Alex Trevithick

@alextrevith

Research Scientist @NVIDIAAI. PhD @UCSanDiego. 4D Vision, Machine Learning, Generative Models.

alextrevithick.com

Joined October 2020

377 Following

595 Followers

Replies Reposts Media

Alex Trevithick
@alextrevith
Oct 19
Film once. Move the camera later. 🎥 Our video model reconstructs what you see and generates what you don’t. Feed it a rough 4D reconstruction, get back a dynamic world you can explore in real time! Led by the amazing @liyuan_zz. Come see how at #NeurIPS2026!
Liyuan Zhu
@liyuan_zz
Oct 18
Glad to share that World from Motion has been accepted to #NeurIPS2026! We’re releasing the code, model weights and DyCheck reproduction scripts: Code: github.com/GradientSpaces… Model weights: huggingface.co/liyzzz/World-f… See you in Sydney 🌏🇦🇺🐨! #neurips2026 #NVIDIA @alextrevith
Alex Trevithick
@alextrevith
Oct 1, 2025
Come check out our workshop at the intersection of generative models and 3D reconstruction at #ICCV2025! 🏝️
Ethan Weber
@ethanjohnweber
Oct 1, 2025
📢 SceneComp @ ICCV 2025 🏝️ 🌎 Generative Scene Completion for Immersive Worlds 🛠️ Reconstruct what you know AND 🪄 Generate what you don’t! 🙌 Meet our speakers @angelaqdai, @holynski_, @jampani_varun, @ZGojcic @taiyasaki, Peter Kontschieder scenecomp.github.io #ICCV2025
Alex Trevithick
@alextrevith
Jun 14, 2025
🎥 What if 3D capture could gracefully handle moving scenes and varying illumination? 🎯Come see how video models generate exactly the data you need at our poster, SimVS! 📍CVPR, June 14th (afternoon), Poster #60.
1
Alex Trevithick
@alextrevith
Apr 23, 2025
After finishing ICCV reviews this year...
4
Alex Trevithick
@alextrevith
Apr 2, 2025
What's the difference between the oai and google image generators? Giving both of them the same image and prompt "generate this image" Gemini is essentially the identity function whereas oai changes content. Does this indicate continuous encoder for Gemini vs. VQVAE for oai?

Alex Trevithick

Alex Trevithick’s posts