MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis

@misc{guo2025mllmctbench,
  title = {MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis},
  author = {Haiyun Guo and Zhi-Yan Hou and Yandu Sun and Jinghan He and Yu Chen and Yu-Zhe Zhou and Yu-Heng Jia and Jinqiao Wang and Tat-Seng Chua},
  year = {2025},
  eprint = {2508.08275},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.08275},
}