MAVIS
Mathematical Visual Instruction Tuning Model
CommonProductProductivityMachine LearningMultimodal Learning
MAVIS is a mathematical visual instruction tuning model designed for multimodal large language models (MLLMs). It enhances MLLMs' capabilities in visual mathematical problem-solving by improving visual encoding of mathematical graphs, graph-language alignment, and mathematical reasoning skills. The model includes two newly curated datasets, a mathematical visual encoder, and a mathematical MLLM, achieving leading performance in the MathVerse benchmark test through a three-phase training paradigm.
MAVIS Visit Over Time
Monthly Visits
485459945
Bounce Rate
35.86%
Page per Visit
6.1
Visit Duration
00:06:25