MRCL extends pairwise spatial contrastive pre-training to multi-hop paths in scene graphs, yielding NDCG@5 = 0.748 on GQA graph retrieval and gains on spatial recognition and QA tasks.
Scene graph generation by iterative message passing
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Learn2Fold generates physically valid origami folding sequences from text prompts by decoupling LLM-based program proposals from verification in a learned graph-structured world model.
citing papers explorer
-
Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations
MRCL extends pairwise spatial contrastive pre-training to multi-hop paths in scene graphs, yielding NDCG@5 = 0.748 on GQA graph retrieval and gains on spatial recognition and QA tasks.
-
Learn2Fold: Structured Origami Generation with World Model Planning
Learn2Fold generates physically valid origami folding sequences from text prompts by decoupling LLM-based program proposals from verification in a learned graph-structured world model.