Vinh VC

All the credits goes to the incredible engineers working with me on this adventure. If you'd like to join us, visit tornyol.com

Augmented Reality is the natural interface for robotics. Not only for giving commands, but also to visualise hardware data (like LiDAR) natively in 3D. @specs AR glasses, @UnitreeRobotics Go2 Lite quadruped, @dimensionalos OS for the robot

Babe wake up, someone reinvented the LSTM again.

In neuroscience, global workspace theory holds that thoughts become consciously accessible when they enter a privileged workspace that’s broadcast across the brain. Using a new interpretability technique, we found something similar in Claude: the J-space. anthropic.com/research/globa…

underrated account, invest early

I'm at ICML this week, presenting SceneSmith (Spotlight) on Wednesday (10:30-12:15, Hall A, #404). Reach out if you want to chat simulation authoring, agentic systems, robotics, or otherwise!

Can we RL coding agents without environments? The answer is yes! 🥳 In Dockerless, we replace environment-based test execution with an agentic verifier that explores the repo and scores patches as RL rewards. No env-setup/test execution. But full performance!

🎁 We are pleased to introduce Syn4D, a large-scale multiview synthetic dataset for dynamic scenes, accepted at #ECCV2026. The complete dataset, including its dense geometric annotations, is now publicly available. 🌐 Project: jzr99.github.io/Syn4D/ 💻 GitHub: github.com/jzr99/Syn4D 🤗 Dataset: huggingface.co/datasets/Syn4D… 🧵1/8

📢WorldMesh is accepted to #ECCV2026, and we're releasing the code today! 🎉 Led by @mschneider456: navigable, multi-room 3D scenes from a text prompt, with a mesh scaffold conditioning image diffusion for global consistency + photorealistic detail 👇 mschneider456.github.io/world-mesh/

Our papers just got accepted at #ECCV2026 — and the one we're most excited about: SPEAR, our next-gen Physical AI simulation platform, built with multiple tech giants. SPEAR closes the loop from real-world space to robot training: digitize → simulate → train. Alongside Syn-GRPO and WalkerBench, this is our full-stack bet on the data, simulation, and evaluation infrastructure that Physical AI runs on. Built on OpenUSD. Designed for the age of Physical AI. Huge thanks to our SPEAR co-authors and partners: @ros_german, @StefanLeuteneg1, Kalyan Sunkavalli, Vladlen Koltun, Rushikesh Zawar, Rachith Dey-Prakash, and Quentin Leboutet. #PhysicalAI #EmbodiedAI #Robotics #Simulation #ECCV2026 #SpatialAI #OpenUSD

Group3D MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection paper: huggingface.co/papers/2603.21…

Does 3D reconstruction have to be complex? We answer this question with PointDiT (#ICML2026): a minimalist pixel-space Diffusion Transformer without bells and whistles. We show that a plain ViT can estimate dense 3D point maps by operating directly on raw patches. No hybrid ViT+Conv architectures, no lossy VAEs, no complicated training losses. (1/5) 🧵👇

Postiz is on $145k MRR! Right now, we are growing by $1k MRR per day (some days are better) and will probably hit $2m ARR this week. But how can Postiz be growing that fast? What about the competitors? Why do some of them even struggle to pass the $1k MRR? This is my point of view on the subject. But it relates to everyone. Try to listen. It might help you with your startup.

Real robot data is expensive. Real robot evaluations are slow. Excited to share SimFoundry - a system that turns real scenes into sim-ready worlds for training and benchmarking robots at scale - ✅Automated Scene Reconstruction with asset generation ✅Handles clutter, articulated objects, multiple robot embodiments ✅High Correlation Real-to-Sim Evals ✅Zero-shot Sim-to-Real ✅Generates diverse digital cousins Less manual environment authoring, more scalable feedback for robot learning. 🌐research.nvidia.com/labs/gear/simf… 🧵1/9

Mito Claude is back in an insane way This is a 16-minute tutorial on how to create $50,000 cinematic websites (step by step) with Claude Fable 5

We are releasing a new benchmark to evaluate world models!

New paper coming soon.. teaser.. no transformer, no backprop, no problem! Zero Order CAN pretrain! very exciting.. stay tuned!

This is an incredibly cool paper.

"Neural Fields as World Models" by Joshua Nunley (Feb 2026) 🔗arxiv.org/abs/2602.18690