paper-with-me

Papers

TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoning

2026-01-23 · Daixian Liu, Jiayi Kuang, Yinghui Li, Yangning Li, Di Yin, Haoyu Cao, Xing Sun, Ying Shen, Hai-Tao Zheng, Liang Lin, Philip S. Yu arxiv

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual recognition and semantic understanding. Nevertheless, their ability to perform precise compositional spatial reasoning remains largely unexplored. Existing benchmarks often involve relatively simple tasks and rely on semantic approximations or coarse relative positioning, while their evaluation metrics are typically limited and lack rigorous mathematical formulations. To bridge this gap, we introduce TangramPuzzle, a geometry-grounded benchmark designed to evaluate compositional spatial reasoning through the lens of the classic Tangram game. We propose the Tangram Construction Expression (TCE), a symbolic geometric framework that grounds tangram assemblies in exact, machine-verifiable coordinate specifications, to mitigate the ambiguity of visual approximation. We design two complementary tasks: Outline Prediction, which demands inferring global shapes from local components, and End-to-End Code Generation, which requires solving inverse geometric assembly problems. We conduct extensive evaluation experiments on advanced open-source and proprietary models, revealing an interesting insight: MLLMs tend to prioritize matching the target silhouette while neglecting geometric constraints, leading to distortions or deformations of the pieces.

📄 PDF Abstract BibTeX arXiv:2601.16520

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial ReasoningCode Generation

Similar Papers 제목 키워드 기반

An Examination of the Compositionality of Large Generative Vision-Language Models

2023-08-21 · Teli Ma, Rong Li, Junwei Liang

With the success of Large Language Models (LLMs), many Generative Vision-Language Models (GVLMs) have been constructed via multimodal instruction tuning. However, the performance of GVLMs in multimodal compositional reas…

Visual Reasoning

Evaluating Compositional Scene Understanding in Multimodal Generative Models

2025-03-29 · Shuhao Fu, Andrew Jun Lee, Anna Wang, Ida Momennejad 외

The visual world is fundamentally compositional. Visual scenes are defined by the composition of objects and their relations. Hence, it is essential for computer vision systems to reflect and exploit this compositionalit…

Scene Understanding

CrossMed: A Multimodal Cross-Task Benchmark for Compositional Generalization in Medical Imaging

2025-11-14 · Pooja Singh, Siddhant Ujjain, Tapan Kumar Gandhi, Sandeep Kumar arxiv

Recent advances in multimodal large language models have enabled unified processing of visual and textual inputs, offering promising applications in general-purpose medical AI. However, their ability to generalize compos…

Visual Question Answering

MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge

2026-04-20 · Sua Lee, Sanghee Park, Jinbae Im arxiv

Multimodal Large Language Models (MLLMs) have been increasingly used as automatic evaluators-a paradigm known as MLLM-as-a-Judge. However, their reliability and vulnerabilities to biases remain underexplored. We find tha…

MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models

2024-10-13 · Hang Hua, Yunlong Tang, Ziyun Zeng, Liangliang Cao 외

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal understanding, enabling more sophisticated and accurate integration of visual and textual information across various tasks, includin…

Cross-Modal RetrievalQuestion AnsweringVideo CaptioningVisual Question Answering