@katherineliu
Senior Research Scientist at the Toyota Research Institute (LBM/CV), previously Robotics PhD at CSAIL/MIT. Excited about embodied intelligence and the intersection of CV/Planning/ML. Opinions my own. Give me all the robots!
Also: if you are interested in working on VLAs/LBMs, my group is recruiting interns! I’m particularly interested in improving 3D reasoning in embodied foundation models. Come find me to chat if this sounds interesting to you!
I’ll be in Seoul for #CoRL2025 this week, helping run the Learning to Simulate Robot Worlds workshop. I'll also be at the TRI booth and the TRI Women and Allies Breakfast. Come say hello or DM me! Looking forward to seeing everyone in person.
We've extended the deadline to August 25th, 2025 🎉 Hope this helps any submissions that didn't quite make it in by the 18th. If you're working on robot simulation please consider submitting!
Are you working on real-to-sim, sim-to-real, learning world models, or using physics based simulators to do interesting robotics tasks? There are 15 days to the submission deadline for our CoRL workshop Learning to Simulate Robot Worlds. More details here simulatingrobotworlds.github.io/submit.html
And thanks to all the organizers for working together to make this a successful workshop! Including
@egavves.bsky.social @cgumbsch.bsky.social @yunzhu-li.bsky.social @zadaianchuk.bsky.social
+ many others!
#CoRL2025 #sim2real #real2sim #robotworldmodels #robotics
Have you been working on simulating worlds for robots?Submit to our workshop! Example topics include: real-to-sim and sim-to-real learning, photorealistic differentiable simulation, and end-to-end learned world models. The submission deadline is 8/18/2025.
simulatingrobotworlds.github.io/submit.html
We’re really excited about the speakers we have lined up, including Animesh Garg (Georgia Tech) @animesh-garg.bsky.social , Daniel Ho (1X Technologies), Hao Su (UCSD), Katerina Fragkiadki (CMU), Yilun Du (Harvard) @yilundu.bsky.social, and Russ Tedrake (TRI + MIT).
We envision this workshop as a forum to bring together researchers from traditionally separate communities: those focused on high-fidelity simulators and those developing learned implicit models.
🚀 We’re pleased to announce our workshop at CoRL 2025: Learning to Simulate Robot Worlds! Workshop website: simulatingrobotworlds.github.io
The workshop aims to cover topics like physics-grounded simulation, photorealistic digital twins, AI-controlled simulators, to learned neural world models.
Come hang out! We ran a similar event at CoRL last year that was really fun.
IT'S THAT TIME AGAIN!!!! Time to wake up early and go watch birds at the @cvprconference.bsky.social #CVBirdWalk
Friday, June 13th, from 7:00 AM to 9:00 AM at the scenic Shelby Bottoms Nature Center & Greenway (1900 Davidson St, Nashville, TN 37206). maps.app.goo.gl/Km8oWJzgVQyo...
Something that really stood out to me this ICRA was the diversity of robots in Expo hall. For a while there I’ve been seeing only humanoids and quadrupeds. This year I saw quadrotors, a cool inverted pendulum, espresso making robots, and more. Special thanks to everyone who brought a weird robot!
📢 Check out the list of accepted papers for Robotics: Science and Systems 2025: roboticsconference.org/program/pape...
📜 You can also find the complete conference program here: roboticsconference.org/program/over...
🌴 We look forward to seeing you at #RSS2025 in Los Angeles June 21st-25th!
At ICRA, I'll be chairing Perception for Manipulation 4, and presenting some new work on generative object shape completion and pose estimation from real images. ICRA is always a blast and I'm excited to see what everyone has been working on.
I'll be at #ICRA2025 and #RSS2025 this year 🎉. Send me event/paper/food recommendations!
Wrote a bit this morning on my own early reflections on teaching this class - in short, ML evaluation has been a neglected sore spot of the field since its inception & the class opened all of us up to embracing the complexity of this problem!
Excited to see this course evolve in future iterations.
I use Scholar Inbox to get really targeted paper recommendations -- I definitely recommend trying it out if you haven't yet!
Computer Vision: Fact & Fiction is now available on YouTube 🙌🏼 I made a playlist for it with the seven chapters. Enjoy this time capsule from two decades ago!
Thanks for the suggestion and your contribution to the community! What year did you organize?
The debaters (Harold Soh, Jeannette Bogh, Nadia Figueroa, Chad Jenkins) did a great job talking strong stances. Watch until the end to hear what they actually personally think. And unsurprisingly, @ken-goldberg.bsky.social was a wonderful moderator!
I personally tuned in (from a laptop -- the room was very crowded) to the third debate ("Generative AI will make a lot of traditional robotics approaches obsolete.") and highly recommend it!
Just discovered the recordings of the debates this year at ICRA. As usual, it was a very popular event. It's easily often the highlight of the conference for me, very cool that they're uploaded! I wish an event of this type was held at every conference.
This podcast, about letting a chatbot + voice clone armed with information about you loose in your personal life, was an uncomfortable listen.
radiolab.org/podcast/shel...
Let's make AI more inclusive.
At @huggingface.bsky.social we'll launch a huge community sprint soon to build high-quality training datasets for many languages.
We're looking for Language Leads to help with outreach.
Find your language and nominate yourself:
forms.gle/iAJVauUQ3FN8...
Just a heads up to everyone: @deep-mind.bsky.social is unfortunately a fake account and has been reported. Please do not follow it nor repost anything from it.
Thanks for the context!
Wonderful blog post by Matt Mason: mtmason.com/the-beetle-r...
Quote from it: “... When humans have to handle things not designed for their hands, it’s all tools! Look at their dentists and surgeons. Look at their watchmakers. ...”
Lots of protein-related answers in this thread right now! I’m an outsider to the field — do the new diffusion-based methods represent a step change in performance, or is it more incremental?
I hadn’t read any weather prediction ones yet — thank you for the link!
We are in the process of editing a SLAM handbook, to be published by Cambridge University Press, with many *stellar* contributors. Part 1 is available as an online draft for public comments. Help us find bugs/problems!
Link to release repo is here: lnkd.in/gZhTkaxb
