting @StanfordHCI yesterday to give a modified variation of my dissertation talk, "Enhancing Visual Media Through Reflection and Composition" — thanks for the great discussions!

Here's a video of my recent dissertation talk at UC Berkeley (including a quick guitar serenade): youtu.be/obdSsjdiEFQ

Congratulations to @jeremywrnr on a great PhD exit talk yesterday. Looking for a researcher at the intersection of HCI and graphics/vision? jeremywrnr.com

I'll be giving my PhD dissertation talk today (4/27) at 11am PST. This is a public, hybrid (in-person/online) talk so if you'd like to join please DM me and I'll send the Zoom link!