🧵1/10 Excited to share our #SIGGRAPH paper "MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills" 🌟
We explore how to make MLLMs operation-aware by solving visual puzzles and propose a procedural framework for image retouching
#MLLM

Queer in Robotics - Queer in Robotics - ICRA 2025 Event Summary The Queer in Robotics event at ICRA Diversity Day aims to build an inclusive community for queer students, researchers, and practitioners. Queer in AI’s demographic survey reveals that m...

We are pleased to announce that Queer in Robotics is hosting an event at the 2025 IEEE International Conference on Robotics and Automation (ICRA) Community Building Day on May 21st, 2025!

For more information, check out the information on our website:
sites.google.com/view/queerin...

Robots are widely marketed as "time-saving" devices. This efficiency-based perspective makes sense for managers in workplaces, but what about our choices at home?

I've learned a lot researching with this interdisciplinary team! Here is a preview of our project (graphic by @wolfchirp.bsky.social):

Why Automate This? Exploring the Connection between Time Use, Well-being and Robot Automation Across Social Groups Understanding the motivations underlying the human inclination to automate tasks is vital to developing truly helpful robots integrated into daily life. Accordingly, we ask: are individuals more incli...

See our paper + website for details:
🌐 arxiv.org/abs/2501.06348
🤔 robin-lab.cs.utexas.edu/why-automate...
This work could not happen without my amazing collaborators Leona Pang, Sanjana Srivastava, @drfeifei.bsky.social, Samantha Shorey and Roberto Martín-Martín
(5/5)

Interactive Tool screenshot

We open-sourced the data + built an interactive tool for the community to explore trends and guide future robotics research. We hope the community can use it to guide the next tasks to address (4/5)

We also observe trends by income and gender:
👩Women would prioritize automating stressful tasks
👨Men focus on automating tasks they find less enjoyable
💰Mid-income individuals would prioritize automating tasks with low enjoyment and meaning. (3/5)

We cross-analyzed 3 datasets,BEHAVIOR-1K, ATUS, ATUS-WB, to uncover trends:
🕒 Time spent on tasks isn’t the main driver! Feelings like happiness and pain are stronger predictors of automation preferences. (2/5)

The image illustrates the evolution of cleaning tasks, balancing time (ATUS) and well-being (ATUS-WB). A central figure considers two options: Manual Labor (vacuum cleaner) and Automated Labor (robotic vacuum), connected by an orange arrow labeled B1-K.

🤔What tasks do we want robots to handle? Are these preferences based on saved time or feelings we associate with the tasks?

Introducing Why Automate This?—a study exploring automation preferences across social groups, using feelings & time-spent as key factors. 👇 (1/5)

Here we grow again. Introducing my 2nd AWESOME #ComputerVision Starter Pack.

Missed you? Let me know in the thread.

go.bsky.app/Gjcs339

Hi Kosta👋🏻, could you add me?

Proud to be part of this small but mighty group - let me know if I missed you or any women to add!

go.bsky.app/BuDHCYF

Hi ☺️👋🏻!

Hi! I'm a roboticist too! I work on perception for robotics!

Queer in Robotics Purpose

Hello, Bluesky! 🌈🤖 Thrilled to introduce Queer in Robotics! We're building a welcoming, safe space for queer roboticists and shining a light on queer issues in robotics. Join us! 💫
sites.google.com/view/queerin...