🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

MASt3R-SLAM code release! github.com/rmurai0610/MAS… Try it out on videos or with a live camera Work with Eric Dexheimer*, Andrew Davison (*Equal Contribution)

AnySense is built to empower researchers, engineers, and developers with better tools for sensor-based AI. Our code is fully open-source and can be found on Github: github.com/NYU-robot-lear… Website: AnySense.app

Big congrats to Vivian Shen for winning the Three Minute Thesis #3MT competition at Carnegie Mellon University. She'll be on the job market next year... Three Minute Thesis CMU School of Computer Science @CMUHCII CMU Robotics Institute

Holograms that you can Grab. #CHI2025 FlexiVol: a Volumetric Display with an Elastic Diffuser to Enable Reach-Through Interaction. F Video: youtu.be/4wwKOXxX9Ck preprint: hal.science/hal-04981007v1 doi: doi.org/10.1145/370659… UPNA - Universidad funded by European Research Council (ERC) InteVol

Yes, your iPhone already has a projector—using invisible light! 📱✨ In my latest research at ACM CHI Conference, we repurpose its LiDAR dot pattern as a visual marker, enabling paired AR experiences without any online communication or pre-registration.

We interact with physical objects every day, yet we can’t control how they feel to us. In our #CHI2025 paper, we propose a WEARABLE interface that empowers users to adjust perceived MATERIAL PROPERTIES. Check it out: interactive-structures.org/publications/2…

Excited to share code & models for FastVLM — our blazing-fast Vision-Language Model appearing at #CVPR2025 Run it on-device with inference code optimized for Apple Silicon using #mlx. Code: github.com/apple/ml-fastv… Updated paper & results coming soon. Stay tuned! 👀

Kicking off a new podcast/blog series walking you though how to build a smartwatch in 2025! First episode is on picking a chip, with an interview and dive into my box of ancient products youtube.com/watch?v=umQ39B…

Out now in Chemical Science! Give it a read if you're interested in molecular design, synthesizability, and/or organic electronics! Co-authors: James Damewood, Juno Nam , Kevin Greenman , Avni Singhal , and RGB Lab @ MIT. pubs.rsc.org/en/Content/Art…

Laser Dance, the mixed reality obstacle game from Cubism's creator, will launch in early access this fall on Quest 3. Details here: uploadvr.com/laser-dance-ea…

Fun new paper at #SIGGRAPH2025: What if instead of two 6-sided dice, you could roll a single "funky-shaped" die that gives the same statistics (e.g, 7 is twice as likely as 4 or 10). Or make fair dice in any shape—e.g., dragons rather than cubes? That's exactly what we do! 1/n

Tomorrow I'll talk at the #ICRA workshop on "Enhancing human mobility" on recent 3D human estimation works from our group led by Gerard Pons-Moll. And I've released PyTorch training code for NLF, and more tools. Here's a preview of the even stronger upcoming DINOv2-ViTg-based NLF

I’m hiring students who are interested in multimodal generative AI / UI agent-related topics. My current vision is that we should have human-in-the-loop controllable UI generation models that adapt UIs to the diverse needs of designers and users + enhance human creativity.

Project led by Jan Held and Renaud Vandeghen in collaboration with Adrien Deliege, Abdullah Hamdi, Silvio Giancola, Anthony Cioppa, Andrea Vedaldi, Bernard Ghanem, Andrea Tagliasacchi, Marc Van Droogenbroeck The Triangle is Dead! Long Live the Triangle! (credit: Alec Jacobson)

Anyone interested in 3D printing some funky dice—like a "fair dragon" which can land in three different ways, or a single die equivalent to to 2D6? We've now put printable STL files online: cs.cmu.edu/~kmcrane/Proje… More info here: hbaktash.github.io

What if a Transformer could render? Not text → image. But mesh → image — with global illumination. No rasterizers. No ray-tracers. Just a Transformer without per-scene training. RenderFormer does exactly that. #SIGGRAPH2025 🔗microsoft.github.io/renderformer

Well... a new chapter is starting! I'm over the moon to be joining MIT EECS / MIT CSAIL as an Assistant Professor, starting Fall 2026. 🌕 (1/5)

📢Code Release of Pixel3DMM 📢 Looking for a robust and accurate face tracker? Our state-of-the-art tracker handles challenging in-the-wild settings, such as extreme lighting conditions, fast movements, and occlusions. 👨‍💻github.com/SimonGiebenhai… 🌍simongiebenhain.github.io/pixel3dmm/

My students put up a banner on our building announcing my tenure! I don't know if they planned it to be the first thing almost entering CMU sees. 😅 They also put stickies with my random tweets all over the building. I didn't realize I had made so many dad jokes on Twitter.

EgoPressure at #CVPR2025 2025 (Highlight)! w/ Yiming Zhao , Taein Kwon , Marc Pollefeys , Christian Holz 🌍 Project page: yiming-zhao.github.io/EgoPressure/ 📰 Paper: openaccess.thecvf.com/content/CVPR20… 📍Come visit us during our poster session in ExHall D Poster 149, 15 Jun, 16:00 CDT — 18:00 CDT!