Author

James Lucas

h-index 5 View on Semantic Scholar

We have 3 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jun 2026

NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

Preliminary results indicate that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters.

Aarti Basant, Amlan Kar, Despoina Paschalidou et al. · arXiv.org · 14 citations · ⚡2

#machine learning Preprint Aug 2026

GLOSS: Geometric Local Self-Similarity Learning for Faithful Reference-Guided Texture Fill

This work leverages the geometric self-similarity and geometry-texture correlation existing in many natural and man-made shapes; and trains a shape-specific local texture generation and completion model that enables local geometry-conditioned texture inpainting, guided by artist-selected references, and generalizes to...

Chen-Yu Cai, A. Hu, James Lucas et al. · 0 citations

Preprint Aug 2026

Addressable Memory for Video World Models

This work proposes WorldTrace, a training-free memory framework for long-horizon visual persistence that keeps compressed memory addressable by assigning each summary slot a distinct, in-distribution virtual position.

Xindi Wu, Sven Elflein, James Lucas et al. · 1 citation