Diffusion models spend the same compute on a blank wall as on a face. But you often know in advance where the detail will be.
Introducing Level-of-Token (LoT) Diffusion: we turn that knowledge into a multiresolution token layout, with fine tokens where detail is needed and coarse tokens elsewhere.
1/9🧵
Very excited to present the new member of the DataComp family: DataComp-VLM!!!
I feel blessed to be a part of such a strong team of researchers from all around the world 🌎🌍🌏
For more details, check out the awesome thread by my dear friend @vishaal_urao below👇👇👇
📣New Paper: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation.
🌐 https://t.co/lvpmhTDLPB
🤗: https://t.co/AEvUNZtefY
A feedforward latent scene decoder for generating explicit triangle-based 3D scenes from video diffusion latents.
3D Scene Graphs: Open Challenges and Future Directions
Dennis Rotondi, Francesco Argenziano, Sebastian Koch, Nathan Hughes, Martin Buechner, Johanna Wald, Lukas Rosenberger Schmid, Daniele Nardi, Abhinav Valada, @duckietown_coo, @fedassa, @lucacarlone1, Kai O. Arras
tl;dr: in title
https://t.co/nUSKl654vn
Very excited to share the outcome of my internship @Google where we propose a new elastic visual tokenization architecture:
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
https://t.co/9d2XuqiKpB
Thread below 🧵👇
Excited and deeply honored to receive the #3D Outstanding Doctoral Dissertation Award! 🏆 Huge thanks to the awards committee and to everyone making 3DV such a blast.
And I couldn't be happier to share this recognition with my long-time friend and colleague @songyoupeng 🙌✨
Presenting M2SVid at #3DV2026 today! We tackle Monocular-to-Stereo Video conversion using a end-to-end inpainting and refinement pipeline.
📍 Poster Session 1 (10:15 - 12:00)
🚀 Code and models are now released!
🔗 https://t.co/PibIzp5RzI
💻 https://t.co/6ZkHc2C7dg…
@3DVconf
Hiring: Student Researcher @ Google Zurich! 🇨🇭
Looking for an EMEA-based PhD student to work on: Efficient 3DGS / Feedforward Models / 3D GenAI.
Start: June 2026 or earlier.
If interested, please reach out with your CV to: [email protected]
📢 Exciting news: The 1st GenRecon3D is coming to #CVPR2026! 🚀
We are exploring how to reconstruct more than what is directly visible using generative priors. Fantastic speaker lineup coming soon.
📍 Website: https://t.co/BJ9YNenIWY
#CVPR#GenAI#3DVision
The next OpenSUN3D workshop and challenge will be held @CVPR 🚀 ✨ #CVPR2026
Website: https://t.co/fUTf397a9F
Paper and challenge deadlines coming soon 🏆🗒️
📄 Paper: https://t.co/sdX59mC6N7
🌐 Project page: https://t.co/8fM8mclJvZ
This is joint work with Fabian Manhardt, Marie-Julie Rakotosaona, Michael Oechsle, Christina Tsalicoglou, Keisuke Tateno, @jon_barron , @fedassa.
#SG2RL returns to @ICCVConference 2025 at Honolulu, Hawai'i 🌴☀️
We call for full papers and extended abstracts on all topics around graphs and scene graphs.
Deadline: 26 June (23:59PT)
Website: https://t.co/e0EJfmZjoh
With our amazing co-organizers: @eadeli@ir0armeni@fedassa
Excited to see our paper "Tokenformer: Rethinking transformer scaling with tokenized model parameters" accepted as a spotlight at #ICLR2025 !
Hope our idea of tokenizing everything can inspire the future of AI.
Paper: https://t.co/0ofQpsudSH
Code: https://t.co/D3rhZzqMwD