Preprint2025
Llava-Mini
Unknown
Llava-Mini reduces vision tokens by pre-fusing CLIP visual information into text tokens and using query-based compression for efficient multimodal processing.
0Jan 1, 2025MultimodalComputer Vision
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
5 papersPreprint2024
LLaVA 1.6
Unknown
LLaVA 1.6 enhances multimodal AI with dynamic high-resolution processing, improved OCR, and scalable LLM integration.
0Jan 1, 2024Reasoning
Preprint2024
MoE-LLaVA
Unknown
MoE-LLaVA introduces a sparse mixture-of-experts framework for vision-language models, activating only top-k experts per token to match larger model performance with fewer parameters.
0Jan 1, 2024
arXiv
Preprint2023
LLaVA 1.5
Unknown
LLaVA 1.5 enhances multimodal AI by integrating CLIP-ViT-L-336px with MLP projection and academic VQA data, achieving state-of-the-art results.
0Oct 1, 2023MultimodalBenchmarks
Preprint2023
LLaVA 1
Unknown
LLaVA connects CLIP and Vicuna via end-to-end training on GPT-4-generated instruction-following data from image-text pairs.
0Apr 1, 2023MultimodalInstruction Tuning