牛哥精选 · 三个月

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

📝 深度技术 arXiv 机器学习 2026-06-01

Student Capacity Moderates Knowledge Distillation Effectiveness: A Systematic Study Across ResNet Teacher-Student Pairs on CIFAR-10

系统研究知识蒸馏中学生容量影响，ResNet对CIFAR-10实证揭示关键调节作用

arXiv:2605.31191v1 Announce Type: new Abstract: We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effecti…

知识蒸馏学生容量 resnet cifar-10 深度学习研究

🤖 AI·大模型 arXiv NLP 2026-05-20

Language models fail at extended rule following

最新研究揭示大语言模型在复杂多步规则遵循上的显著失败，挑战现有能力边界

arXiv:2605.02028v2 Announce Type: replace Abstract: Large language models are highly capable of answering difficult questions by retrieving, recombini…

语言模型规则遵循 ai局限性深度学习研究大模型评估

📝 深度技术 arXiv AI 2026-05-19

Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers

揭示FFN架构稀疏性如何重塑注意力计算，影响小型Transformer模型学习机制。

arXiv:2605.09403v2 Announce Type: replace-cross Abstract: Architectural choices inside the Transformer feedforward network (FFN) block do not merely a…

稀疏性 ffn架构注意力机制 transforme 深度学习研究

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Student Capacity Moderates Knowledge Distillation Effectiveness: A Systematic Study Across ResNet Teacher-Student Pairs on CIFAR-10

Language models fail at extended rule following

Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers

📅 日期