0:000:00
<p>本期的 15 篇论文如下：</p><p>[00:25] 🧠 General Agentic Memory Via Deep Research（通过深度研究的通用代理记忆）</p><p>[00:52] 🧪 AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning（AutoEnv：用于跨环境智能体学习的自动化环境测量）</p><p>[01:24] 🤖 Computer-Use Agents as Judges for Generative User Interface（以计算机使用代理作为生成式用户界面的评判者）</p><p>[01:55] 🎨 DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation（DeCo：用于端到端图像生成的频率解耦像素扩散）</p><p>[02:24] 🎨 UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios（UltraFlux：面向高质量原生4K文本到图像跨多样宽高比的数据-模型协同设计）</p><p>[03:10] 🔍 DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research（DR Tulu：基于演化评分标准的深度研究强化学习）</p><p>[03:46] 🎬 In-Video Instructions: Visual Signals as Generative Control（视频内指令：视觉信号作为生成控制）</p><p>[04:24] 📊 Budget-Aware Tool-Use Enables Effective Agent Scaling（预算感知的工具使用实现有效的智能体扩展）</p><p>[05:12] 🎬 Plan-X: Instruct Video Generation via Semantic Planning（Plan-X：通过语义规划指导视频生成）</...