0:000:00
<p>本期的 14 篇论文如下：</p><p>[00:17] 🏅 P1: Mastering Physics Olympiads with Reinforcement Learning（用强化学习攻克物理奥赛）</p><p>[00:56] 🌐 Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data（Uni-MoE 2.0 Omni：以语言为中心的万模态大模型，通过先进MoE、训练与数据实现规模跃升）</p><p>[01:42] 🧩 Part-X-MLLM: Part-aware 3D Multimodal Large Language Model（Part-X-MLLM：面向部件感知的3D多模态大语言模型）</p><p>[02:22] 🧠 TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models（TiViBench：视频生成模型思维推理基准测试）</p><p>[03:08] 🚀 GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning（GroupRank：一种由强化学习驱动的分组重排范式）</p><p>[03:49] 🧩 PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image（PhysX-Anything：单张图像生成可仿真物理3D资产）</p><p>[04:28] 🌌 UFO$^3$: Weaving the Digital Agent Galaxy（UFO³：编织数字智能体银河）</p><p>[04:59] 🍲 Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance（“汤”级模型：简单加权平均即可让大语言模型性能跃升）</p><p>[05:38] 🌍 OlmoEarth: Stable Latent Image Modeling for...