nvidia/omni-dreams-models
Image-to-Video • Updated • 16.6k • 42
Jonathan Lorraine
lorraine2
AI & ML interests
Senior Research Scientist at NVIDIA Research (LPR). Agentic AI for science and engineering, world models, generative models, and scalable nested optimization.
Recent Activity
authored a paper 10 days ago
Addressable Memory for Video World Models posted an update 10 days ago
🧠 New NVIDIA paper: WorldTrace 🧠
Long-horizon video world models can store prior scenes in their KV cache and still fail to retrieve them once RoPE offsets leave the training range. We show this is an addressability problem, not just a compression problem.
WorldTrace assigns compressed memory slots fixed, in-distribution positions. WT-Field improves temporal consistency by +15.5%, while WT-Landmark improves episodic recall by +19.5% on LoopBench, without retraining.
🏆 Best Paper + Oral, ICML 2026 From Frames to Stories Workshop
🔎 Project page: https://research.nvidia.com/labs/sil/projects/WorldTrace/
📄 Paper: https://huggingface.co/papers/2608.07408
Led by Xindi Wu, with Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taixé, Despoina Paschalidou, Aljoša Ošep, and me. updated a dataset 13 days ago
lorraine2/fusion-eq-pred-dev1Organizations
liked a
model 3 months ago
liked a
model almost 2 years ago
liked a
Space almost 2 years ago