Matt Groh (@mattgroh) 's Twitter Profile
Matt Groh

@mattgroh

Assistant professor @NorthwesternU @KelloggSchool | PhD @MIT @medialab | human AI collaboration | computational social science | applied computer vision

ID: 577235600

linkhttp://mattgroh.com calendar_today11-05-2012 15:39:43

2,2K Tweet

2,2K Followers

1,1K Following

Matt Groh (@mattgroh) 's Twitter Profile Photo

Amazing line up of brilliant researchers coming soon to Kellogg School Ryan Institute on Complexity for the AI & Innovation Speakers Series. This year we'll have talks from Michiel Bakker, Julio Ottino, Juan Mateos Garcia, John Horton, and Emma Pierson

Amazing line up of brilliant researchers coming soon to <a href="/KelloggSchool/">Kellogg School</a> Ryan Institute on Complexity for the AI &amp; Innovation Speakers Series. 

This year we'll have talks from <a href="/bakkermichiel/">Michiel Bakker</a>, Julio Ottino, <a href="/JMateosGarcia/">Juan Mateos Garcia</a>, <a href="/johnjhorton/">John Horton</a>, and <a href="/2plus2make5/">Emma Pierson</a>
Jessica Hullman (@jessicahullman) 's Twitter Profile Photo

Decision studies appear in HCI, vis, & AI/ML, but how “good decision” is defined is often ad-hoc. My #CHI2025 talk today will answer Qs like: What's a decision problem? What's the best possible performance on a decision problem? What minimum info do participants need? 1/2

Decision studies appear in HCI, vis, &amp; AI/ML, but how “good decision” is defined is often ad-hoc. 

My #CHI2025 talk today will answer Qs like: 
What's a decision problem? 
What's the best possible performance on a decision problem? 
What minimum info do participants need?  

1/2
Negar Kamali (@n3grain) 's Twitter Profile Photo

I’m at #chi2025 and today I’m presenting our paper on characterizing photorealism and artifacts in diffusion model-generated images (@ 2:10 PM, G318-319) Paper: dl.acm.org/doi/pdf/10.114… With Karyn Nakamura ,Aakriti Kumar, Angelos Chatzimparmpas, Matt Groh and Jessica Hullman

I’m at #chi2025 and today I’m presenting our paper on characterizing photorealism and artifacts in diffusion model-generated images (@ 2:10 PM, G318-319) 

Paper: dl.acm.org/doi/pdf/10.114…

With <a href="/frogspitsimulat/">Karyn Nakamura</a> ,<a href="/aakriti1kumar/">Aakriti Kumar</a>, <a href="/chatzimparmpas/">Angelos Chatzimparmpas</a>, <a href="/mattgroh/">Matt Groh</a> and <a href="/JessicaHullman/">Jessica Hullman</a>
Matt Groh (@mattgroh) 's Twitter Profile Photo

Awesome write up in Kellogg Insight on our paper published at #CHI2025 this week! insight.kellogg.northwestern.edu/article/are-we…

NICO (@nicoatnu) 's Twitter Profile Photo

This Wednesday, NICO is thrilled to once again host Lightning Talks! This term we are lucky to have three amazing researchers from NICO, Kellogg, and McCormick Engineering. Join us in Chambers Hall or online via Zoom. 🗓️ Wed 5/14 at 12pm US Central 🔗 bit.ly/WedatNICO

This Wednesday, NICO is thrilled to once again host Lightning Talks! This term we are lucky to have three amazing researchers from NICO, Kellogg, and McCormick Engineering. Join us in Chambers Hall or online via Zoom.

🗓️ Wed 5/14 at 12pm US Central
đź”— bit.ly/WedatNICO
tal boger (@talboger) 's Twitter Profile Photo

Looking at Van Gogh’s Starry Night, we see not only its content (a French village beneath a night sky) but also its *style*. How does that work? How do we see style? In Nature Human Behaviour, Chaz Firestone & I take an experimental approach to style perception! osf.io/preprints/psya…

Looking at Van Gogh’s Starry Night, we see not only its content (a French village beneath a night sky) but also its *style*. How does that work? How do we see style?

In <a href="/NatureHumBehav/">Nature Human Behaviour</a>, <a href="/chazfirestone/">Chaz Firestone</a> &amp; I take an experimental approach to style perception! osf.io/preprints/psya…
Matt Groh (@mattgroh) 's Twitter Profile Photo

Veo3 represents a paradigm shift in AI capabilities for realistic media that tells provocative, fabricated stories This video + thread offer a quick tutorial of the capabilities and limitations (like malformed text & character consistency) that are easy to creatively bypass

Matt Groh (@mattgroh) 's Twitter Profile Photo

When are LLMs-as-judge reliable? That's a big question for frontier labs and it's a big question for computational social science. Excited to share our findings (led by Aakriti Kumar!) on how to address this question for any subjective task & specifically for empathic comms