LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Paper
•
2408.10188
•
Published
•
51
VLM papers
-
-
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
Paper • 2408.08872 • Published • 97 -
Building and better understanding vision-language models: insights and future directions
Paper • 2408.12637 • Published • 116 -
Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
Paper • 2408.12528 • Published • 50 -
HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models in Resource-Constrained Environments
Paper • 2408.10945 • Published • 6 -
CogVLM2: Visual Language Models for Image and Video Understanding
Paper • 2408.16500 • Published • 56 -
Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
Paper • 2408.15998 • Published • 83 -
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Paper • 2409.12191 • Published • 73 -
An Introduction to Vision-Language Modeling
Paper • 2405.17247 • Published • 85 -
NVLM: Open Frontier-Class Multimodal LLMs
Paper • 2409.11402 • Published • 71 -
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
Paper • 2408.04840 • Published • 31 -
VILA^2: VILA Augmented VILA
Paper • 2407.17453 • Published • 38 -
EVLM: An Efficient Vision-Language Model for Visual Understanding
Paper • 2407.14177 • Published • 42 -
Matryoshka Multimodal Models
Paper • 2405.17430 • Published • 30 -
LEOPARD : A Vision Language Model For Text-Rich Multi-Image Tasks
Paper • 2410.01744 • Published • 24 -
Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
Paper • 2410.02740 • Published • 52 -
MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
Paper • 2409.20566 • Published • 51 -
MANTIS: Interleaved Multi-Image Instruction Tuning
Paper • 2405.01483 • Published • 6
Pixtral 12B
Paper • 2410.07073 • Published • 59Note Написали про свой картиночный энкодер, ропе2д, плюс какой-то свой бенч принесли и смотрели на то, как скоры на бенчах реагирует на разные промты
Aria: An Open Multimodal Native Mixture-of-Experts Model
Paper • 2410.05993 • Published • 107Note МоЕ моделька, 4 стадии претрейна: текст онли, мультимодальный: интерлив 190B, синтетические пары 70B, документы и qa 102B, Video и qa 34B, Multimodal Long-Context Pre-training
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 99Note Микро статья, базовая влмка, использовали качественный датасет для претерейна 1.2М пар, который размечали ассесорами,
-
MIO: A Foundation Model on Multimodal Tokens
Paper • 2409.17692 • Published • 49 -
Baichuan-Omni Technical Report
Paper • 2410.08565 • Published • 82 -
MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Paper • 2410.11779 • Published • 24