[人人能懂] AI的“小灶、泥人与神级助理”

00:00:29 解锁AI推理能力：少即是多的秘密

00:05:17 AI巨兽的“成长配方”：如何让小个子智慧指导大块头？

00:10:03 AI作画的“临门一脚”：如何让快马跑得又快又好？

00:14:05 AI 创造 3D 模型：从“盖房子”到“捏泥人”

00:07:44 AI界的“小灶”，如何喂出绝顶高手？

本期介绍的五篇论文：

[LG] Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning  

[Alibaba Group]  

arxiv.org 

---

[LG] μ-Parametrization for Mixture of Experts  

[University of Warsaw]  

arxiv.org 

---

[LG] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models  

[Technical University of Munich & Inceptive]  

arxiv.org 

---

[CV] VertexRegen: Mesh Generation with Continuous Level of Detail  

[Meta Reality Labs Research & UC San Diego]  

arxiv.org 

---

[LG] Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning  

[Zhongxing Telecom Equipment (ZTE)]  

arxiv.org 

---

[CL] Speed Always Wins: A Survey on Efficient Architectures for Large Language Models  

[Unknown / Survey paper]  

arxiv.org