https://phdstudio.org/2024/10/07/vinoground-a-temporal-counterfactual-large-multimodal-models-lmm-evaluation-benchmark-encompassing-1000-short-and-natural-video-caption-pairs-adeeba-alam-ansari-artificial-intelligence-category-mar/
Vinoground: A Temporal Counterfactual Large Multimodal Models LMM Evaluation Benchmark Encompassing...
multimodal modelstemporalcounterfactuallarge