Kiki or Bouba? Our work uses vision and language models to explore cognition, providing new insights into classical questions in psycholinguistics. Morris will be presenting it later this month at #NeurIPS2023 - reach out if you'll be around and are curious to learn more!

Generating 3D shapes conditioned on text and auxiliary guidance shapes (within seconds!) is now possible with SPiC·E 🌶️ Very proud of our team - Etai Sella , Gal Fiebelman and Noam Atia! Project page: tau-vailab.github.io/spic-e/

Image captions generated by SOTA models are very impressive, but... suffer from hallucinations, making them unusable for many practical tasks. Our work MOCHa☕️ mitigates hallucinations in an open-vocabulary setup with a reinforcement learning-based approach. Check it out!

כתבה הבוקר בעיתון הארץ על מחקר שלנו שהתפרסם לאחרונה בניוריפס... haaretz.co.il/science/2024-0… With Morris Alper

Morris discussing our work on the radio! 😀

We're releasing the first-ever, pretrained Japanese/English Mamba on the Hugging Face platform. Enjoy!

I will be speaking at @IMVC2024 about our work on sound symbolism in VLMs. If you're in Israel, check it out! (Apr 8, Expo Tel Aviv)

Interactive editing of real images with our ReNoise inversion method 🤩

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