LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Paper
•
2501.03895
•
Published
•
53
MLLM
-
-
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
Paper • 2501.12368 • Published • 46 -
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Paper • 2501.13106 • Published • 91 -
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
Paper • 2502.05173 • Published • 65 -
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
Paper • 2502.06788 • Published • 12 -
Scaling Pre-training to One Hundred Billion Data for Vision Language Models
Paper • 2502.07617 • Published • 29 -
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper • 2502.14786 • Published • 143 -
Token-Efficient Long Video Understanding for Multimodal LLMs
Paper • 2503.04130 • Published • 94 -
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 146 -
Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
Paper • 2504.00595 • Published • 35 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 176 -
Kimi-VL Technical Report
Paper • 2504.07491 • Published • 122 -
The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer
Paper • 2504.10462 • Published • 15 -
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
Paper • 2504.15271 • Published • 63