MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models Paper • 2410.17637 • Published 13 days ago • 34
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree Paper • 2410.16268 • Published 15 days ago • 65
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction Paper • 2410.17247 • Published 14 days ago • 43
Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate Paper • 2410.07167 • Published 27 days ago • 36
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution Paper • 2409.12191 • Published Sep 18 • 73
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding Paper • 2407.15754 • Published Jul 22 • 19
VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models Paper • 2407.11691 • Published Jul 16 • 13
InternVL 2.0 Collection Expanding Performance Boundaries of Open-Source MLLM • 16 items • Updated 15 days ago • 75
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output Paper • 2407.03320 • Published Jul 3 • 92
Qwen2 Collection Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated Sep 18 • 346
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs Paper • 2406.14544 • Published Jun 20 • 34
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs Paper • 2406.11833 • Published Jun 17 • 61
MotionClone: Training-Free Motion Cloning for Controllable Video Generation Paper • 2406.05338 • Published Jun 8 • 39
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions Paper • 2406.04325 • Published Jun 6 • 71
Open-LLaVA-NeXT Collection Open-source implementation of the LLaVA-NeXT series with Open-LLaVA-NeXT repositary • 3 items • Updated May 29 • 4
Idefics2 🐶 Collection Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation. • 11 items • Updated May 6 • 88
LLaVA-Video Collection Models focus on video understanding (previously known as LLaVA-NeXT-Video). • 6 items • Updated about 1 month ago • 51
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites Paper • 2404.16821 • Published Apr 25 • 53