arXiv AI September 10, 2026 By Akhila Yerukola, Fabrice Y Harel-Canada, Simran Khanuja, Abhinav Sukumar Rao, Ashima Suvarna, Nanyun Peng, Saadia Gabriel, Maarten Sap

NormViz: A Benchmark and Framework for Grounding Multimodal Reasoning in Global Cultures

Read the original on arXiv AI →

NormViz introduces a new benchmark, NormViz‑Bench, comprising 3,268 contrastive image pairs from 16 countries that test AI’s ability to recognize culturally relevant visual norms. Each pair differs only in a behavior that changes its cultural interpretation, and images are labeled as conforming, violating, or irrelevant to local norms, requiring both images to be correctly classified. The benchmark shows current VLMs perform poorly, and a complementary training set, NormViz‑Train, offers a path to improve performance by teaching models to link visual perception with cultural significance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computer Vision

Sep 4

VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs

VKnowU is a benchmark that tests multimodal large language models (MLLMs) on their grasp of visual knowledge—intuitive, human-like understanding of physical and social principles in videos. The benchmark contains 1,680 questions across 1,249 videos, covering eight core types of visual knowledge, and shows that current state‑of‑the‑art MLLMs still lag behind human performance, especially on world‑centric tasks. To address this gap, the authors release VKnowQA and VideoKnow+, a baseline model that incorporates visual knowledge via a See‑Think‑Answer framework and reinforcement learning, improving performance on VKnowU and related datasets.

By Tianxiang Jiang, Sheng Xia, Yicheng Xu, Linquan Wu, Xiangyu Zeng, Limin Wang, Yu Qiao, Yi Wang

llms reinforcement-learning multimodal benchmarks

arXiv AI

Oct 9

Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models

The paper introduces Humanity's Sixth Sense (HSS), a benchmark designed to evaluate intuitive visual reasoning in multimodal large language models. HSS covers a wide range of image and video inputs, organizes them under a structured taxonomy, and pairs each with human‑written prompts that probe implicit temporal, spatial, social, and abstract cues that humans can infer at a glance. Current state‑of‑the‑art models, including GPT‑6‑astra, achieve far lower accuracy than humans (53.6 % vs. 93.1 %), highlighting a significant gap in intuitive visual understanding.

By Xingang Guo, Jing Gu, Brian Jang, Renxiong Wang, Utkarsh Tyagi, Daniel Quigley, Steven Li, David Yan, Daniel Yue Zhang, Darvin Yi, Forrest Huang, HiJae Kim, Tianyi Zhang, Jared Lichtarge, Jihua Huang, Le Xue, Manan Tomar, Qiuyi Richard Zhang, Ruofei Yu, Seth Neel, Yaning Hu, Marcella Valentine, Xinzhe Jiang, Daniel Evans, Chenguang Wang, Dustin Tran, Tong Zhao, Yinfei Yang, Yunzhong He

llms agents robotics multimodal benchmarks

arXiv AI

Sep 10

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

arXiv:2609.06245v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) perform strongly on general visual understanding tasks such as visual question answering, yet they often str...

By Yixin Wan, Tianle Zheng, Kai-Wei Chang

llms computer-vision nlp multimodal benchmarks

arXiv Computation and Language

Oct 15

More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training

arXiv:2610.19443v1 Announce Type: new Abstract: Native multimodal pre-training trains a single model from scratch on text and multimodal data, enabling it to understand both language and visual input...

By Haoyuan Wu, Aoqi Wu, Jiani Hu, Bei Yu

rag multimodal

arXiv Computer Vision

Oct 12

GraphVerse: A Comprehensive Visual Graph Reasoning Benchmark for Multimodal Large Language Models

GraphVerse is a new benchmark for multimodal large language models that tests visual graph reasoning by combining perception, graph-based visual inputs, and multi-step reasoning. It introduces Graph-centric Image Editing strategies to actively challenge models while preserving semantics, and offers a VGR-Score metric that evaluates reasoning quality beyond simple answer accuracy. Experiments show current models have limitations in VGR and demonstrate the effectiveness of GraphVerse for broader multimodal reasoning tasks.

By Yuanfu Sun, Yuanhang Ren, Kang Li, Chuanhao Ji, Jiaxi Li, Jiajin Liu, Ninghao Liu, Qiaoyu Tan

llms multimodal benchmarks

arXiv Computation and Language

Oct 5

The Percept-V Challenge: Can Multimodal LLMs Crack Simple Perception Problems?

The paper introduces Percept-V, a dataset of 6,000 program-generated images across 30 domains designed to test simple visual perception skills from the TVPS-4 framework. Experiments show that state‑of‑the‑art multimodal large language models perform poorly compared to humans, especially as image complexity increases, and that fine‑tuning yields only limited generalization to related datasets. The study highlights specific perception skills that remain challenging for current models.

By Samrajnee Ghosh, Ashish Goswami, Naman Agarwal, Hemanshu Garg, Chinmay Mittal, Mausam, Parag Singla

llms fine-tuning multimodal benchmarks