🔥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

💫🏆 Special congratulations to our amazing Prof. Joyce Chai for receiving a 2024 @Umich EECS Outstanding Achievement Award! She was recognized for her sustained excellence and contributions made in teaching, research, and service. cse.engin.umich.edu/stories/2024-e…

钝角

Money can't buy happiness. Just like an H100. H100 = happiness.

🔥 3D-LLMs go brrrr! 🚀 Excited to announce our latest research on scaling 3D-LLM training data to *million-scale* with *dense grounding*. 🌟 Introducing 3D-GRAND: a pioneering dataset featuring 40,087 household scenes paired with 6.2 million densely-grounded 3D-text pairs. 🏠💬

I’m excited to share our work towards densely grounded 3D-LLMs! Check our work if you are looking for a million-scale, densely-grounded 3D-text dataset! Happy to collaborate!

🎉Happy to share my first paper "Multi-Object Hallucination in Vision-Language Models" in #ALVR at #ACL2024! Do VLMs hallucinate more in multi-object scenes? Shortcuts? Spurious correlations? What factors contribute to their hallucinations? 👀 🔗multi-object-hallucination.github.io 🧵[1/n]

Congratulations! Please take some time to rest and I wish we will have more interesting collaborations in the near future. Jianing “Jed” Yang @ CVPR Since it starts from an interesting observation during data curation, any new insights while you are at Meta?

Verry happy to share our new paper, This&That, an dynamic robot video generation model with language and simple gestures conditioning! Moreover, we also propose Diffusion Video to Action (DiVA) model to transfer generated videos to robot actions in the rollout environment.

⚡️ Excited to announce Fast3R: 3D reconstruction of 1000+ images in a single forward pass! Fast3R achieves 251 FPS at its peak. 🔥 Try the demo with your images or video! 🔗 Website: fast3r-3d.github.io 🎮 Demo: fast3r.ngrok.app #CVPR2025 #3D AI at Meta

Thanks AK for sharing! The homepage can be found at: uva-computer-vision-lab.github.io/Frame-In-N-Out/ Thank you to all my coauthors: Xuweiyi Chen Matheus Gadelha Zezhou Cheng Research Work at UVA! Special thanks Xuweiyi Chen for bridging this opportunity.

SAB3R: Semantic-Augmented Backbone in 3D Reconstruction Xuweiyi Chen, Tian XIA, Si.X, Jianing “Jed” Yang @ CVPR, Joyce Chai, Zezhou Cheng tl;dr: MASt3R+distillation->open-vocabulary segmentation+3D reconstruction arxiv.org/abs/2506.02112

We’re officially set up and ready to go at #CVPR2025—swing by booth #1417 and say hi to the Voxel51 team. 👋 We’re showcasing powerful tools and workflows designed to help ML and computer vision teams work faster, smarter, and more accurately at scale. Here’s what you’ll see

Thanks to all of my amazing co-authors Xuweiyi Chen Shoubin Yu Sai Bi Kai Zhang Ziwen Chen Si.X Jianing “Jed” Yang @ CVPR Zexiang Xu Kalyan Sunkavalli Mohit Bansal Michigan SLED Lab Hao Tan!♥️ Wrapped up an amazing year Adobe Research — beyond grateful for this risky journey from an NLP guy