🔥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

Find it surprising that vision-and-language models lack the expert knowledge of the architectural domain? Check out how we adapt these models for localizing 3D scenes in the wild with HaLo-NeRF (presented last week at Eurographics!) 😇

HaLo-NeRF Learning Geometry-Guided Semantics for Exploring Unconstrained Photo Collections Internet image collections containing photos captured by crowds of photographers show promise for enabling digital exploration of large-scale tourist landmarks. However, prior

Folks working on image-caption data, check out our method for quantifying visual concreteness of text!

I will be speaking today at 2pm in the computational cameras and displays workshop at #CVPR (in Arch 204) Come check it out! csiplab.github.io/ccd2024/

Dear #CV #AI folks, a batch of WACV reviewer invitations was sent out today 👇. Please check your inbox (or spam) and consider accepting our invitations! We are targeting 2200+ reviewers and expecting a spike in submissions, and we appreciate everyone's contributions!

🎉 Calling all researchers! 🚀 The countdown is on! ⏳ Round 1 submission deadline for #WACV2025 is just around the corner: JULY 15TH! 🗓️ 🌟 Get those papers ready and submit! 📚✨

Make some noise for ReNoise for getting accepted to #ECCV2024! ReNoise is an inversion method that enables interactive image editing with the recent few-steps diffusion models. More details are on our project page. garibida.github.io/ReNoise-Invers…

Check out Spice-E (that adds structural priors to 3D Diffusion models) at SIGGRAPH this week 🌶️🌶️🌶️

Do multimodal vision and language models encode hierarchical knowledge? Our work (now accepted to ECCV'24!) explores this intriguing question, and we also provide a benchmark for quantifying this property. Check it out at: tau-vailab.github.io/hierarcaps/

Pleased to announce that this was just accepted as an oral presentation at #ECCV2024! Check out our work on emergent hierarchies in vision-language models like CLIP.

Thank you to my amazing students (most of whom are pictured below) and colleagues for two wonderful years at Tel Aviv University! Today is my first official day as an Assistant Professor at Cornell Computer Science and Cornell Tech. Excited and looking forward to the years ahead!

At #ECCV2024 Milan? Join us for our 🤩 ORAL PRESENTATION and POSTER 🤩 ⭐ Emergent Visual-Semantic Hierarchies in Image-Text Representations ⭐ w/ Hadar Averbuch-Elor Presentation: Oct 3rd (9:00 | 5C) Poster: Oct 3rd (10:30 | #148) hierarcaps.github.io

'Mitigating Open-Vocabulary Caption Hallucinations' is accepted to EMNLP 2024! 🎉 t.ly/cBQM0 TL;DR OpenCHAIR: an open-vocabulary hallucination benchmark MOCHa: RLAIF framework for hallucination reduction A great coop with Moran Yanuka Morris Alper Raja Giryes 💔 Hadar Averbuch-Elor

Very excited about this interdisciplinary collaboration led by Rachel and Morris in our group (to be presented in #ICLR2025)!

I am looking for a postdoc. A serious-looking call coming soon, but this is to get it going. Topics include (but not limited to): LLMs (🫢!), multimodal LLMs, interaction+learning, RL, intersection with cogsci, ... see our work to get an idea: yoavartzi.com/pubs Plz RT 🙏

Let it Snow! Animating Static Gaussian Scenes With Dynamic Weather Effects Contributions: • A novel framework for incorporating physically-based global dynamic effects into static 3D Gaussian scenes. • Ensuring realistic scene interaction and collision effects by producing

That's a wrap for #ICLR2025! See you all next year in Brazil! Please all welcome Bharath Hariharan as the new Senior Program Chair! (With Carl Vondrick continuing on as General Chair.)

Excited to share that our latest paper: "InstanceGen: Image Generation with Instance Level Instructions" was recently accepted to #SIGGRAPH2025! InstanceGen tackles the problem of generating images for complex multi-object prompts tau-vailab.github.io/InstanceGen/ 👇🧵[1/7]

I’m looking for PhD students for the 2026 cycle! If you’re #CVPR2025 and think we might be a good fit, come say hi or send me an email with [CVPR2025] in the subject line so that I don’t miss it. #CVPR2025

💥New preprint! WildCAT3D uses tourist photos in-the-wild as supervision to learn to generate novel, consistent views of scenes like the one shown below. Work from Meta AI internship, with @davnov123 Filippos Kokkinos Hadar Averbuch-Elor Tom Monnier (1/5)