arXiv:2510. 08543v2 Announce Type: replace-cross Abstract: As Video Large Language Models (VideoLLMs) are deployed globally, it is important to assess their ability to reason across cultural contexts.
By Nikhil Reddy Varimalla, Yunfei Xu, Meng Fan Wang, Arkadiy Saakyan, Smaranda Muresan
CultureVidBench is a new benchmark that evaluates how well text‑to‑video generation models capture cultural details. It contains 1,000 prompts spanning 12 countries, 6 continents, 8 cultural regions, and 14 cultural aspects, grouped into material culture, social practice & performance, and ritual & ceremony. Human studies and automated assessments show that while current models perform well on semantic adherence and visual quality, they often miss fine‑grained cultural details, especially for underrepresented regions and multimodal cues.
By Xianjing Han, Yuhan Su, Yang Deng, Dong Ma, Wee Peng Tay, Bin Zhu
TimeBlind is a diagnostic benchmark designed to evaluate fine‑grained spatio‑temporal compositionality in video large language models (LLMs). It categorizes temporal understanding into three levels—atomic event recognition, event property characterization, and reasoning about event interdependencies—and uses a minimal‑pairs paradigm where video pairs share identical static content but differ only in temporal structure. Across 20 state‑of‑the‑art MLLMs tested on 600 curated instances, the best model achieved only 48.2% instance accuracy, far below human performance of 98.2%, highlighting a reliance on static visual shortcuts rather than true temporal reasoning.
By Baiqi Li, Kangyi Zhao, Ce Zhang, Chancharik Mitra, Jean de Dieu Nyandwi, Gedas Bertasius
TempCloze is a video cloze benchmark designed to evaluate visual temporal reasoning in Video-LLMs. The task presents a video’s beginning and ending clips and asks models to select the correct missing middle from four candidates, focusing on semantic, alignment, and progression aspects while minimizing appearance cues. Evaluation of 31 models shows that temporal alignment is the main challenge, with models performing better on semantic content and event progression but struggling to place events correctly in time.
By Wenqi Pei, Henry Hengyuan Zhao, Yilai Liu, Jiahao Meng, Han Chen, Ziyu Wang, Hongyang Du
MemeCULT-1K is a multilingual benchmark of 1,000 South Asian memes in Bengali, English, and Hindi, each paired with a cultural context note and three human-written explanations, plus an additional set of 54 Bengali regional dialect memes. The study evaluates thirteen vision‑language models under meme‑only and context‑aware settings, showing that providing minimal cultural context consistently improves performance across all models and languages. Error analysis indicates closed‑source models struggle with entity and reference misidentification, while open‑source models are limited by broader cultural knowledge gaps, especially in linguistic and phonological aspects.
By Tawsif Tashwar Dipto, Mehedi Ahamed, Radib Bin Kabir, Mueeze Al Mushabbir, Mohammed Saidul Islam, Mir Rayat Imtiaz Hossain, Md Tahmid Rahman Laskar, Sabbir Ahmed
arXiv:2606. 07311v1 Announce Type: cross Abstract: As video generation models like Veo 3.
By Anku Rani, Wei Dai, Shravan Nayak, Pattie Maes, Mahdi M. Kalayeh, Paul Pu Liang