Changhong Jiang — accepted AI-conference papers

2026

EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval

Jiashi Lin, Changhong Jiang, Xiangru Lin, Ruifei Zhang, Xinyi Zhu, Jiyao Liu +9

CVPR 2026

Retrieval-augmented generation (RAG) has emerged as a critical paradigm for grounding Multimodal Large Language Models (MLLMs) in external knowledge. Recent GraphRAG methods introduce structured entity-relation graphs to improve retrieval and reasoning. However, they remain limited by treating knowl

Cited by 0 Source ↗Scholar ↗

2025

SaCa: A Highly Compatible Reinforcing Framework for Knowledge Graph Embedding via Structural Pattern Contrast

Jiashi Lin, Changhong Jiang, Yixiao Wang, Xinyi Zhu, Zhongtian Hu, Wei Zhang

EMNLP 2025

Knowledge Graph Embedding (KGE) seeks to learn latent representations of entities and relations to support knowledge-driven AI systems. However, existing KGE approaches often exhibit a growing discrepancy between the learned embedding space and the intrinsic structural semantics of the underlying kn

Cited by 0 Source ↗PDF ↗Scholar ↗