paper-with-me

Papers

Learning from the Tangram to Solve Mini Visual Tasks

2021-12-12 · Yizhou Zhao, Liang Qiu, Pan Lu, Feng Shi, Tian Han, Song-Chun Zhu

Current pre-training methods in computer vision focus on natural images in the daily-life context. However, abstract diagrams such as icons and symbols are common and important in the real world. This work is inspired by Tangram, a game that requires replicating an abstract pattern from seven dissected shapes. By recording human experience in solving tangram puzzles, we present the Tangram dataset and show that a pre-trained neural model on the Tangram helps solve some mini visual tasks based on low-resolution vision. Extensive experiments demonstrate that our proposed method generates intelligent solutions for aesthetic tasks such as folding clothes and evaluating room layouts. The pre-trained feature extractor can facilitate the convergence of few-shot learning tasks on human handwriting and improve the accuracy in identifying icons by their contours. The Tangram dataset is available at https://github.com/yizhouzhao/Tangram.

📄 PDF Abstract BibTeX arXiv:2112.06113

Code (1)

yizhouzhao/tangram 공식 구현

Tasks

Few-Shot Learning

Similar Papers 제목 키워드 기반

Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations

2025-06-05 · Linjie Li, Mahtab Bigverdi, Jiawei Gu, Zixian Ma 외

Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning…

4kSpatial Reasoning

TangramSR: Can Vision-Language Models Reason in Continuous Geometric Space?

2026-02-05 · Yikun Zong, Cheston Tan arxiv

Humans excel at spatial reasoning tasks like Tangram puzzle assembly through cognitive processes involving mental rotation, iterative refinement, and visual feedback. Inspired by how humans solve Tangram puzzles through …

Spatial Reasoning

ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning

2026-03-13 · Bangjun Xiao, Yihao Zhao, Xiangwei Deng, Shihua Yu 외 arxiv

Agentic reinforcement learning (RL) has emerged as a transformative workload in cloud clusters, enabling large language models (LLMs) to solve complex problems through interactions with real world. However, unlike tradit…

Reinforcement Learning

TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoning

2026-01-23 · Daixian Liu, Jiayi Kuang, Yinghui Li, Yangning Li 외 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 …

Spatial ReasoningCode Generation

Tangram: Benchmark for Evaluating Geometric Element Recognition in Large Multimodal Models

2024-08-25 · Chao Zhang, Jiamin Tang, Jing Xiao

Significant advancements in Large Multimodal Models (LMMs) have enabled them to tackle complex problems involving visual-mathematical reasoning. However, their ability to identify geometric elements remains underexplored…

Mathematical Reasoning