Great to see our work (arxiv.org/abs/2401.02460) featured in iNaturalist January highlight — inaturalist.org/blog/89266-ina… on iNaturalist’s impact on iEcology and AI Research!

Our group at Adobe Research is looking for a summer intern to work on 3D shape parsing from images/meshes/volumes. If you know/are a PhD student working in that space, reach out! This is a research-focused internship --publishing findings in the best venues is highly encouraged

Humble to announce my *ONE* and only paper arxiv.org/abs/2401.02460 got accepted :))) Grant Van Horn Subhransu Maji

We have open-sourced the code and data for "Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions" #CVPR2024 at: github.com/cvl-umass/Adap… Also, find the poster and video links at the GitHub repo!

At #CVPR2024 this week presenting AdaptCLIPZS (github.com/cvl-umass/Adap…) at CV4Science (June 18th), MMFM (June 19th) workshops and at the main conference on June 20th evening poster session. Do drop by if you are interested in multimodal models! Grant Van Horn Subhransu Maji

This week I will be attending #CVPR2024 in Seattle! We will be presenting three papers (all in Session 2): * Continuous 3D Words, led by Ta-Ying Cheng, P190 * Generative Rendering, led by Shengqu Cai, P273 * Diffusion Handles, led by Karran Pandey, P281

Check out our new work featured below on measuring geographic disparities in image generations, led by Abhishek Sureddy, Dishant, & Nandhinee Periyakaruppa, along with coauthors Oindrila Saha, Adina Williams, Adriana Romero-Soriano, Polina Kirichenko, Melissa Hall! 🎉

Had a wonderful time working with this great team of students and fellow mentors!!

It was a blast to be at #CVPR2024 meeting old friends and new. Thoroughly enjoyed presenting AdaptCLIPZS (github.com/cvl-umass/Adap…) with the help of Grant Van Horn and Subhransu Maji

Thanks Zhengzhong "Jay" Tu for sharing our work! More details soon

8 papers submitted to daily papers so far today If your a author with at least one indexed paper on HF, submit your paper directly to daily papers: huggingface.co/papers/submit

Thanks for sharing Dreaming Tulpa 🥓👑

That's cool. Create posed and anatomic consistent animals with text-to-3D. "YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals" Project: youdream3d.github.io Paper: arxiv.org/abs/2406.16273… I hope we will get some code soon to try it out!