ϕ-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models
- 2026-02-26
- 0
@inproceedings{truong2026dpo,
title = {ϕ-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models},
author = {Thanh-Dat Truong and Huu-Thien Tran and J. Cothren and Bhiksha Raj and Khoa Luu},
year = {2026},
booktitle = {CVPR},
eprint = {2602.22601},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2602.22601},
}