# PuzzleGPT: Emulating Human Puzzle-Solving Ability for Time and Location Prediction

arXiv: https://arxiv.org/abs/2501.14210 · HTML: https://mlsanity.com/paper/2501.14210/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections](https://mlsanity.com/paper/2205.12005/) (2022)
- [Neural Programmer: Inducing Latent Programs with Gradient Descent](https://mlsanity.com/paper/1511.04834/) (2015)
- [Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning](https://mlsanity.com/paper/2307.06166/) (2023)
- [Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval](https://mlsanity.com/paper/2206.02082/) (2022)
- [G^3: Geolocation via Guidebook Grounding](https://mlsanity.com/paper/2211.15521/) (2022)

## Built on by (most cited first, 2 of 2)

- [GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning](https://mlsanity.com/paper/2505.21863/) (2025)
- [NewsRECON: News Article Retrieval for Image Contextualization](https://mlsanity.com/paper/2601.14121/) (2026)

## Abstract (arXiv)

The task of predicting time and location from images is challenging and requires complex human-like puzzle-solving ability over different clues. In this work, we formalize this ability into core skills and implement them using different modules in an expert pipeline called PuzzleGPT. PuzzleGPT consists of a perceiver to identify visual clues, a reasoner to deduce prediction candidates, a combiner to combinatorially combine information from different clues, a web retriever to get external knowledge if the task can't be solved locally, and a noise filter for robustness. This results in a zero-shot, interpretable, and robust approach that records state-of-the-art performance on two datasets -- TARA and WikiTilo. PuzzleGPT outperforms large VLMs such as BLIP-2, InstructBLIP, LLaVA, and even GPT-4V, as well as automatically generated reasoning pipelines like VisProg, by at least 32% and 38%, respectively. It even rivals or surpasses finetuned models.