Marcus Brubaker

High-fidelity 360s are crucial for generating 3D environments. This work, led by @Dazitu_616, "solves" 360° generation with a simple, scalable architecture, achieving remarkable 3D consistency. Check out the thread and website for an interactive viewer.

📢📢📢 360Anything I am excited to announce this new project, which to me represents the apex in geometry free novel view synthesi for world models. No triangles/splats!! No camera poses!! yet you get a whole world to navigate!

This was a really fun project to see come together, great work Ziyi!

Checkout some really cool work by @Dazitu_616 with me and the @GoogleDeepMind team in Toronto. Turn perspective images and video into immersive 360s!

There's still time to apply to join us at GDM in Toronto as a Student Researcher! We are reviewing applications now though, so apply soon to be considered.

Our team at Google DeepMind in Toronto is hiring student researchers for 2026 to work on cutting-edge vision research, focusing on both generative models and scene understanding. Come work with us! Apply at: forms.gle/qTEbEfwwQnModV…

🎉Excited to present CryoSPIRE (Scaffold Part-Aware Mixture of Gaussians) in #NeurIPS2025! I will be in Mexico City, happy to chat!! Grateful to my supervisors @fleet_dj @marcusabrubaker and @DaveLindell Paper: arxiv.org/abs/2506.09063 Webpage: shekshaa.github.io/CryoSPIRE/ 🧵[1/7]

We at TMLR are proud to announce that selected papers will now be eligible for an opportunity to present at the joint NeurIPS/ICML/ICLR Journal-to-Conference (J2C) Track: @TmlrOrg/tmlr-joins-neurips-icml-iclr-journal-to-conference-track-937a898eab3d" target="_blank" rel="nofollow noopener">medium.com/@TmlrOrg/tmlr-…

Thrilled to announced that at #ICCV2025 we will host the first workshop on 𝐆𝐞𝐨𝐦𝐞𝐭𝐫𝐲-𝐅𝐫𝐞𝐞 𝐍𝐨𝐯𝐞𝐥 𝐕𝐢𝐞𝐰 𝐒𝐲𝐧𝐭𝐡𝐞𝐬𝐢𝐬 𝐚𝐧𝐝 𝐂𝐨𝐧𝐭𝐫𝐨𝐥𝐥𝐚𝐛𝐥𝐞 𝐕𝐢𝐝𝐞𝐨 𝐌𝐨𝐝𝐞𝐥𝐬 geofreenvs.github.io a.k.a. "3D Computer Vision in the era of Video Models" 😅

📢Interested in doing a PhD in generative models 🤖, AI4Science 🧬, Sampling 🧑‍🔬, and beyond? I am hiring PhD students at Imperial College London @ICComputing for the next application cycle. 🔗See the call below: joeybose.github.io/phd-positions/ And a light expression of interest: forms.gle/6m2rbfFf96D8nu…

@bose_joey @imperialcollege @ICComputing Congratulations!

🎉Personal update: I'm thrilled to announce that I'm joining Imperial College London @imperialcollege as an Assistant Professor of Computing @ICComputing starting January 2026. My future lab and I will continue to work on building better Generative Models 🤖, the hardest AI4Science applications in computational biology 🧬and chemistry 🧪, and also a sprinkling of Deep Learning theory 📚 that supports these goals.

@CSProfKGD OpenReview can already make the matching process much better. The NeurIPS process isn't perfect but it's definitely better.

Overall, I think the move from CMT to OpenReview was a great decision. Now if only we can improve the paper-reviewer matching system!

I’ve been through many conference decision releases. The @ICCVConference #ICCV2025 rollout was by far the smoothest. Decision, metareview & reviews released in a single email. HUGE shoutout to the program and technical chairs 💪 And don’t forget your AMAZING publicity chairs 😉

@taiyasaki Sorry to hear that. Hope the little one recovers quickly!

Afraid I am cancelling my #CVPR2025 trip… Newborn has an infection and admitted to the paediatrics ward. Enjoy Nashville

Vector research internships are a great way to launch your career in AI. Apply and think carefully which faculty are most aligned.

Ever wish you could turn your video generator into a controllable physics simulator? We're thrilled to introduce Force Prompting! Animate any image with physical forces and get fine-grained control, without needing any physics simulator or 3D assets at inference. 🧵(1/n)

@hugo_larochelle Congratulations and good luck! Looking forward to see what comes next.

Today is my last day at Google. I started over 8 years ago, with a mandate to build a team doing bleeding edge AI research from Montreal, in what would be the first big tech AI research lab in the city. These years led to countless amazing scientific contributions from my team, to several initiatives nurturing the Montreal AI ecosystem, and to many new invaluable friendships across the globe at Google. It is with a heavy heart that I say goodbye, but I know I’m leaving behind an exceptionally strong Google DeepMind group in Montreal for which its best accomplishments are still ahead. There are too many people to thank, but I can’t pass on thanking Samy Bengio and @JeffDean who first believed in me and the opportunity of building a research lab in Montreal. I’m still working on determining the details of my next chapter, but certainly it will be grounded in my continuing motivation to leverage and make the most out of our enormous and talented local AI ecosystem.

📢📢📢 SFU (Vancouver) is re-opening PhD applications for students seeking different arrangements due to the current political climate. Condition: you must be holding an offer from a US university that ranks in the top-50 (worldwide). **Please** do not email me otherwise.

@roydanroy @pcastr I'm not sure how easily quantifiable some things are but even without that anything more explicit would be an improvement over the current state of affairs.

@marcusabrubaker @pcastr I have argued that author contribution statements must be zero-sum. That is, one needs to split 100% across each category. Writing: 80% X, 20% Y. Otherwise it is meaningless and subject to inflation.

i get first author equal contribution. i get senior author equal contribution. but *second* author equal contribution?? 🤣

📢 Introducing a geometry-aware diffusion model for 3D scene inpainting! TL;DR: We condition a diffusion inpainter on a set of coordinate-aligned reference-based cues derived from the scene geometry to autoregressively inpaint a set of images. 🖼️✨ (1/7)