牛哥精选 · 半年

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

🤖 AI·大模型 arXiv 计算机视觉 2026-07-07

BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception

贝叶斯方法加持多模态大模型，破解细粒度视觉搜索难题，ICML 2026前沿研究。

arXiv:2607.03184v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate impressive general capabilities, they strug…

贝叶斯视觉搜索多模态大模型细粒度感知

🤖 AI·大模型 arXiv 计算机视觉 2026-06-16

LOCUS: Local Visual Cue Search for Enhancing Fine-Grained Perception in Multimodal Large Language Models

新方法LOCUS通过局部视觉线索搜索，大幅提升多模态大模型对图像细节的感知能力

arXiv:2606.16586v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) remain unreliable on fine-grained visual perception, even whe…

locus 多模态大模型细粒度感知局部视觉搜索计算机视觉

🤖 AI·大模型 arXiv AI 2026-05-27

VisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes

MLLM高分背后隐藏的视觉捷径？新基准揭示模型搜索真实信息的能力缺口

arXiv:2605.26380v1 Announce Type: cross Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90% accuracy on…

多模态大模型视觉搜索基准测试细粒度感知评估方法

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception

LOCUS: Local Visual Cue Search for Enhancing Fine-Grained Perception in Multimodal Large Language Models

VisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes

📅 日期