OP-CL: On-Policy Guided Continual Post-training for Multimodal Large Language Models
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2644-2653
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62272250)
- National Natural Science Foundation of China (62302243)
- Natural Science Foundation of Tianjin, China (22JCJQJC00150)
- Fundamental Research Funds for the Central Universities, Nankai University (63263244)
This publication has 10 references indexed in Scilit:
- Grow-on-Demand: Sparse and Adaptive Expert Expansion for Continual Instruction TuningProceedings of the AAAI Conference on Artificial Intelligence, 2026
- Progressive LoRA for Multimodal Continual Instruction Tuning2025
- Development of a large-scale medical visual question-answering datasetCommunications Medicine, 2024
- Improved Baselines with Visual Instruction Tuning2024
- Advancing Visual Grounding with Scene Knowledge: Benchmark and Method2023
- Learning to Prompt for Continual Learning2022
- TextCaps: A Dataset for Image Captioning with Reading Comprehension2020
- OCR-VQA: Visual Question Answering by Reading Text in Images2019
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- CIDEr: Consensus-based image description evaluation2015