0:000:00
<p>本期的 15 篇论文如下：</p><p>[00:20] ⚡ Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning（原生并行推理器：通过自蒸馏强化学习实现并行推理）</p><p>[01:04] 🧠 Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs（超越实数：用于长上下文大语言模型的旋转位置编码虚部扩展）</p><p>[01:54] 🎬 Unified Video Editing with Temporal Reasoner（基于时序推理的统一视频编辑）</p><p>[02:33] 🔍 DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems（DoVer：面向LLM多智能体系统的干预驱动自动调试方法）</p><p>[03:24] 🎮 Voxify3D: Pixel Art Meets Volumetric Rendering（Voxify3D：像素艺术与体素渲染的融合）</p><p>[04:07] 🎬 Scaling Zero-Shot Reference-to-Video Generation（零样本参考到视频生成的规模化研究）</p><p>[04:39] 🧬 Distribution Matching Variational AutoEncoder（分布匹配变分自编码器）</p><p>[05:12] 🔭 Multi-view Pyramid Transformer: Look Coarser to See Broader（多视图金字塔Transformer：看粗以见广）</p><p>[05:47] 🎬 EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing（EgoEdit：用于第一人称视频编辑的数据集、实时流式模型与基准测试）</p><p>[06:25] 🖼 LongCat-Image Techn...