排序方式：按更新时间排序 | 按标题排序 | 按浏览次数排序
TIGER：Recommender Systems with Generative Retrieval 生成式召回
论文   推荐系统   召回  
Soft MoE《FROM SPARSE TO SOFT MIXTURES OF EXPERTS》
论文  
Fast Inference from Transformers via Speculative Decoding
论文  
谷歌MLP - Mixer: An all - MLP Architecture for Vision
论文   谷歌  
谷歌DiLoCo: Distributed Low-Communication Training of Language Models
论文   LLM  
快手冷启动POSO: Personalized Cold Start Modules for Large-scale Recommender Systems
论文   冷启动   快手  
快手MARM: Unlocking the Future of Recommendation Systems through Memory Augmentation and Scalable Complexity
论文   快手  
论文 | ROFORMER: ENHANCED TRANSFORMER WITH ROTARY POSITION EMBEDDING、RoPE编码
论文   RoPE  
论文：Improving Item Cold - start Recommendation via Model - agnostic Conditional Variational Autoencoder
论文   冷启动  
Rethinking the Role of Pre-ranking in Large-scale E-Commerce Searching System
论文   粗排  
ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
论文   LLM   推荐系统  
阿里MIMN模型Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction
论文   阿里  
论文《Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling》学习率和批量大小
论文  
Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders,ADS自适应域缩放
论文   推荐系统   跨域推荐   字节  
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
论文   deepseek  
TPM基于树的渐进回归模型（Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation）
论文   回归问题  
论文：Large Memory Layers with Product Keys
论文  
论文：Key-Value Memory Networks for Directly Reading Documents 键值记忆网络（KV-MemNN）
论文  
论文：The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
论文   Transformer  
论文：Training Compute-Optimal Large Language Models 最优模型缩放结论
论文