Implicit Fine-tuning via Context Engineering: A Curriculum Learning Framework for Multimodal Entity Alignment
Open Access
- 8 August 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1698-1709
Abstract
No abstract availableAll Related Versions
Funding Information
- National Natural Science Foundation of China (No. 62120106008)
- Anhui Provincial Science and Technology Fortification Plan (No. 202423k09020015)
- the Hefei Key Generic Technology Research and Development Program (No. 2024SGJ010)
- the Youth Talent Support Program of the Anhui Association for Science and Technology (No. RCTJ202420)
- New Chongging Youth Innovation Talent Project (No. CSTB2024NSCQ-QCXMX0035)
- the Open Project of Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) (BigKEOpen2025-03)
This publication has 43 references indexed in Scilit:
- OTMEA : Multi-modal Entity Alignment via Optimal Transport2025
- Graph structure prefix injection transformer for multi-modal entity alignmentInformation Processing & Management, 2024
- MEA: A Multimodal Entity Entailment framework for multimodal Entity AlignmentInformation Processing & Management, 2024
- SCMEA: A stacked co-enhanced model for entity alignment based on multi-aspect information fusion and bidirectional contrastive learningNeural Networks, 2024
- MMIEA: Multi-modal Interaction Entity Alignment model for knowledge graphsInformation Fusion, 2023
- Multimodal learning with graphsNature Machine Intelligence, 2023
- Estimating Example Difficulty using Variance of Gradients2022
- Dynamic Curriculum Learning for Imbalanced Data Classification2019
- Deep Supervised Cross-Modal Retrieval2019
- Deep Residual Learning for Image Recognition2016