MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances

arXiv 2026 20.2 method

TLDR

MAMHOI factorizes scene-aware human-object interaction generation using affordances as an interface, learning scene understanding and motion synthesis from separate supervision sources without paired data.

Reasoning

The paper's strength is its affordance-mediated factorization that allows complementary supervision without paired human-object-scene data, and experiments indicate improved physical feasibility. Weaknesses include the abstract lacking quantitative details, explicit metrics, and discussion of limitations or comparisons.

Read-first score

Read-first score 20.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 4.

Recency 5%

100

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

Reproducibility 15%

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

Methodology quality 15%

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

Topical relevance 25%

5.7

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

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: 115.

Keyword Scores

interactive world model

world model

world dynamics prediction

world simulator

generative world model

video world model

model-based reinforcement learning world model

Resources

Paper