EgoForge: Goal-Directed Egocentric World Simulator

arXiv 2026 39.4 method

TLDR

EgoForge is a goal-directed egocentric world simulator generating coherent first-person video rollouts from a single egocentric image, instruction, and optional exocentric view, using GRAFT diffusion refinement.

Reasoning

The paper introduces a novel generative world-model approach for egocentric video, addressing challenges like viewpoint changes and latent intent with minimal inputs. Its strengths include a new trajectory-level diffusion refinement method and real-world smart-glasses validation, but the abstract lacks quantitative details and explicit limitations.

Read-first score

Read-first score 39.4, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 52.

Recency 5%

100

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

Topical relevance 25%

74.3

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 15%

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

Reproducibility 15%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

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: 500.

Keyword Scores

world simulator

world model

generative world model

video world model

world dynamics prediction

interactive world model

model-based reinforcement learning world model

Deep Analysis

Innovations

EgoForge, an egocentric goal-directed world simulator that generates coherent first-person video rollouts from minimal static inputs: a single egocentric image, a high-level instruction, and an optional auxiliary exocentric view.
GRAFT, a trajectory-level diffusion refinement method that uses positive and negative rollout distributions derived from goal, temporal, scene-consistency, and perceptual rewards to steer the diffusion velocity field toward coherent, goal-complete egocentric simulations.
Operates without dense supervision such as camera trajectories, long video prefixes, or synchronized multi-camera capture, unlike prior egocentric approaches.

Methodology

EgoForge takes a single egocentric image, a high-level instruction, and an optional auxiliary exocentric view to generate first-person video rollouts. It employs GRAFT, a trajectory-level diffusion refinement method that steers the diffusion velocity field using positive and negative rollout distributions derived from goal, temporal, scene-consistency, and perceptual rewards.

Key Results

Extensive experiments show EgoForge achieves consistent gains in semantic alignment, geometric stability, and motion fidelity over strong baselines, and performs robustly in real-world smart-glasses experiments.

Resources

Paper