paper-with-me

Papers

GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEs

2025-03-30 · Kalliopi Basioti, Pritish Sahu, Qingze Tony Liu, Zihao Xu, Hao Wang, Vladimir Pavlovic

Raven's Progressive Matrices (RPMs) is an established benchmark to examine the ability to perform high-level abstract visual reasoning (AVR). Despite the current success of algorithms that solve this task, humans can generalize beyond a given puzzle and create new puzzles given a set of rules, whereas machines remain locked in solving a fixed puzzle from a curated choice list. We propose Generative Visual Puzzles (GenVP), a framework to model the entire RPM generation process, a substantially more challenging task. Our model's capability spans from generating multiple solutions for one specific problem prompt to creating complete new puzzles out of the desired set of rules. Experiments on five different datasets indicate that GenVP achieves state-of-the-art (SOTA) performance both in puzzle-solving accuracy and out-of-distribution (OOD) generalization in 22 OOD scenarios. Compared to SOTA generative approaches, which struggle to solve RPMs when the feasible solution space increases, GenVP efficiently generalizes to these challenging setups. Moreover, our model demonstrates the ability to produce a wide range of complete RPMs given a set of abstract rules by effectively capturing the relationships between abstract rules and visual object properties.

📄 PDF Abstract BibTeX arXiv:2503.23598

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Reasoning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles

2025-06-27 · Mengyi Shan, Brian Curless, Ira Kemelmacher-Shlizerman, Steve Seitz

We challenge text-to-image models with generating escape room puzzle images that are visually appealing, logically solid, and intellectually stimulating. While base image models struggle with spatial relationships and af…

Eye-Q: A Multilingual Benchmark for Visual Word Puzzle Solving and Image-to-Phrase Reasoning

2026-01-06 · Ali Najar, Alireza Mirrokni, Arshia Izadyari, Sadegh Mohammadian 외 arxiv

Vision-Language Models (VLMs) have achieved strong performance on standard vision-language benchmarks, yet often rely on surface-level recognition rather than deeper reasoning. We propose visual word puzzles as a challen…

Pictorial and apictorial polygonal jigsaw puzzles: The lazy caterer model, properties, and solvers

2020-08-17 · Peleg Harel, Ohad Ben-Shahar

Jigsaw puzzle solving, the problem of constructing a coherent whole from a set of non-overlapping unordered visual fragments, is fundamental to numerous applications and yet most of the literature of the last two decades…

Generating Creative Chess Puzzles

2025-10-27 · Xidong Feng, Vivek Veeriah, Marcus Chiam, Michael Dennis 외 arxiv

While Generative AI rapidly advances in various domains, generating truly creative, aesthetic, and counter-intuitive outputs remains a challenge. This paper presents an approach to tackle these difficulties in the domain…

Solving and Generating NPR Sunday Puzzles with Large Language Models

2023-06-21 · Jingmiao Zhao, Carolyn Jane Anderson

We explore the ability of large language models to solve and generate puzzles from the NPR Sunday Puzzle game show using PUZZLEQA, a dataset comprising 15 years of on-air puzzles. We evaluate four large language models u…

Multiple-choicePrompt Engineering