AIBullisharXiv – CS AI · 6h ago6/10
🧠
Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement
Researchers introduce NOVA, a world modeling framework that represents scene state as weights in implicit neural representations (INRs) rather than traditional encoded latent spaces. The approach eliminates decoder bottlenecks, achieves structural disentanglement of scene components, and enables controllable video generation on consumer GPUs with only 40M parameters.