# Multimodal LLMs / vision-language models

12,360 papers in 16 research directions. Data through 7 Oct 2026.
HTML: https://mlsanity.com/mllm/

## Directions (largest first)

- [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/index.md): 2,288 papers, 8 new this week
- [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/index.md): 2,063 papers, 5 new this week
- [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/index.md): 1,468 papers, 3 new this week
- [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/index.md): 1,045 papers, 7 new this week
- [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/index.md): 947 papers, 6 new this week
- [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/index.md): 850 papers, 9 new this week
- [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/index.md): 742 papers, 2 new this week
- [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/index.md): 635 papers, 5 new this week
- [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/index.md): 599 papers, 2 new this week
- [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/index.md): 480 papers, 0 new this week
- [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/index.md): 396 papers, 3 new this week
- [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/index.md): 390 papers, 1 new this week
- [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/index.md): 202 papers, 1 new this week
- [Social bias and fairness in VLMs](https://mlsanity.com/mllm/social-bias-and-fairness-in-vlms/index.md): 123 papers, 0 new this week
- [Multimodal emotion understanding](https://mlsanity.com/mllm/multimodal-emotion-understanding/index.md): 90 papers, 0 new this week
- [Agricultural vision-language models](https://mlsanity.com/mllm/agricultural-vision-language-models/index.md): 42 papers, 0 new this week