0:000:00
<p>本期的 15 篇论文如下：</p><p>[00:20] 🧠 From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence（从代码基础模型到智能体与应用：代码智能实用指南）</p><p>[01:05] 🎬 LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling（LongVT：通过原生工具调用激励“长视频思考”）</p><p>[01:43] 🔍 Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights（Envision：面向因果世界过程洞察的统一理解与生成基准）</p><p>[02:21] 🧠 Stabilizing Reinforcement Learning with LLMs: Formulation and Practices（利用大语言模型稳定强化学习的公式与实践）</p><p>[02:59] 🔍 How Far Are We from Genuinely Useful Deep Research Agents?（我们距离真正有用的深度研究智能体还有多远？）</p><p>[03:47] ⚖ What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards（视频生成中的重力考量？基于可验证奖励的后训练牛顿定律应用）</p><p>[04:24] 🔍 The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment（一致性批评家：通过参考引导的注意力对齐纠正生成图像中的不一致性）</p><p>[05:14] 🎬 Infinity-RoPE: Action-Controllable Infinite Video Generatio...