0:000:00
<p>本期的 12 篇论文如下：</p><p>[00:21] 🎬 Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm（用视频思考：视频生成作为统一多模态推理新范式）</p><p>[00:58] 🧠 V-Thinker: Interactive Thinking with Images（V-Thinker：与图像互动的思维推理）</p><p>[01:39] 🧠 Scaling Agent Learning via Experience Synthesis（基于经验合成的智能体规模化强化学习）</p><p>[02:23] 🧠 Cambrian-S: Towards Spatial Supersensing in Video（Cambrian-S：迈向视频中的空间超感）</p><p>[03:06] 🖥 GUI-360: A Comprehensive Dataset and Benchmark for Computer-Using Agents（GUI-360°：面向计算机使用智能体的大规模综合数据集与评测基准）</p><p>[03:51] 📄 NVIDIA Nemotron Nano V2 VL（NVIDIA Nemotron Nano V2 VL：面向文档与长视频理解的高效视觉语言模型）</p><p>[04:28] 🎟 The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms（多头注意力机制的强彩票假设）</p><p>[05:12] 🕵 Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts（基准设计者应“在测试集上训练”以暴露可利用的非视觉捷径）</p><p>[05:48] ⚽ Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots（人形机器人视觉驱动反应式足球技能学习）</p><p>[06:18] 🔍 Contamination Detecti...