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

Efficient World Models with Context-Aware Tokenization

ICML 24 2024 69.4 method

TLDR

Δ-IRIS uses delta encoding and context-aware tokenization for efficient transformer-based world models, achieving SOTA on Crafter with faster training.

Reasoning

Strengths: Novel delta encoding reduces sequence length, leading to significant speedup and SOTA results on Crafter. Weaknesses: Only evaluated on a single simulated benchmark (Crafter), lacking real-world or diverse environment validation.

Read-first score

Read-first score 69.4, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 51.

Reproducibility 25%
81

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

Recency 8%
75.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2024

Topical relevance 42%
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

Methodology quality 25%
50

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

Field roles

Reproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 107.

Keyword Scores

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

Deep Analysis

Innovations

  • Discrete autoencoder that encodes stochastic deltas between consecutive time steps
  • Autoregressive transformer that predicts future deltas by summarizing the current world state with continuous tokens
  • Context-aware tokenization enabling efficient world model representation

Methodology

The paper proposes Δ-IRIS, a model-based RL agent whose world model consists of a discrete autoencoder that encodes stochastic deltas between time steps and an autoregressive transformer that predicts future deltas by summarizing the current state with continuous tokens. The agent is trained and evaluated on the Crafter benchmark across multiple frame budgets, with comparisons to prior attention-based approaches.

Key Results

Δ-IRIS achieves a new state of the art on the Crafter benchmark at multiple frame budgets while being an order of magnitude faster to train than previous attention-based world models.

Tags