Mauro Comi
@mauro_ai
Research Intern @GoogleDeepMind || PhD student in Machine Learning, 3D Computer Vision, and Robotics || https://maurocomi.com
Grateful to be starting my second internship as a Student Researcher at @GoogleDeepMind! I'm having a wonderful time at GDM and I'm excited to keep collaborating with such brilliant researchers! 🥳
Help support growth in the African AI ecosystem and in the process learn a lot, meet interesting people and have fun! Mentorship commitments are flexible and require as little as an hour a month!
🌍 Become an Indaba Mentor! We're inviting mentors with diverse skills, backgrounds, and perspectives to help grow the African machine learning community. Share your expertise in areas such as research, careers, presentations, and more — on your schedule. 💡 1-hour virtual…
For folks in the @siggraph community: You may or may not be aware of the controversy around the next #SIGGRAPHAsia location, summarized here: cs.toronto.edu/~jacobson/webl… If you're concerned, consider signing this letter: docs.google.com/document/d/1ZS… via this form docs.google.com/forms/d/e/1FAI…
Join experts Yuval Tassa from @GoogleDeepMind and Miles Macklin from NVIDIA at #GTCParis to learn about Newton, an open-source, extensible physics engine for robotics simulation, co-developed by Disney Research, Google DeepMind and NVIDIA. Gain insights into breakthroughs in…
On my way to Singapore for #ICLR2025 ! Looking forward to discussing generative video models and how to make them more controllable. We will also be presenting CubeDiff (cubediff.github.io) on Friday afternoon. Stop by and say hi :)
Perception Encoder: The best visual embeddings are not at the output of the network "we find that contrastive vision-language training alone can produce strong, general embeddings for all of these downstream tasks. There is only one caveat: these embeddings are hidden within the…
We’re kicking off the 3D Deep Learning Reading Group again! 🎉 Next session: Mesh-Up 📅 Wednesday 9th April at 09:30-10:30 AM London time GMT+01 Join the Slack channel of the reading group to add calendar invites and stay up to date with the sessions: 3d-deeplearning-rg.github.io
🚀 3D Deep Learning meets the physical world! Our survey on Neural Fields in Robotics looked at over 200 papers covering real-world applications - autonomous driving, manipulation, and more. We provide key takeaways and outline open challenges in each area. Feedback appreciated!
How do we represent 3D world knowledge for spatial intelligence in next-generation robots? We recently wrote an extensive survey paper on this emerging topic, covering recent state-of-the-art! 🦾 🚀 Check it out below. Feedback/Suggestions welcome! 📖arXiv:…