Reading, Writing, Sharing, and Interacting with the World through Video

arXiv 2026 41.8 survey

TLDR

A survey viewing video foundation models and video world models through a unifying world-modeling lens, organizing the field into reading, writing, sharing, and interacting with world states.

Reasoning

The paper provides a novel unifying framework that connects video understanding and generation to world modeling, and it explicitly covers datasets and benchmarks. As a survey, it does not introduce new methods, and the abstract alone limits detailed assessment of specific contributions.

Read-first score

Read-first score 41.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 51.

Recency 5%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 15%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,dataset,evaluation,experiment

Topical relevance 25%

72.9

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 15%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=dataset

Graph prestige 15%

5.7

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0016

Citation impact 15%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 10%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 541.

Keyword Scores

world model

video world model

interactive world model

world dynamics prediction

generative world model

world simulator

model-based reinforcement learning world model

Deep Analysis

Innovations

Adopts world modeling as a unifying lens connecting video foundation models and video world models, treating observed video as a partial, lossy, temporally ordered projection of a latent temporal world.
Organizes the video literature around four complementary operations: reading, writing, sharing, and interacting.
Distinguishes temporal coherence in observed or generated sequences from consistency in the underlying world state.
Traces a shift in emphasis from clip-level recognition and perceptual fidelity toward persistent state, controllable evolution, physical and causal validity, and interaction-grounded evaluation.

Methodology

This survey organizes existing video modeling research around the operations of reading, writing, sharing, and interacting, and analyzes tasks, representations, models, datasets, and benchmarks through that framework. It does not present new empirical experiments but synthesizes and contrasts prior work under a world modeling perspective.

Key Results

The survey identifies a shift in the field from clip-level recognition and perceptual fidelity toward persistent world state, controllable evolution, physical and causal validity, and evaluation grounded in interaction and downstream decisions. It also distills open challenges that follow from this shift.

Resources

Paper