Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

World2Act: Latent Action Post-Training via Skill-Compositional World Models

arXiv 26.3 2026 49.8 method

TLDR

World2Act transfers world model dynamics to VLA policies via latent-space alignment, improving success rates on simulation and real robots without pixel supervision.

Reasoning

The paper introduces a novel latent-space post-training method that avoids pixel-space supervision, showing clear gains on multiple benchmarks and a real robot. Strengths include the contrastive alignment approach and empirical validation; weaknesses are limited scope of benchmarks and lack of detailed analysis of failure cases.

Read-first score

Read-first score 49.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 46.

Recency 6%
100

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

Topical relevance 29%
65.7

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

Methodology quality 18%
60

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

Reproducibility 18%
50

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

Citation impact 18%
29.2

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.29161764

Citation velocity 12%
0

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

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 320.

Keyword Scores

world model
10
world dynamics prediction
9
generative world model
7
world simulator
6
video world model
5
model-based reinforcement learning world model
5
interactive world model
4

Deep Analysis

Innovations

  • Latent-space post-training framework for VLA policies that avoids pixel-space supervision
  • Shared video-action latent space induced by contrastively aligning WM-dynamics latents with action embeddings
  • Guiding policy action representations toward WM-imagined dynamics instead of decoded pixels

Methodology

World2Act operates in two stages: first, it induces a shared video-action latent space by contrastively aligning WM-dynamics latents with action embeddings; second, it post-trains the VLA by guiding policy action representations toward WM-imagined dynamics rather than decoded pixels. The framework is built on GR00T-N1.6 and evaluated on simulation benchmarks (RoboCasa, LIBERO, Bridge-SIMPLER) and a real robot.

Key Results

World2Act achieves absolute success-rate gains of up to +2.5% on simulation benchmarks and +6.7% on a real robot over finetuned VLA baselines. It outperforms pixel-space WM supervision by up to +6.0%, including on LIBERO where pixel supervision degrades the baseline.

Tags