arXiv AI
PhysTrace: Interpretable Temporal Evaluation of Physical Consistency in Video Generative Models
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
What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction
arXiv:2606. 07687v1 Announce Type: cross Abstract: Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces.
arXiv Computer Vision
Oct 23
Self-Distilling Future Video Representations for World Action Models
The paper introduces FRED, a framework that self‑distills future video representations for World Action Models (WAMs) by predicting these representations from noise using ground‑truth future observations as targets. By conditioning on historical observations, FRED improves the quality of future representations obtained in a single denoising step, thereby enhancing action prediction efficiency. Experiments on real‑world manipulation tasks show that FRED outperforms existing WAMs, especially on long‑horizon, out‑of‑domain, and zero‑shot scenarios, achieving a 50.0% success rate on tasks only seen in human videos versus 19.4% for the best competitor.
arXiv Machine Learning
Oct 15
StateCraft: Augmenting Video World Models with Abstract-State Reasoning
StateCraft introduces a new architecture that separates a persistent, updatable abstract state from the visual state in video world models. By pairing a language model with a video diffusion model, it tracks entity changes over time and conditions visual generation on this abstract state. The approach is evaluated on generative interfaces and a new benchmark, showing improved generation quality, memory usage, and controllability, while enabling direct editing of unseen states and extending to spatial 3D environments.
arXiv AI
Jun 2
Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
arXiv:2606. 02522v1 Announce Type: cross Abstract: Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evidence remains underexplored.
arXiv AI
Jun 10
Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency
arXiv:2606. 10620v1 Announce Type: cross Abstract: Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly understood.
arXiv Computer Vision
Oct 15
Masked Diffusion Vision-Language Models for Temporal Action Localization
arXiv:2605.29858v3 Announce Type: replace Abstract: Temporal action localization (TAL) requires recognizing the target event and localizing its start and end times precisely in untrimmed videos. Rece...