Such an excellent (and emotional) reunion! It reminded me once again how lucky I am to know, collaborate, and be friends with these amazing people! 💖 Thx PAVIS IIT !

Thank you all for coming to my talk yesterday at #ECCV2024 where we discussed the lessons learned from evaluating VLMs and designing Molmo. In today's talk, I will discuss limitations still left with VLMs and what we can do about it: **Suite 9 at 2pm** green-fomo.github.io/ECCV2024/

🚀 We’re kicking off our GreenFOMOWorkshop@ECCV2024 with Ranjay Krishna, who will be sharing insights in his talk on "Outperforming Proprietary Multimodal Language Models"!

🌟 Up next, we have Elisabetta Farella at GreenFOMOWorkshop@ECCV2024 on "Unlocking the Potential of Foundation Models in TinyML"! Don’t miss her insights on the future of AI in resource-constrained environments!

Two spotlight talks at the Green Foundation Models Workshop at #ECCV2024! 🌍 First up: “How green is continual learning, really? Analyzing energy consumption in continual training of vision foundation models.”

🚗 The next speaker in GreenFOMO workshop is Jose M. Alvarez with his talk on "Towards an Efficient Use of Foundation Models in Autonomous Driving"! #ECCV2024

📊 Next up in GreenFOMO workshop, Eric Schulz will present "A Light-Weight Benchmark for Large Language Models"! #ECCV2024

Join if you wanna connect with Benedetta Liberatori , and learn about our work on Temporal Action Localisation!

Partial team of GreenFOMOWorkshop@ECCV2024 European Conference on Computer Vision #ECCV2026 Thanks to everyone that has contributed to the event, and we hope to see you in future editions!

🌞 All Hands in Malta! Our team gathered to connect, collaborate, and plan the next steps for driving impact together. Here’s to the teamwork that powers our journey! 💪🌍 #Pattern #Infrastructure #Malta #HorizonEurope

🤖🔍 Want to continually learn vision-language tasks without relying on external data? Check out our latest approach, GaB, now accepted at #WACV2025! It tackles catastrophic forgetting head-on. Learn more: arxiv.org/abs/2411.02210 #AI #MachineLearning

🎉 Paper alert! We present a new deep learning approach to jigsaw puzzle solving 🧩. Instead of pairwise matching, we use conditioned generation to estimate a solution image and solve puzzles as a global assignment problem. sciencedirect.com/science/articl…

🌍 Cities are leading the shift toward zero-emission mobility, but they need stronger EU support! The EU aims for zero road deaths by 2050 and zero-emission urban transport by 2035. How can we get there? 🔗 eurocities.eu/latest/towards… #SustainableTransport #GreenMobility

🎉 Excited to share that our paper "Seeing the Abstract: Translating the Abstract Language for Vision Language Models" has been accepted at #CVPR2025 ! 🚀 Thanks to Federico Girella Ziyue Liu Marco Cristani Yiming Wang for their incredible work! 🙌 Stay tuned!! 📢

🚨 CVPR main conference decisions are out, unlucky? Do not despair! The MULA workshop deadline is March 12, 2025. If you want to experience Nashville and present your work, don’t miss this opportunity! 🎸📅 #CVPR2025 More info here 👇🏻 mula-workshop.github.io

So excited for #CVPR25! We are presenting our paper "Seeing the Abstract: Translating the Abstract Language for Vision Language Models" Join us on June 13, 2–4 PM - Poster #370 Homepage 👉 davidetalon.github.io/fashionact-pag… 🙏 Federico Girella Ziyue Liu Marco Cristani Yiming Wang

What if we stopped treating image classification like a multiple-choice quiz… …and just asked the model: "What’s in this image?" Our paper on open-world classification with LMMs got into #ICCV2025! 🎉🌺 Let’s talk failures, insights, and flipping mistakes 👇