NVLM: Open Frontier-Class Multimodal LLMs
Paper • 2409.11402 • Published • 75
MIT Talk 31/10 Papers
-
-
BRAVE: Broadening the visual encoding of vision-language models
Paper • 2404.07204 • Published • 20 -
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Paper • 2403.18814 • Published • 49 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 123 -
LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
Paper • 2407.07895 • Published • 42 -
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Paper • 2409.01704 • Published • 82 -
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Paper • 2409.12191 • Published • 80 -
Unifying Multimodal Retrieval via Document Screenshot Embedding
Paper • 2406.11251 • Published • 12 -
LLaVA-OneVision: Easy Visual Task Transfer
Paper • 2408.03326 • Published • 61 -
ColPali: Efficient Document Retrieval with Vision Language Models
Paper • 2407.01449 • Published • 51 -
Pixtral 12B
Paper • 2410.07073 • Published • 69 -
Building and better understanding vision-language models: insights and future directions
Paper • 2408.12637 • Published • 134 -
PaliGemma: A versatile 3B VLM for transfer
Paper • 2407.07726 • Published • 73 -
Sigmoid Loss for Language Image Pre-Training
Paper • 2303.15343 • Published • 12