开发迄今最大的遥感指令数据集，IBM研究院等提出专为地球观测数据设计的VLM，入选CVPR 2025
"视觉语言模型" 相关文章
7B超越GPT！1/20数据，无需知识蒸馏，马里兰等推出全新视觉推理方法
Microsoft Research Introduces MMInference to Accelerate Pre-filling for Long-Context Vision-Language Models
Kimi开源MoE架构多模态推理模型，小激活参数，大能量！
Meta AI Released the Perception Language Model (PLM): An Open and Reproducible Vision-Language Model to Tackle Challenging Visual Recognition Tasks
Do We Still Need Complex Vision-Language Pipelines? Researchers from ByteDance and WHU Introduce Pixel-SAIL—A Single Transformer Model for Pixel-Level Understanding That Outperforms 7B MLLMs
CVPR 2025 | MAE损失+最优传输双剑合璧！上科大提出全新鲁棒提示学习方法
中科大、中兴提出新后训练范式：小尺寸多模态模型，成功复现R1推理
Moonsight AI Released Kimi-VL: A Compact and Powerful Vision-Language Model Series Redefining Multimodal Reasoning, Long-Context Understanding, and High-Resolution Visual Processing
Kimi-VL：视觉语言模型（VLM）的新探索
Kimi 16B胜GPT-4o！开源视觉推理模型：MoE架构，推理时仅激活2.8B
UCLA Researchers Released OpenVLThinker-7B: A Reinforcement Learning Driven Model for Enhancing Complex Visual Reasoning and Step-by-Step Problem Solving in Multimodal Systems
专抓AI“看图说谎”，谷歌哥大用三类陷阱触发幻觉，打造可随技术发展动态演进的评估框架
32B本地部署！阿里开源最新多模态模型：主打视觉语言，数学推理也很强
32B本地部署！阿里开源最新多模态模型：主打视觉语言，数学推理也很强
Qwen Releases the Qwen2.5-VL-32B-Instruct: A 32B Parameter VLM that Surpasses Qwen2.5-VL-72B and Other Models like GPT-4o Mini
This AI Paper from NVIDIA Introduces Cosmos-Reason1: A Multimodal Model for Physical Common Sense and Embodied Reasoning
2025.03.24 | 多智能体协作提升性能，苏格拉底式对话优化提示。
50条数据解锁空间智能，RL视觉语言模型3D空间推理框架MetaSpatial ｜西北大学
50条数据解锁空间智能，RL视觉语言模型3D空间推理框架MetaSpatial ｜西北大学
