Papers by Songyao Wang

2 papers
Adaptive Text2GQL: Integrating Structural Twig Linking and Evolutionary In-Context Learning (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches struggle with structural hallucinations and lack adaptability in cold-start scenarios.
Approach: They propose a unified, training-free framework for translating natural language into Graph Query Languages.
Outcome: The proposed framework improves accuracy and executability over baselines in Graph2GQLs.
Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing MLLMs are strong at understanding single plots, but struggle with multi-step reasoning . Existing approaches to manage context in chart reasoning include text-based chain-of-thought prompting .
Approach: They propose a hierarchical visual agent framework that iteratively constructs a working context in an image–text space.
Outcome: The proposed framework improves on strong multimodal baselines.

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