Imke Grabe (she/her) (@imkegrabe) 's Twitter Profile
Imke Grabe (she/her)

@imkegrabe

PhD candidate: interaction + interpretability @itukph

ID: 73636728

calendar_today12-09-2009 12:56:56

7 Tweet

32 Followers

112 Following

Jichen Zhu (@jichenz) 's Twitter Profile Photo

We are #hiring. Excited to announce another fully funded PhD position in human-AI interaction at the PXL group at Int’l Telecommunication Union Copenhagen. I'm happy to answer any questions. Know anyone who might be interested? candidate.hr-manager.net/ApplicationIni…

NDIF (@ndif_team) 's Twitter Profile Photo

More big news! Applications are open for the NDIF Summer Engineering Fellowship—an opportunity to work on cutting-edge AI research infrastructure this summer in Boston! 🚀

More big news! Applications are open for the NDIF Summer Engineering Fellowship—an opportunity to work on cutting-edge AI research infrastructure this summer in Boston! 🚀
Rohit Gandikota (@rohitgandikota) 's Twitter Profile Photo

Can you ask a Diffusion Model to break down a concept? 👀 SliderSpace 🚀 reveals maps of the visual knowledge naturally encoded within diffusion models. It works by decomposing the model's capabilities into intuitive, composable sliders. Here's how 🧵👇

David Bau (@davidbau) 's Twitter Profile Photo

Why is interpretability the key to dominance in AI? Not winning the scaling race, or banning China. Our answer to OSTP/NSF, w/ Goodfire's Tom McGrath Transluce's Sarah Schwettmann MIT's Dylan HadfieldMenell resilience.baulab.info/docs/AI_Action… Here's why:🧵 ↘️

Why is interpretability the key to dominance in AI?

Not winning the scaling race, or banning China.

Our answer to OSTP/NSF, w/ Goodfire's <a href="/banburismus_/">Tom McGrath</a> Transluce's <a href="/cogconfluence/">Sarah Schwettmann</a> MIT's <a href="/dhadfieldmenell/">Dylan HadfieldMenell</a>
resilience.baulab.info/docs/AI_Action…

Here's why:🧵 ↘️
Rohit Gandikota (@rohitgandikota) 's Twitter Profile Photo

Why do distilled diffusion models generate similar-looking images? 🤔 Our Diffusion Target (DT) visualization reveals the secret to diversity. It is the very first time-step! And—there is a simple, training-free way to make them more diverse! Here is how: 🧵👇

Why do distilled diffusion models generate similar-looking images? 🤔

Our Diffusion Target (DT) visualization reveals the secret to diversity.

It is the very first time-step!

And—there is a simple, training-free way to make them more diverse!

Here is how: 🧵👇
Imke Grabe (she/her) (@imkegrabe) 's Twitter Profile Photo

Last chance to come find the unicorn at #CVPR2025 Come by ExHall A1 and try our interface #PatchExplorer along so many beautiful artworks. Open until 3pm today. Thanks to Luba Elliott @cvpr for having us. Read more at patch.baulab.info 🦄

Sabrina Osmany (@sabrinaosmany) 's Twitter Profile Photo

Thrilled to present my "Agents" collection at #CVPR2025 2025's AI Art Gallery alongside incredible researchers and artists pushing the frontiers of AI creativity. Thanks to Luba Elliott for curating an exhibition that perfectly captures this transformative moment - a testament to how AI

Thrilled to present my "Agents" collection at <a href="/CVPR/">#CVPR2025</a>  2025's AI Art Gallery alongside incredible researchers and artists pushing the frontiers of AI creativity. Thanks to <a href="/elluba/">Luba Elliott</a> for curating an exhibition that perfectly captures this transformative moment - a testament to how AI