ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation

arXiv 2026 20.8 method

TLDR

ViRDM proposes a teacher- and critic-free post-training method for few-step causal video generation using representation distribution matching with memory-efficient techniques and dynamics regularization.

Reasoning

The paper addresses a relevant efficiency problem by removing the teacher-critic stack and introduces several technical contributions to make representation distribution matching feasible for video. However, the abstract lacks explicit quantitative results or benchmark comparisons, so the empirical impact and limitations are not clearly visible.

Read-first score

Read-first score 20.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 5.

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=baseline,evaluation,result

Reproducibility 15%

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

Topical relevance 25%

7.1

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

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

Frontier

Rank sensitivity

Stability: volatile; rank range: 124.

Keyword Scores

video world model

world model

generative world model

world dynamics prediction

world simulator

interactive world model

model-based reinforcement learning world model

Resources

Paper