BabyVision: Visual Reasoning Beyond Language
UniPat AI · Peking University · University of Illinois at Urbana-Champaign · Alibaba Group · Nanyang Technological University · Moonshot AI · Beijing University of Posts and Telecommunications · StepFun · Tsinghua University · University of Wisconsin - Madison · Princeton University · Nanyang Technological University, MMLab@NTU · Department of Electronic Engineering, Tsinghua University · Zero Gravity Labs · CMU, Carnegie Mellon University · ByteDance Inc. · hongshan capital · Hongshan · Hong Kong University of Science and Technology
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing Babyvision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://anonymous.4open.science/r/BabyVision-E88F/ for reproduction.