arXiv AI
How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 9
Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis
arXiv:2606. 09646v1 Announce Type: cross Abstract: We study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how this information varies across model families, layers, and probe types.
arXiv AI
Aug 6
Seeking Physics in Diffusion Noise
arXiv:2603. 14294v3 Announce Type: replace-cross Abstract: Do video diffusion models encode signals predictive of physical plausibility?
Hugging Face Trending Papers
Aug 13
V-RAE: Rethinking Video Latent Spaces for Generation
Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization.
arXiv Machine Learning
Jun 5
The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
arXiv:2606. 05328v1 Announce Type: cross Abstract: Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators.
arXiv Computer Vision
Sep 1
Off-Manifold Refinement: Guiding Video Generators with a Frozen World Model
arXiv:2608.29904v1 Announce Type: new Abstract: Modern video generators routinely fail at physical dynamics: objects float, trajectories violate gravity, contacts vanish. Standard denoising and flow-...
arXiv Computer Vision
Aug 31
LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation
LayerRecall is a memory router for autoregressive video diffusion that selectively retrieves and injects historical key/value states into specific layers of the model, based on the current context. It addresses the problem that existing memory mechanisms expose nonlocal history but do not guarantee effective use, by recognizing that different layers prefer current, recent, or distant context. The method, combined with Cross‑Horizon Prediction Matching, achieves state‑of‑the‑art long‑range consistency on MemoBench and MovieBench while maintaining local continuity and incurring negligible inference overhead.