@article{notanothertextbenchmarkputtingthevisualb,
  title = {Not Another Text Benchmark: Putting the "Visual" Back in Visual Question Answering for Large Video Models},
  author = {Rwiddhi Chakraborty and  Yinong and  Wang and Cheng Zhang and Fan Bai and Zhuoran You and Michael Kampffmeyer and Yong Jae Lee and Fernando De la Torre and Robert Jenssen},
  year = {2026},
  eprint = {2609.17112},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.17112},
}