This year the Symposium on Geometry Processing (SGP) will include a poster session! Please submit poster abstracts by May 26 to share your work --- we'll be setting them up in the beautiful new MIT Museum . Submission information here: sgp2024.github.io/submit/

Check out Marco's presentation of NVIDIA GTC on how Nvidia shapes next-gen autonomous driving with foundation models!

#CVPR2024 Don’t miss the “Vision and Language for Autonomous Driving and Robotics” workshop!

Check out Yiming’s recent work on building multitraversal dataset for robotics!

Congrats Vincent and co! One of my favorite papers in the year.

Do image generation models know copy rights? Check out our recent work "CopyCat" led by Luxi (Lucy) He Weijia Shi Yangsibo Huang. We conduct a systematic study and propose strategies to protect copyrighted characters.

🚗 Autonomous Vehicles meet Multimodal Foundation Models 🌐 We’re accepting submissions of new, ongoing and previously published work to our #ECCV2024 European Conference on Computer Vision #ECCV2024 workshop until 15 Aug ‘24: mllmav.github.io See you in Milan with your new driving world models and VLMs!

Hmmm.... Conference on Language Modeling

Check out this new exciting work that tackles autonomy with LLMs!

Congratulations Marco, Ed, and co for winning this prestigious award!

DVT accepted to ECCV! Let’s make Vision Transformers great again by removing their noises.

3 posters on copyright/unlearning at the GenLaw workshop tomorrow #ICML2024 The GenLaw Center. Come say hi to my awesome coauthors 🤗 1️⃣ [Copyright in image/video generations]: Fantastic Copyrighted Beasts and How (Not) to Generate Them 🔗 arxiv.org/abs/2406.14526 👩‍🏫Luxi (Lucy) He 2️⃣

The new Italian Foundation on Artificial Intelligence for Industry (AI4I) is looking for a Director! A unique opportunity to shape the R&D AI agenda in Italy and in Europe (I serve as member of the scientific committee). Apply here: ai4i.it/call-for-direc… Fabio Pammolli #AI

Agent-Driver is accepted to Conference on Language Modeling with top 1% reviews (7, 7, 8, 9) among all submissions. We sincerely thank reviewers for providing super constructive comments and helping us improve this paper. We incorporated all feedback from the rebuttal and released a final version:

🚀 Just dropped the code: #InstantSplat! Reconstruct your 3D scenes in seconds. Get it now at github.com/NVlabs/Instant… and start building! ✨ #3DVision #AI #ComputerVision #NVlabs #OpenSource

Our workshop extends the submission deadline to August 25th! Look forward to seeing all great submissions!

OmniRe: Omni Urban Scene Reconstruction About the Project: "We build a dynamic Gaussian scene graph leveraging the collective strengths of different representations: • Vehicles are modeled as static Gaussians, transformed using rigid body transformations to simulate their

Check out our new work (ziyc.github.io/omnire/) on reconstructing in-the-wild scenes with any actor. Ziyu is dedicated enough to bring the framework to six datasets (Waymo, PandaSet, Argoverse2, KITTI, nuScenes, nuPlan). We pack everything as an open-source project DriveStudio

x.com/i/article/1831…

RAM is selected an oral presentation at #CoRL! Paper: arxiv.org/abs/2407.04689 Project: yxkryptonite.github.io/RAM/ Code: github.com/yxKryptonite/R… led by Yuxuan Kuang Junjie Ye Haoran Geng and w/ Jiageng Mao Congyue Deng Leo Guibas He Wang