paper-with-me

홈 › Papers

[De|Re]constructing VLMs' Reasoning in Counting

2025-10-22 · Simone Alghisi, Gabriel Roccabruna, Massimo Rizzoli, Seyed Mahed Mousavi, Giuseppe Riccardi arxiv

Vision-Language Models (VLMs) have recently gained attention due to their competitive performance on multiple downstream tasks, achieved by following user-input instructions. However, VLMs still exhibit several limitations in visual reasoning, such as difficulties in identifying relations (e.g., spatial, temporal, and among objects), understanding temporal sequences (e.g., frames), and counting objects. In this work, we go beyond score-level benchmark evaluations of VLMs by investigating the underlying causes of their failures and proposing a targeted approach to improve their reasoning capabilities. We study the reasoning skills of seven state-of-the-art VLMs in the counting task under controlled experimental conditions. Our experiments show that VLMs are highly sensitive to the number and type of objects, their spatial arrangement, and the co-occurrence of distractors. A layer-wise analysis reveals that errors are due to incorrect mapping of the last-layer representation into the output space. Our targeted training shows that fine-tuning just the output layer improves accuracy by up to 21%. We corroborate these findings by achieving consistent improvements on real-world datasets.

📄 PDF Abstract BibTeX arXiv:2510.19555

Code (0)

등록된 구현이 없습니다.

Tasks

Temporal SequencesVisual Reasoning

Similar Papers 제목 키워드 기반

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models

2026-03-19 · Liwei Che, Zhiyu Xue, Yihao Quan, Benlin Liu 외 arxiv

Counting serves as a simple but powerful test of a Large Vision-Language Model's (LVLM's) reasoning; it forces the model to identify each individual object and then add them all up. In this study, we investigate how LVLM…

Visual Reasoning

Unveiling the Visual Counting Bottleneck in Vision-Language Models

2026-05-28 · Xingzhou Pang, Yifan Hou, Junling Wang, Mrinmaya Sachan arxiv

While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visual counting. In this work, we investigate this extrapolation bottlenec…

Can Vision-Language Models Solve Visual Math Equations?

2025-09-10 · Monjoy Narayan Choudhury, Junling Wang, Yifan Hou, Mrinmaya Sachan arxiv

Despite strong performance in visual understanding and language-based reasoning, Vision-Language Models (VLMs) struggle with tasks requiring integrated perception and symbolic computation. We study this limitation throug…

Mathematical ReasoningVisual Reasoning

Counting to Four is still a Chore for VLMs

2026-04-11 · Duy Le Dinh Anh, Patrick Amadeus Irawan, Tuan Van Vo arxiv

Vision--language models (VLMs) have achieved impressive performance on complex multimodal reasoning tasks, yet they still fail on simple grounding skills such as object counting. Existing evaluations mostly assess only f…

Multimodal ReasoningAnswer GenerationObject Counting

CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models

2026-05-18 · Reem Alzahrani, Hassan Alshanqiti, Bushra Bin Hemid, Zaid Alyafeai 외 arxiv

Vision-Language Models (VLMs) excel at multimodal reasoning, yet it remains unclear whether their answers are grounded in visual evidence or driven by learned language and world priors. Counting provides a precise testbe…

Multimodal Reasoning