Great winter school on social robotics, AI and multimedia near to the beautiful Grenoble!

On my way to Nashville for hashtag. #CVPR25; almost ready to dance! We will present "TANGO: Training-free Embodied AI Agents for Open-world Tasks" at the main conference (June 15) and at the Embodied AI Workshop (June 12).

If you are in Nashville and want to catch up, DM me here or via email!

This is insane

Screenshot of the workshop website "Emergent Visual Abilities and Limits of Foundation Models" at CVPR 2025

Our paper submission deadline for the EVAL-FoMo workshop @cvprconference.bsky.social has been extended to March 19th!
sites.google.com/view/eval-fo...
We welcome submissions (incl. published papers) on the analysis of emerging capabilities / limits in visual foundation models. #CVPR2025

Just a reminder that (very) often this is our outcome... and that this short discussion with Nobel prize Ben Faringa is, to me, one of the best I have ever heard about "failures and perseverance": youtu.be/vpPfb6CscyI?...

#KostasThoughts: When communicating with conference organizers, start by assuming good intentions and always keep it respectful. Remember, these are real people, volunteering their time and making personal sacrifices to bring everything together.

TANGO: Training-free Embodied AI Agents for Open-world Tasks Large Language Models (LLMs) have demonstrated excellent capabilities in composing various modules together to create programs that can perform complex reasoning tasks on images. In this paper, we pro...

This is the early version on arXiv: arxiv.org/abs/2412.10402

I am thrilled to share that TANGO (Training-free Embodied AI Agents for Open-world Tasks) finally made it to #CVPR2025!
Super proud of my students F. Ziliotto and T. Campari who made an awesome work. It took two rounds of review, some trouble, and many improvements, but this made the work stronger!

A good review spells out a paper's contributions & strengths/shortcomings targeted for someone who doesn't work on the problem & has not read the paper!

A good review also gives actionable feedback to improve the work regardless of the accept/reject decision.

Happy reviewing!

Ad on research positions and internships at NAVER LABS Europe, Grenoble, France in February 2025

Welcome to NAVER LABS Europe on Bluesky! We chose 'LABS blue' to kickoff our posts & we'd appreciate it if you could share this one widely tinyurl.com/2nt9jdnv 😊 #hiring #jobs #internships

Happy to give a talk very soon in Florence, in a very familiar place ("my alma mater") with some familiar faces, about our recent works in the embodied computer vision field!

#ICLR decisions are out! We have a paper on social navigation (this is an early version arxiv.org/abs/2404.11327). Great collaboration with @galasso.bsky.social and his awesome students from Sapienza Univ of Rome

Still have two missing reviews (that hopefully will be done by heroic emergency reviewers)... I am still against "collective punishment" that would impact other co-authors. But I agree that ghosts are the worst; maybe we could consider individual ban preventing submissions to the next conferences.

Shoutout to all our #CVPR2025 emergency reviewers who stepped up when others couldn’t or wouldn’t! 🫡

Prof. on website vs Prof. in person

Brilliant talk by Ilya, but he's wrong on one point.

We are NOT running out of data. We are running out of human-written text.

We have more videos than we know what to do with. We just haven't solved pre-training in vision.

Just go out and sense the world. Data is easy.

Congratulations to our fresh CS graduates! They both did a great job at the intersection between vision and language.

Calling all ELLIS PhDs & Postdocs!

Join the #ELLISWinterSchool in Brunico 🇮🇹 on Jan 27-31, 2025 for lectures on Multimodal Learning, with a focus: Generative Models, Embodied AI & Sustainability.

Apply via elias-ai.eu/event/ellis-...

#MachineLearning #AI

Congratulations Sara! Well deserved

So true :)

Welcome @stanfordhai.bsky.social to bluesky!

Super excited to be part of this great winter school (in an amazing place)!

Looking at ICLR submissions with the lowest score - What a work of art! 🧵

It is hard to fully grasp the versatility of linear operations:

- Rotation / projection / skewing
- Dimension reduction
- Discrete differentiation
- Kernel diffusion
- Matching
- Readout
- Fourier transform
- Weighted average / expectation
- Permutation
- Counting
- Intersection

Created a #robotics and #vision starter pack. Feel free to suggest yourself or others missing from the list!

go.bsky.app/HcQYMj

Hi, with my group we are doing several things in the embodied AI area...

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, can you add me to the starter pack please? Thanks, Lamberto

This is great! Could you add me to the list please?

At Naver Labs Europe in Grenoble, France, we are searching for talented PhD interns for work on Spatial AI, geometric and robotic foundation models for navigation and manipulation. If you have experience in Embodied AI and are interested, DM me.