Poppi, T., Uzkent, B., Garg, A., Porto, L., Kessler, G., Yang, Y., Cornia, M., Baraldi, L., Cucchiara, R., & Schiffers, F. (2026). CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models. Conference on Empirical Methods in Natural Language Processing. https://iris.unimore.it/handle/11380/1416028