Beyond Inconsistent Reasoning: Intermediate Process Direct Preference Optimization on Small Multi-modal Large Language Models for Visual Question Answering.

Yongzhu Miao|Puzhen Su|Haoran Yin|Shasha Li|Jintao Tang|Ting Wang


Anthology ID:DBLP:conf/mir/MiaoSYLTW26
Volume:Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026
Year:2026
Venue:International Conference on Multimedia Retrieval (ICMR)
Publisher:ACM
Pages:787-796
URL:https://doi.org/10.1145/3805622.3810807
DOI:https://doi.org/10.1145/3805622.3810807
DBLP:conf/mir/MiaoSYLTW26
BibTeX:
@inproceedings{miao-2026-beyond, author = {Yongzhu Miao and Puzhen Su and Haoran Yin and Shasha Li and Jintao Tang and Ting Wang}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{Beyond Inconsistent Reasoning: Intermediate Process Direct Preference Optimization on Small Multi-modal Large Language Models for Visual Question Answering}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {787--796}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810807}, doi = {https://doi.org/10.1145/3805622.3810807} }