个人简介：
彭道万，重庆人，工学博士，讲师。中国人工智能学会会员，受邀担任多个国际学术会议审稿人或PC，包括机器学习领域学术会议NeurIPS，计算机视觉领域学术会议CVPR、ICCV、ECCV、BMVC、WACV，多媒体计算领域学术会议ACM MM、IEEE ICME、IEEE ICASSP，数据挖掘领域学术会议ACM CIKM，人工智能领域学术会议AAAI等.
教育与工作经历：
2013.09-2017.06，重庆邮电大学，本科
2017.09-2020.06，重庆邮电大学，硕士
2021.09-2025.06，华中科技大学，博士
2020.07-2021.07，华为技术有限公司，工程师
2025.12-至今，重庆师范大学，讲师
研究方向：
多模态机器学习、视觉推理、因果推理、智能信息处理
科研项目:
[1]重庆市教委科学技术研究计划-青年项目，主持。
[2]重庆师范大学人才引进博士启动基金项目，主持。
[3]重庆市教委科学技术研究计划-重大项目，参与。
[4]重庆市自然科学基金面上项目，参与。
代表论著：
[1]TokTic: Alleviating Multimodal Hallucinations via Token-Intervention Decoding. In2026 IEEE International Conference on Multimedia and Expo. (ICME 2026, CCF-B 类)
[2]Mitigating Hallucinations in Vision-Language Models via Contextual Entropy Calibration. InProceedings of the 16th ACM International Conference on Multimedia Retrieval. (ICMR 2026, CCF-B 类)
[3]Detection-based Intermediate Supervision for Visual Question Answering. InProceedings of the 38th AAAI Conference on Artificial Intelligence. (AAAI 2024, CCF-A 类)
[4]Towards Deconfounded Visual Question Answering via Dual-causal Intervention. InProceedings of the 33rd ACM International Conference on Information and Knowledge Management. (CIKM 2024, CCF- B类)
[5]Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation. In2024 IEEE International Conference on Multimedia and Expo. (ICME 2024, CCF-B 类)
[6]An Empirical Study on the Language Modal in Visual Question Answering. InProceedings of the 32nd International Joint Conference on Artificial Intelligence.(IJCAI 2023, CCF-A 类)
[7]Declaration-based Prompt Tuning for Visual Question Answering. InProceedings of the 31st International Joint Conference on Artificial Intelligence.(IJCAI 2022, CCF-A 类)
[8]Depth-Aware and Semantic Guided Relational Attention Network for Visual Question Answering.IEEE Transactions on Multimedia, 2022. (IEEE TMM, CCF-B 类)
[9]Ball k-Means: Fast Adaptive Clustering with No Bounds.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020. (IEEE TPAMI, CCF-A 类)
