用动态偏好调优扩散采样器，D2PO在ECCV 2026提出创新方案，让AI绘画更高效精准。
arXiv:2607.06609v1 Announce Type: cross Abstract: We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diff…
多模态大模型新方法，实现视觉token高效嵌入，已被ECCV 2026录用。
arXiv:2602.05275v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrie…
高分辨率视觉感知新思路，层级实体探索方法被ECCV 2026收录，值得关注。
arXiv:2607.00816v1 Announce Type: new Abstract: High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLL…
ECCV 2026论文，用语言引导在结构约束下完成3D物体外表面补全，突破传统几何修复限制。
arXiv:2606.31680v1 Announce Type: new Abstract: Despite advances in indoor scene generation, synthesizing coherent building exteriors consistent with …
遥感图像变化描述迎来多模态大模型，ECCV 2026论文详解RSICCLLM方案
arXiv:2606.28266v1 Announce Type: new Abstract: Remote Sensing Image Change Captioning (RSICC) aims to describe changes between bi-temporal remote sen…