🔥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

Thanks for sharing AK! U2Seg: a unified framework for Unsupervised Universal image Segment (instance/semantic/panoptic) that consistently surpasses prev SOTAs designed for individual tasks. collaborated w/Dantong Niu Xinyang Han Long Lian Roei Herzig trevordarrell

How can we better unlock LLM reasoning ability? How does code training steer LLMs to produce structured intermediate steps & self-improve? New Year, New Paper 🚀 Check out our systematic survey: How Code Empowers LLMs to Serve as Intelligent Agents arxiv.org/abs/2401.00812

I have good news! We got accepted in #CVPR2024. I would like to thank to my collaborators Barışcan KURTKAYA Hidir Yesiltepe Pinar Yanardag James Matthew Rehg. Looking forward to meeting with new faces in Seattle!

Delighted to share an overview of my lab's eight #cvpr 2024 papers. Thanks to my amazing postdoc Sangmin Lee for spearheading the effort and to our invaluable collaborators AI at Meta Reality Labs at Meta Stability AI Toyota USA. See you in Seattle! @IllinoisCS The Grainger College of Engineering

ZeroShape got accepted to CVPR24! 🥳

Today we are releasing TripoSR in collaboration with @tripoAI. TripoSR is a new image-to-3D model capable of creating high quality outputs in less than a second. Learn more here: bit.ly/3P7bNMn

#ICLR2024 How can we choose meaningful positive pairs for time-series contrastive learning? What about motif similarity? REBAR uses a learned measure that captures motif similarity and achieves SOTA performance. Arxiv: arxiv.org/abs/2311.00519 Github: github.com/maxxu05/rebar

While learning new skills, have you ever felt tired of reading the verbose manual or annoyed about the unclear instructions? Check out our #ECCV2024 work on generating egocentric (first-person) visual guidance tailored to the user's situation! [1/7] Page: bolinlai.github.io/Lego_EgoActGen/

#ECCV2024 Large 2D visual foundation models like DINOv2 and Stable Diffusion have shown impressive capabilities in understanding object semantics. How can we leverage these features for 3D object part segmentation? Paper: arxiv.org/abs/2407.09648

We are excited to introduce Stable Fast 3D, Stability AI’s latest breakthrough in 3D asset generation technology. This innovative model transforms a single input image into a detailed 3D asset in just 0.5 seconds, setting a new standard for speed and quality in the field of 3D

Glad to release SPAR3D, a 0.7-second single-image 3D reconstructor with intermediate point cloud generation! SPAR3D allows for interactive user edits and achieves state-of-the-art performance. Check our project page for details: spar3d.github.io

Extracting structure that’s implicitly learned by video foundation models _without_ relying on labeled data is a fundamental challenge. What’s a better place to start than extracting motion? Temporal correspondence is a key building block of perception. Check out our paper!