2025.11.14 | UniVA四合一开源视频通才；Depth Anything 3单ViT通吃3D

<p>本期的 4 篇论文如下：</p><p>[00:24] 🎬 UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist（UniVA：面向开源下一代视频通才的通用视频智能体）</p><p>[00:59] 🌐 Depth Anything 3: Recovering the Visual Space from Any Views（Depth Anything 3：从任意视角恢复视觉空间）</p><p>[01:50] 🔍 AlphaResearch: Accelerating New Algorithm Discovery with Language Models（AlphaResearch：用语言模型加速全新算法发现）</p><p>[02:21] 🔍 MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samples（MuSc-V2：无需标注样本的零样本多模态工业异常分类与分割）</p><figure><img src="https://image.xyzcdn.net/FrkrDkQdK2X5tiFWc4ecYZkgHkQT.webp"/></figure><p>【关注我们】</p><p>您还可以在以下平台找到我们，获得播客内容以外更多信息</p><p>小红书: AI速递</p>