BradyFU /Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
★ 18,088⑂ 1,135👁 281⑃ 143● 157▤ 0
+1
Daily
18,088
stars
1,135
forks
281
watchers
143
prs
157
issues
0
releases
README
Awesome-Multimodal-Large-Language-Models
✨ Highlights of NJU-MiG
🔥🔥 Surveys of MLLMs | 💬 WeChat (MLLM微信交流群)
- 🌟 MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs
arXiv 2025, Paper, Project
- 🌟 A Survey of Unified Multimodal Understanding and Generation: Advances and Challenges
arXiv 2025, Paper, Project
- A Survey on Multimodal Large Language Models
NSR 2024, Paper, Project
---
🔥🔥 VITA Series Omni MLLMs | 💬 WeChat (VITA微信交流群)
- VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
NeurIPS 2025 Highlight, Paper, Project
- VITA: Towards Open-Source Interactive Omni Multimodal LLM
arXiv 2024, Paper, Project
- VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
NeurIPS 2025, Paper, Project
---
🔥🔥 MME Series MLLM Benchmarks
- 🔥 Video-MME-v2: Towards the Next Stage in Video Understanding Evaluation
[🍎 Project Page] [📖 Paper] [🤗 Dataset] [🏆 Leaderboard]
- 🌟 MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs
arXiv 2025, Paper, Project
- MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
NeurIPS 2025 DB Highlight, Paper, Dataset, Eval Tool, ✒️ Citation
- Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
CVPR 2025, Paper, Project, Dataset
---
Table of Contents
- Awesome Papers
- Multimodal Instruction Tuning (& Latest Works)
- Multimodal Hallucination
- Multimodal In-Context Learning
- Multimodal Chain-of-Thought
- LLM-Aided Visual Reasoning
- Foundation Models
- Evaluation
- Multimodal RLHF
- Others
- Awesome Datasets
- Datasets of Pre-Training for Alignment
- Datasets of Multimodal Instruction Tuning
- Datasets of In-Context Learning
- Datasets of Multimodal Chain-of-Thought
- Datasets of Multimodal RLHF
- Benchmarks for Evaluation
- Others
---
Awesome Papers
Multimodal Instruction Tuning (& Latest Works)
| Title | Venue | Date | Code | Demo |
|:--------|:--------:|:--------:|:--------:|:--------:|
| Gemini 4 Carbon: our next frontier model | Blog | 2026-10-28 | - | - |
| Gemini 4 Argon: our next era of frontier intelligence | Blog | 2026-09-30 | - | - |
| Qwen3.8-Omni-Flash: Omni Senses. Agentic Delivery. | Blog | 2026-09-18 | - | - |
| GPT-6 Astra: A new generation of intelligence | Blog | 2026-09-04 | - | - |
| Introducing Gemini 3.8 Flash and 3.8 Flash Cyber | Blog | 2026-09-02 | - | - |
| GLM-5.3-Flash: Frontier Intelligence, Flash Cost | Zhipu | 2026-08-26 | Huggingface | - |
| DeepSeek-V4-Flash-Vision-Exp | DeepSeek | 2026-08-21 | - | - |
| Qwen3.8-Max: A New Bar for Coding and Cowork | Blog | 2026-08-15 | Huggingface | Demo |
| !Star DeepSeek Harness | DeepSeek | 2026-08-13 | Github | - |
| !Star Qwen-MM-Plugins | Qwen | 2026-08-11 | Github | - |
| !Star Kimi K3: Open Frontier Intelligence | Kimi | 2026-07-27 | Github | Demo |
| !Star VideoCTop issues
#191Addition: GITA-7B/13B & GVLQA Dataset(Accepted by NeurIPS 2024)4 comments · 2024-11-03#229请收录skywork r1v2 comments · 2025-04-02#213Add Multi-image Benchmark MMIU2 comments · 2025-01-07#194What is MME_Benchmark_release_version?2 comments · 2024-11-15#186May you add IDA-VLM?2 comments · 2024-10-17#169How many samples are in the dataset?2 comments · 2024-07-11#273Add StoryRoute - multimodal LLM travel storytelling app1 comments · 2026-03-22#248Request to add MindOmni1 comments · 2025-06-26