Very exciting news!! Our most recent paper is out! We train a llama model on a folder with jpeg files. 🦙—>📂 We found very exciting potential when doing this! If you are interested see the thread, and check our paper!

Very exciting news!! Our most recent paper is out! We train a llama model on a folder with jpeg files. 🦙➡️📂 We found very exciting potential when doing this! If you are interested see the thread, and check our paper!

This is quite remarkable, being able to ~talk file formats is a massive jump ahead for so many domains

We are proud to note that Juan C. Pérez Juan Camilo Perez, a member of our lab, has been highlighted as an Outstanding Reviewer at #CVPR once again!! ⭐️ Congrats, Juan C, on your continued excellent efforts!

🚀 Exciting News! 🚀 KAUST Computer Vision Lab (IVUL) Paper accepted at #ECCV2024! 🎉📚 🌟DATENeRF: Depth-Aware Text-based Editing of NeRFs🌟 Authors: Sara Rojas Martinez, Julien Philip, Kai Zhang, Sai Bi, Fujun Luan, Bernard Ghanem, Kalyan Sunkavalli. Project page: datenerf.github.io/DATENeRF/ European Conference on Computer Vision #ECCV2026 🇮🇹

Exciting News! 🎉 My paper got accepted at #ECCV2024! Huge thanks to my Adobe and KAUST collaborators! 💌 DATENeRF: Depth-Aware Text-based Editing of NeRFs 💌 Sara Rojas Martinez, Julien Philip, Kai Zhang, Sai Bi, Fujun Luan,Bernard Ghanem , Kalyan Sunkavalli datenerf.github.io/DATENeRF/

Proud to be part of this list of Outstanding Reviewers at ECCV!

Ever noticed how one scene seamlessly transitions into another in films? That’s a match-cut—a subtle yet powerful cinematic trick. Our MatchDiffusion, generates two videos from text prompts, designed to form a seamless match-cut—effortlessly and training-free. 🎥✨ 1/n

A beautiful effect that is difficult to describe in simple words. I still find it hard to believe this can be achieved w/o fine tuning. A fantastic (and apparently inherent?) property of diffusion models to be further exploited. Proud to have been part of this project!

Some exciting news to share: - In November, I successfully defended my thesis and earned my PhD in Computer Science from KAUST. - I started a new role as an AI Research Scientist at Meta in London, focusing on Generative AI. I'm deeply grateful to everyone who supported me!

Happy to introduce our new CVPR paper—Pow3R: Empowering Unconstrained 3D Reconstruction with Scene and Camera Priors : arxiv.org/pdf/2503.17316 Inspired by the amazing DUSt3R, which reconstructs 3D from just two unposed images, we explored: (1/n)