[人人能懂] 揭秘顶尖模型的“偷懒”智慧

00:00:30 AI刷题也“偷懒”？聪明的懒办法，效率翻倍

00:05:15 换个姿势“算命”，AI才能更聪明

00:09:16 AI的省钱之道：从“专家会诊”到“超级记忆”

00:13:08 组建梦之队：一个“鸟群智慧”给AI模型的启发

00:16:55 AI界的“偏科生”：我们如何让它变成全能学霸？

本期介绍的几篇论文：

[LG] TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling  

[ByteDance Seed]  

arxiv.org  

---

[LG] Predicting the Order of Upcoming Tokens Improves Language Modeling  

[MBZUAI]  

arxiv.org  

---

[LG] UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning  

[ByteDance Seed]  

arxiv.org  

---

[LG] PSO-Merging: Merging Models Based on Particle Swarm Optimization  

[Chinese Academy of Science]  

arxiv.org  

---

[CL] Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning  

[Yale University & Harvard University]  

arxiv.org