Papers by Jianing Zhao
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
Yuanjian Xu, Tianze Sun, Changwei Xu, XinLong Zhao, Jianing Hao, Ran Chen, Yang Liu, Ruijie Xu, Stephen Chen, Guang Zhang
| 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. |