告别繁琐文档处理！PaddleOCR-VL-vLLM-OpenAI-API本地部署教程：精准解析文本/表格/公式
"视觉语言模型" 相关文章
北大团队让AI学会考古！全球首个古希腊陶罐3D视觉问答数据集发布，还配了专用模型
大道至简，中科院等提出OneRef：统一视觉定位和指代分割
北大团队让AI学会考古！全球首个古希腊陶罐3D视觉问答数据集发布，还配了专用模型
达摩院联合浙大、港理工推出PixelRefer：多模态大模型迈向像素级视觉理解
OCR战场再起风云：LightOnOCR-1B凭什么比DeepSeekOCR快1.7倍？（附演示开源地址）
GenDexHand: Generative Simulation for Dexterous Hands
Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction
Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots
A Retrospect to Multi-prompt Learning across Vision and Language
Latent Domain Prompt Learning for Vision-Language Models
SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World
Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries
超越谷歌、Meta，360的FG-CLIP2为何能成为“全球最强图文模型”？
视觉语言模型“扫地僧”：360低调开源FG-CLIP2登顶29项全球基准测试 | 甲子光年
PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reporting
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
Generating Accurate and Detailed Captions for High-Resolution Images
Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench
