大脑的“压缩算法”：Nat Commun研究揭示人类泛化学习背后的机制
"泛化能力" 相关文章
大脑的“压缩算法”：Nat Commun研究揭示人类泛化学习背后的机制
Enhancing Language Model Generalization: Bridging the Gap Between In-Context Learning and Fine-Tuning
只有通过海量测试才能抓住泛化性的本质吗？
AI无师自通，搞定所有家务！π0.5突破泛化极限，UC伯克利系出品
【漫话机器学习系列】230.模型复杂度对训练和测试误差的影响（The Effect Of Model Complexity Training And Test）
AI搞定所有家务！具身智能公司Physical Intelligence推出π0.5，换个房子也能行
Improving CNNs with Klein Networks: A Topological Approach to AI
改错能力是这轮推理模型带来的基础能力之一
Transfer-learning for video classification: Video Swin Transformer on multiple domains
机器人可跨类别操作陌生物体，清华团队开发新方法提升泛化能力31.6%
Why Can't We Hypothesize After the Fact?
DeepSeek研究员在线爆料：R1训练仅用两到三周，春节期间观察到R1 zero强大进化
Deep Agent Released R1-V: Reinforcing Super Generalization in Vision-Language Models with Cost-Effective Reinforcement Learning to Outperform Larger Models
Memorization vs. Generalization: How Supervised Fine-Tuning SFT and Reinforcement Learning RL Shape Foundation Model Learning
Meta AI Introduces MR.Q: A Model-Free Reinforcement Learning Algorithm with Model-Based Representations for Enhanced Generalization
机器人泛化怎么做？银河通用、灵初智能、星海图给出三种路径
When does capability elicitation bound risk?
大模型能学会外星语言吗？
Nat. Mach. Intell. | 基准数据集的泛化评估不真实？哈佛医学院提出SPECTRA
