The Evolution of Multimodal Model Architectures
Paper
•
2405.17927
•
Published
•
1
VLMs
-
-
What matters when building vision-language models?
Paper • 2405.02246 • Published • 102 -
Efficient Architectures for High Resolution Vision-Language Models
Paper • 2501.02584 • Published -
Building and better understanding vision-language models: insights and future directions
Paper • 2408.12637 • Published • 125 -
Improving Fine-grained Visual Understanding in VLMs through Text-Only Training
Paper • 2412.12940 • Published -
VILA: On Pre-training for Visual Language Models
Paper • 2312.07533 • Published • 23 -
Renaissance: Investigating the Pretraining of Vision-Language Encoders
Paper • 2411.06657 • Published -
Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions
Paper • 2404.07214 • Published -
NanoVLMs: How small can we go and still make coherent Vision Language Models?
Paper • 2502.07838 • Published -
POINTS: Improving Your Vision-language Model with Affordable Strategies
Paper • 2409.04828 • Published • 24 -
Unveiling Encoder-Free Vision-Language Models
Paper • 2406.11832 • Published • 51 -
Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers
Paper • 2410.14072 • Published -
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Paper • 2501.03895 • Published • 49 -
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
Paper • 2402.03766 • Published • 14 -
PaliGemma: A versatile 3B VLM for transfer
Paper • 2407.07726 • Published • 68 -
BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices
Paper • 2411.10640 • Published • 45 -
Scalable Vision Language Model Training via High Quality Data Curation
Paper • 2501.05952 • Published • 1 -
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Paper • 2403.18814 • Published • 47 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper • 2412.04467 • Published • 107 -
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
Paper • 2401.06209 • Published -
Model Composition for Multimodal Large Language Models
Paper • 2402.12750 • Published -
A Review of Multi-Modal Large Language and Vision Models
Paper • 2404.01322 • Published -
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
Paper • 2312.16862 • Published • 31 -
TinyLLaVA: A Framework of Small-scale Large Multimodal Models
Paper • 2402.14289 • Published • 19 -
Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model
Paper • 2411.05903 • Published -
Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
Paper • 2311.14109 • Published -
TinyLLaVA-Video: A Simple Framework of Small-scale Large Multimodal Models for Video Understanding
Paper • 2501.15513 • Published -
LLaVA-φ: Efficient Multi-Modal Assistant with Small Language Model
Paper • 2401.02330 • Published • 16 -
MM-LLMs: Recent Advances in MultiModal Large Language Models
Paper • 2401.13601 • Published • 47 -
Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance
Paper • 2410.16261 • Published • 5 -
The (R)Evolution of Multimodal Large Language Models: A Survey
Paper • 2402.12451 • Published -
Survey of Large Multimodal Model Datasets, Application Categories and Taxonomy
Paper • 2412.17759 • Published -
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Paper • 2409.12191 • Published • 76 -
Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities
Paper • 2403.04908 • Published -
google/paligemma2-3b-mix-448
Image-Text-to-Text • Updated • 1.43k • 26 -
LLaVA-o1: Let Vision Language Models Reason Step-by-Step
Paper • 2411.10440 • Published • 114 -
InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning
Paper • 2502.11573 • Published • 6 -
OpenGVLab/Mini-InternVL-Chat-2B-V1-5
Image-Text-to-Text • Updated • 2.25k • 71 -
HuggingFaceTB/SmolVLM-256M-Instruct
Image-Text-to-Text • Updated • 38.2k • 155 -
Qwen/Qwen2.5-VL-3B-Instruct
Image-Text-to-Text • Updated • 424k • 222 -
MILVLG/imp-v1-3b
Text Generation • Updated • 373 • 202 -
marianna13/llava-phi-2-3b
Text Generation • Updated • 173 • 12 -
Exploring the Potential of Encoder-free Architectures in 3D LMMs
Paper • 2502.09620 • Published • 26