Robuta

https://openreview.net/forum?id=DrNN5qx66Z&referrer=%5Bthe%20profile%20of%20Cees%20G.%20M.%20Snoek%5D(%2Fprofile%3Fid%3D~Cees_G._M._Snoek1) TVBench: Redesigning Video-Language Evaluation | OpenReview Large language models have demonstrated impressive performance when integrated with vision models even enabling video understanding. However, evaluating these... redesigningvideolanguageevaluationopenreview