arXiv AI
Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Sep 8
Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling
Hi-FLoop introduces a hierarchical state‑feedback framework for multi‑agent traffic simulation that reconciles decision time scales over an 8‑second rollout. The model uses eight scene‑level Worlds to maintain joint hypotheses, with an 8‑second Goal, 2‑second Preview, and 1‑second Control hierarchy, and commits only executed prefixes every 0.5 seconds to preserve factual consistency. A joint preview interaction graph and a prefix‑frozen A‑to‑B cascade enable sparse interaction refinement and accurate state recovery, achieving an overall score of 0.689987 on the H‑D public‑validation split and strong oracle‑minADE performance. whyItMatters":"The paper presents a novel multi‑timescale approach that improves consistency and realism in long‑horizon traffic simulations, as evidenced by its competitive evaluation metrics."
arXiv Machine Learning
Aug 4
FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds
arXiv:2608. 01049v1 Announce Type: cross Abstract: World models have attracted significant attention for their ability to capture and predict the structure and dynamics of the physical world.
arXiv AI
Sep 1
AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policies
arXiv:2608.29937v1 Announce Type: new Abstract: Latent world-action models avoid rendering future pixels by predicting an action-relevant visual subgoal in feature space. LaWAM established this formu...
arXiv AI
Sep 28
OneWorld: Learning Consistent Physics Across Actions in World Models
OneWorld introduces a shared‑mechanism counterfactual generation framework that jointly models multiple action‑conditioned futures using a common latent physical mechanism. By inferring distributions over latent mechanisms for each action‑outcome branch and aggregating them into shared‑world evidence, the model enforces consistency across interventions while preserving distinct action outcomes. Experiments in controlled environments demonstrate that OneWorld improves cross‑intervention physical consistency without sacrificing single‑rollout prediction quality.
arXiv AI
Aug 25
ReWorld: An Interactive World Model with Long-Horizon Memory
arXiv:2608.23565v1 Announce Type: new Abstract: An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: contro...
Hugging Face Trending Papers
Aug 24
ReWorld: An Interactive World Model with Long-Horizon Memory
An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounde...