Alex Trevithick

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

[Ronak Malde @rronak_]

Today, @MichaelElabd, @QuantumArjun, and I are excited to announce Trajectory.

We are a research lab and product company building the platform for Continual Learning.

Our platform unlocks the signal already sitting in product usage, so companies can continuously post-train large-scale agentic models that outperform the frontier. @trajectorylabs

We’ve raised $15M from @Conviction, @BessemerVP, @radicalvcfund, @jeffdean, @drfeifei and more.

We’re partnering with some of the best AI-native companies: @ClayRunHQ @Harvey, @DecagonAI, @mercor_ai, @RogoAI to power their agentic systems, some of which we are already in production with.

We’ve brought together a world class research team from DeepMind, OpenAI, Apple, Meta Superintelligence, Amazon AGI, Scale AI, and an elite product team from Stripe and Figma.

AI will never again start on day one. Every correction, every retry, every edit will make products smarter. This is Continual Learning.

[Ruiyi Wang 王睿仪 @RuiyiWang153]

Collecting demos for training robots is expensive 💸. Each demo is paired with a one-line label that throws away the spatial relations, subgoal structures, etc. The rich pixel information is there — we're just not fully using it.

🚀Introducing DeMiAn: Dense Multi-aspect Annotation as a scaling lever for robot policy learning.

📈 +5 pts on RoboCasa365 tasks, +9 pts on unseen composite tasks
⚡ ~62% less compute at 1M-clip scale (~1.3 × 10²⁰ FLOPs saved)
🤖 Zero new demonstrations collected

[Liyuan Zhu @liyuan_zz]

🚀Tired of floaters, flickering, and blur in 3DGS? We introduce a geometry-informed video generator that refines 3DGS renderings in the wild. 🎥✨

We let the video model actually "see" the rendering process using a Gaussian Primitive buffer. #CVPR2026 @CVPR
Project page: https://t.co/IjE8h0QVuS

🔥 Highlights:
✅ Geometry-Buffer-conditioned video generator
✅ Refines optimization-based & feed-forward 3DGS
✅ Novel artifact simulation pipeline
✅ Highly efficient bidirectional processing ⚡
Thread 👇

[World Labs @theworldlabs]

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU.

RTFM renders persistent and 3D consistent worlds, both real and imaginary.

Try our demo of RTFM today!

[Alex Trevithick @alextrevith]

Come check out our workshop at the intersection of generative models and 3D reconstruction at #ICCV2025! 🏝️

[Ethan Weber @ethanjohnweber]

📢 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

https://t.co/LvONYIK3dz
#ICCV2025

[Sherwin Bahmani @sherwinbahmani]

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model!

We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data.

Check out our results in the video (wait for dynamic scenes in the second half!) :

Project Page: https://t.co/pKtry0BdOL
Code and Models: https://t.co/p4zVBrMKU5
Paper: https://t.co/ZuMM1LCP82

[Nithin Raghavan @nithin_raghavan]

If you’re at SIGGRAPH 2025 in Vancouver, join us Thu 2 PM for our talk “Generative Neural Materials”! We introduce a universal neural material model for bidirectional texture functions and a complementary generative pipeline. 1/2

[Jack Langerman ✈️ CVPR @jacklangerman]

CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

@ChrisWu6080 @RuiqiGao @poolio @alextrevith ChangxiZheng @jon_barron @holynski_

[Alex Trevithick @alextrevith]

Project page: https://t.co/gOZokMZ4NZ

[Alex Trevithick @alextrevith]

🎥 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.

[Aleksander Holynski @holynski_]

Poster #60 this afternoon, swing by!

[Bosung Kim @bosungkim17]

Interactive looong-context reasoning still has a long way to go. We need progress across all axes: more data, bigger model, and smarter architectures.

∞-THOR is just beginning: generate ∞-len trajectories, run agents online train with feedback and more! Let’s push the limits🚀

[Hanwen Jiang @hanwenjiang1]

Supervised learning has held 3D Vision back for too long.

Meet RayZer — a self-supervised 3D model trained with zero 3D labels:
❌ No supervision of camera & geometry
✅ Just RGB images

And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy)

🌐 Project: https://t.co/YpHJIu0tfs
(1/4)

[Alex Trevithick @alextrevith]

@yongyuanxi @jon_barron Someone should do this on Minecraft--seems super doable to make a multiview video model with lots of players.

[Alex Trevithick @alextrevith]

@yongyuanxi @jon_barron 1. Agreed. Real-world videos obey physics; generative models should therefore learn this property of the data with scaling compute and data.

2. It's like taking the "neural" in neural rendering to the limit. I wonder if a prohibitively large decoder may be necessary.

[Alex Trevithick @alextrevith]

After finishing ICCV reviews this year...

[Alex Trevithick @alextrevith]

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?

[Xingyu Chen @RoverXingyu]

🦣Easi3R: 4D Reconstruction Without Training!

Limited 4D datasets? Take it easy.

#Easi3R adapts #DUSt3R for 4D reconstruction by disentangling and repurposing its attention maps → make 4D reconstruction easier than ever!

🔗Page: https://t.co/9BngrGu7EL

[Stan Szymanowicz @ CVPR26 @StanSzymanowicz]

⚡️ Introducing Bolt3D ⚡️
Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images.
It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization.
🧵👇 (1/9)

[Xintao Wang @xinntao]

Thanks @_akhaliq for sharing our ReCamMaster!
ReCamMaster can re-capture existing videos with novel camera trajectories.
Project page: https://t.co/tRo7UyKMr6
Paper: https://t.co/qdTYzxO1x6