0:000:00
<p>本期的 13 篇论文如下：</p><p>[00:24] 🧹 DoPE: Denoising Rotary Position Embedding（DoPE：面向旋转位置嵌入的去噪处理）</p><p>[00:58] 🧪 AIonopedia: an LLM agent orchestrating multimodal learning for ionic liquid discovery（AIonopedia：面向离子液体发现的LLM智能体多模态学习编排）</p><p>[01:44] 🖼 UI2Code^N: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation（UI2Code^N：面向测试时可扩展交互式UI转代码生成的视觉语言模型）</p><p>[02:20] 🚀 Virtual Width Networks（虚拟宽度网络）</p><p>[02:56] ⚡ LiteAttention: A Temporal Sparse Attention for Diffusion Transformers（LiteAttention：面向扩散Transformer的时序稀疏注意力机制）</p><p>[03:32] 🌐 Simulating the Visual World with Artificial Intelligence: A Roadmap（用人工智能模拟视觉世界：路线图）</p><p>[04:12] 📐 GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models（GGBench：面向统一多模态模型的几何生成推理基准）</p><p>[05:00] 🧏 HI-TransPA: Hearing Impairments Translation Personal Assistant（HI-TransPA：面向听障者的语音-唇形翻译个人助手）</p><p>[05:35] 🚀 MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pi...