Papers by Jianing Zhao

2 papers
How to Understand “Support”? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies on Weakly-supervised Phrase Grounding (WPG) largely ignore the implicit phrase-region matching relations, rendering it arduous to explore the semantic nature of phrases.
Approach: They propose an Implicit-Enhanced Causal Inference approach to address the challenges of modeling the implicit relations and highlighting them beyond the explicit.
Outcome: The proposed approach outperforms the state-of-the-art baselines on an implicit-enhanced dataset.
Rethinking Data Mixing from the Perspective of Large Language Models (2026.acl-short)

Copied to clipboard

Challenge: Existing methods to mix data with LLMs have relied on domain definitions derived from intuition.
Approach: They propose a reweighting framework that restructures data scheduling as a graph-constrained optimization problem.
Outcome: The proposed framework achieves competitive performance on GPT-2 models.

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