1
Vision Pretraining for Dense Spatial Perception
视觉预训练如何赋能稠密空间感知？一张图看懂物理智能的视觉基础。
arXiv:2607.05247v1 Announce Type: new Abstract: Dense spatial perception is essential for physical intelligence, where visual systems are expected to …
2
DenseMLLM: Standard Multimodal LLMs for Dense Prediction
标准多模态大模型如何突破粗粒度限制，实现像素级稠密预测任务。
arXiv:2602.14134v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in high-…