ZrrSkywalker / MAVIS
[ICLR 2025] Mathematical Visual Instruction Tuning for Multi-modal Large Language Models
β137Updated 4 months ago
Alternatives and similar repositories for MAVIS:
Users that are interested in MAVIS are comparing it to the libraries listed below
- [ECCV 2024] Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?β159Updated 7 months ago
- The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM".β247Updated 4 months ago
- π [NeurIPS24] Make Vision Matter in Visual-Question-Answering (VQA)! Introducing NaturalBench, a vision-centric VQA benchmark (NeurIPS'2β¦β80Updated 3 weeks ago
- (ECCV 2024) Empowering Multimodal Large Language Model as a Powerful Data Generatorβ107Updated last month
- [NAACL 2025 Oral] π From redundancy to relevance: Enhancing explainability in multimodal large language modelsβ93Updated 2 months ago
- Chain-of-Spot: Interactive Reasoning Improves Large Vision-language Modelsβ93Updated last year
- An open-source implementation for training LLaVA-NeXT.β392Updated 6 months ago
- Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Modelsβ174Updated 5 months ago
- Evaluating Vision & Language Pretraining Models with Objects, Attributes and Relations. [EMNLP 2022]β129Updated 6 months ago
- A collection of multimodal reasoning papers, codes, datasets, benchmarks and resources.β192Updated this week
- Official repository of MMDU datasetβ89Updated 6 months ago
- β¨β¨Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracyβ275Updated last month
- FACTUAL benchmark dataset, the pre-trained textual scene graph parser trained on FACTUAL.β106Updated 2 weeks ago
- A RLHF Infrastructure for Vision-Language Modelsβ171Updated 5 months ago
- A bug-free and improved implementation of LLaVA-UHD, based on the code from the official repoβ33Updated 8 months ago
- β145Updated 5 months ago
- γNeurIPS 2024γDense Connector for MLLMsβ159Updated 6 months ago
- [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".β152Updated last month
- ICML'2024 | MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGIβ108Updated 9 months ago
- β63Updated last year
- [SCIS 2024] The official implementation of the paper "MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diβ¦β49Updated 5 months ago
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability ofβ¦β115Updated 5 months ago
- β98Updated last year
- [NeurIPS 2024] This repo contains evaluation code for the paper "Are We on the Right Way for Evaluating Large Vision-Language Models"β175Updated 7 months ago
- β73Updated 3 months ago
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'β162Updated 3 months ago
- Official implementation of the Law of Vision Representation in MLLMsβ154Updated 5 months ago
- official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Inputβ64Updated 7 months ago
- The official repository for "2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"β152Updated last month
- A Comprehensive Survey on Evaluating Reasoning Capabilities in Multimodal Large Language Models.β56Updated last month