FlowSG recasts scene graph generation as progressive flow matching on a hybrid discrete-continuous state using VQ-VAE tokens and a graph Transformer, delivering roughly 3-point gains over prior one-shot methods on VG and PSG.
Fixedanchorsarenotenough: Dynamicre- trievalandpersistenthomologyfordatasetdistillation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5roles
background 2polarities
background 2representative citing papers
IDCL adds density-based curriculum learning and density-core guidance to deep image clustering, claiming superior robustness, faster convergence, and flexibility on benchmark datasets.
CS-RAG is a GraphRAG framework that plans queries as ordered atomic constraints, uses anchor-relation aware retrieval, applies sufficiency checks, and falls back to text recovery to reduce drift and hallucination from imperfect KGs.
citing papers explorer
-
Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching
FlowSG recasts scene graph generation as progressive flow matching on a hybrid discrete-continuous state using VQ-VAE tokens and a graph Transformer, delivering roughly 3-point gains over prior one-shot methods on VG and PSG.
-
Deep Image Clustering Based on Curriculum Learning and Density Information
IDCL adds density-based curriculum learning and density-core guidance to deep image clustering, claiming superior robustness, faster convergence, and flexibility on benchmark datasets.
-
Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs
CS-RAG is a GraphRAG framework that plans queries as ordered atomic constraints, uses anchor-relation aware retrieval, applies sufficiency checks, and falls back to text recovery to reduce drift and hallucination from imperfect KGs.
- Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
- ScriptHOI: Learning Scripted State Transitions for Open-Vocabulary Human-Object Interaction Detection