@article{puzzlevqadiagnosingmultimodalreasoning,
  title = {PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns},
  author = {Yew Ken Chia and Vernon Toh Yan Han and Deepanway Ghosal and Lidong Bing and Soujanya Poria},
  year = {2024},
  eprint = {2403.13315},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.13315v3},
}