Papers by Jingyang Hu

2 papers
Data Pollination: An Emergent Ecological Process Driving AI Population Evolution (2026.acl-long)

Copied to clipboard

Challenge: evidence from deployed systems suggests that language models interact through a shared data ecosystem.
Approach: They propose to use data pollination to investigate stability dynamics under synthetic data training to investigate model collapse.
Outcome: The proposed model can mitigate model collapse observed in recursive training, and improve performance across benchmarks.
ZoomRAG: Hierarchical Random-walk Zooming across Multi-scale Information Graphs for Fast and Accurate RAG (2026.findings-acl)

Copied to clipboard

Challenge: retrieval-augmented generation (RAG) is a powerful tool for NLP applications . but it is challenging to encode large knowledge bases as compact offline structures .
Approach: They propose a coarse-to-fine hierarchical graph inference method that uses random walks to retrieve information from a corpus of documents.
Outcome: The proposed method reduces offline indexing costs and accelerates retrieval.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations