MathVista
Math Reasoning Evaluation Platform
Evaluating mathematical reasoning in visual contexts using large language models and multimodal AI
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
237 stars
6 watching
36 forks
Language: Jupyter Notebook
last commit: 2 months ago ai4mathlarge-language-modelslarge-multimadality-modelsmachine-learningmathematicsmathqasciencevisual-question-answering
Related projects:
| Repository | Description | Stars |
|---|---|---|
 mathllm/math-v | A dataset and code framework to evaluate the ability of Large Multimodal Models (LMMs) to reason mathematically with visual contexts. | 69 |
| lupantech/scienceqa | Develops a framework for multimodal reasoning and question answering in science and other domains using natural language processing and machine learning techniques. | 606 |
 metadelta/mdlt | A command-line utility for performing arithmetic and symbolic math operations. | 178 |
 open-compass/vlmevalkit | A toolkit for evaluating large vision-language models on various benchmarks and datasets. | 1,343 |
 5anthosh/fcal | A math expression evaluator library that allows users to perform calculations with precision and various units, functions, and constants. | 110 |
 willem-j-an/visidata.nvim | Enables visualizing pandas dataframes in Neovim using Visidata | 24 |
 jy0205/lavit | A unified framework for training large language models to understand and generate visual content | 528 |
 nvlabs/relvit | A deep learning framework designed to improve visual reasoning capabilities by utilizing concepts and semantic relations. | 64 |
 jnhwkim/nips-mrn-vqa | This project presents a neural network model designed to answer visual questions by combining question and image features in a residual learning framework. | 39 |
 davidmascharka/tbd-nets | An open-source implementation of a deep learning model designed to improve the balance between performance and interpretability in visual reasoning tasks. | 348 |
| lupantech/chameleon-llm | An AI framework that enables the composition of diverse tools to generate human-like responses using large language models. | 1,087 |
 airaria/visual-chinese-llama-alpaca | Develops a multimodal Chinese language model with visual capabilities | 427 |
 lirios/calculator | A cross-platform calculator built with QML and Material Design | 29 |
 rucaibox/comvint | Creating synthetic visual reasoning instructions to improve the performance of large language models on image-related tasks | 18 |
 lxtgh/omg-seg | Develops an end-to-end model for multiple visual perception and reasoning tasks using a single encoder, decoder, and large language model. | 1,300 |