Postdoc at Imperial College London. Research in latent disentanglement, geometric deep learning, computer vision, and computer graphics.
Joined February 2022
- Tweets 45
- Following 268
- Followers 487
- Likes 127
14 Photos and videos
Pinned Tweet
Mar 18
It's time to bring 3D meshes into modern machine learning properly! 🛸 Our work solves the non-differentiability of the Exp map on meshes, enabling gradients to flow directly through geodesics. It’s differentiable, GPU-fast, and fully parallelised.
circle-group.github.io/resea…
7
79
685
69,049
Simone Foti retweeted
📣 Deadline Extended – LOGML'26
Due to ICLR conference & NeurIPS deadlines, applications are now open till 10 May'26.
🚀 LOGML @ Imperial College London
📅 13–17 July'26
🎓 Talks
🤝 Projects
🧠 Collaboration
🎉 Networking
🔗 Apply: forms.gle/RjxJHCdKVJF41Vvv7
9
30
3,196
Apr 13
Are you ready for another incredible edition of LOGML 2026? 🇬🇧
While I’m co-organising the school again, I’ll also be mentoring a project alongside Massimiliano Esposito.
Apply now to work with us or any of the other incredible mentors!
📣 Participant Applications Open: LOGML’26, Imperial College London (13–17 July)
A week on geometry/topology ML talks, tutorials, projects & networking.
👩🎓 Students/PhD/Postdocs
💰 Limited fee waivers & travel support
🗓 Deadline: 1 May 2026
🔗 Apply: forms.gle/RjxJHCdKVJF41Vvv7
1
9
508
Simone Foti retweeted
Mar 18
Our #CVPR2026 work Differentiable Straightest Geodesics [circle-group.github.io/resea…] provides exponential maps for 3D meshes allowing to trace geodesics or parallel-transport vectors. With it, we release DiGeo, a PyTorch differential geometry package: digeo.readthedocs.io/. 👇
1
10
95
4,232
Mar 18
It's time to bring 3D meshes into modern machine learning properly! 🛸 Our work solves the non-differentiability of the Exp map on meshes, enabling gradients to flow directly through geodesics. It’s differentiable, GPU-fast, and fully parallelised.
circle-group.github.io/resea…
7
79
685
69,049
Mar 18
🛠️digeo: for easy deployment, we make all of this available with our new PyTorch library for differential geometry on meshes.
Docs & installation: digeo.readthedocs.io
pip-install digeo and be part of the next generation of AI research on 3D meshes! 🚀
1
25
1,126
Mar 18
Huge thanks to the team for making this "straightest" vision a reality: @hippolytever (who developed this for his MSc thesis @ICComputing! 🙌), @Kausta42, Stefanos Zafeiriou, and @tolga_birdal.
#CVPR #CVML #AI #Graphics #ML #PyTorch
15
992
Feb 26
Love Geometry & ML and have a nice research project in mind? 📐🤖
Join us at #LOGML2026 as a mentor! Help a brilliant team turn your project idea into a research success story.
🚀 LOGML26— Mentor applications!
📍 Imperial College London | 13–17 July 2026
Mentor a project team. Attend talks, socials, networking events. 💸 Travel support available.
Deadline: 18 March 2026(AoE)
Apply: logml.ai/apply.html
#LOGML #MachineLearning #SummerSchool
2
11
1,280
Simone Foti retweeted
Feb 24
Our Geometric Neural Distance Fields will be presented at #CVPR2026:
circle-group.github.io/resea….
@CVPR
18 Sep 2025
We present Neural Riemannian Motion Fields (NRMF) as a promising paradigm for generative modeling of articulated motion. Unlike various diffusion based models, NRMF is useful both in generation and in deployment as a prior across tasks: circle-group.github.io/resea…. #CVPR #AI #CVML👇
1
13
75
6,910
Simone Foti retweeted
18 Sep 2025
We present Neural Riemannian Motion Fields (NRMF) as a promising paradigm for generative modeling of articulated motion. Unlike various diffusion based models, NRMF is useful both in generation and in deployment as a prior across tasks: circle-group.github.io/resea…. #CVPR #AI #CVML👇
1
39
190
16,691
17 Jul 2025
Months of planning, and it's over in a flash! Seeing #LOGML come to life with such a fantastic group was worth every bit of effort. The collaborative spirit during the projects was exactly what we hoped for. Immense gratitude to all who came and made the week a huge success. 👏
17 Jul 2025
And that's a wrap on the LOGML 2025 Summer School! 🚀
We’ve been quiet on here, but that’s because we were busy with 100 brilliant minds diving deep into geometry, ML, and social activities. 😉
2
13
559
11 Mar 2025
LOGML 2025 is shaping up to be incredible! 🔥
If you're into geometry & ML, this is your chance to dive deep, meet top researchers, and work on projects that matter—all in London 🇬🇧 with an amazing community.
Trust me, it's as fun as it is inspiring.
Apply now! ⏳👇
6 Mar 2025
🌟Applications open- LOGML 2025🌟
👥Mentor-led projects, expert talks, tutorials, socials, and a networking night
✍️Application form: logml.ai
📅Apply by 6th April 2025
✉️Questions? logml.committee@gmail.com
#MachineLearning #SummerSchool #LOGML #Geometry
1
2
5
1,049
11 Mar 2025
773
22 Jan 2025
💡Excited by geometry & ML like our organizing committee?💡
Mentor at LOGML 2025 and help shape projects that can become top publications. It’s academic, social, and seriously fun—Plus, it’s in London 🇬🇧 (July 7-11) and we’ve got you covered. Apply now 👇👇👇
22 Jan 2025
⭐️Mentor applications open⭐️
We're excited to announce that LOGML summer school will return in London: July 7-11 2025. We are seeking mentors to lead group projects at the intersection of geometry and machine learning. Find out more and apply:
logml.ai
1
9
385
27 Sep 2024
🚨 It's confirmed, "UV-free Texture Generation with Denoising and Geodesic Heat Diffusions" just landed at #NeurIPS2024! No more UV map struggles—just point cloud textures & heat diffusion magic. 🔥 Curious? Keep reading. Oh, and definitely turn up the audio 🎧👇
10
47
312
25,127
27 Sep 2024
Quick hits:
✨Avoid seams, distortions, non-uniform resolution or wasted UV space!
✨Textures are represented and generated directly onto the objects' surface by UV3-TeD.
✨UV3-TeD is a denoising diffusion model (DDPM) based on our attention-enhanced heat diffusion.
1
1
8
1,065