paper-with-me

홈 › Papers

BabyVision: Visual Reasoning Beyond Language

2026-01-10 · Liang Chen, Weichu Xie, Yiyan Liang, Hongfeng He, Hans Zhao, Zhibo Yang, Zhiqi Huang, Haoning Wu, Haoyu Lu, Y. charles, Yiping Bao, Yuantao Fan, Guopeng Li, Haiyang Shen, Xuanzhong Chen, Wendong Xu, Shuzheng Si, Zefan Cai, Wenhao Chai, Ziqi Huang, Fangfu Liu, Tianyu Liu, Baobao Chang, Ming Wu, Xiaobo Hu, Kaiyuan Chen, Yixin Ren, Yang Liu, Yuan Gong, Kuan Li arxiv

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://github.com/UniPat-AI/BabyVision for reproduction.

📄 PDF Abstract BibTeX arXiv:2601.06521

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Reasoning

Similar Papers 제목 키워드 기반

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

2026-08-26 · Junxiang Xu, Ruisi Wang, Fanyi Pu, Maijunxian Wang 외 arxiv

Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be rendered, but first-class substrates for …

Reinforcement LearningVideo GenerationVisual Reasoning

ATLAS: Agentic Test-time Learning-to-Allocate Scaling

2026-06-01 · Peijia Qin, Qi Cao, Pengtao Xie arxiv

Test-time scaling has become a major way to improve large language model reasoning, but its orchestration has remained designer-engineered: a fixed sample budget, a fixed refinement loop, a fixed scoring rule, or a fixed…

Multimodal ReasoningQuestion AnsweringCode Generation

ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense

2023-10-30 · Kankan Zhou, Eason Lai, Wei Bin Au Yeong, Kyriakos Mouratidis 외

Humans possess a strong capability for reasoning beyond common sense. For example, given an unconventional image of a goldfish laying on the table next to an empty fishbowl, a human would effortlessly determine that the …

Common Sense ReasoningLanguage ModelingLanguage Modelling

Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric Reasoning

2026-05-25 · Longteng Guo, Yifan Wang, Pengkang Huo, Tailai Chen 외 arxiv

Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning directly grounded in visual evidence. W…

Visual Reasoning

Self-Rewarding Vision-Language Model via Reasoning Decomposition

2025-08-27 · Zongxia Li, Wenhao Yu, Chengsong Huang, Zhenwen Liang 외 arxiv

Vision-Language Models (VLMs) often suffer from visual hallucinations: generating things that are not consistent with visual inputs and language shortcuts, where they skip the visual part and just rely on text priors. Th…

Reinforcement LearningVisual Reasoning