Tag
AI
- Feb 3, 2026
从传统摘要到语义合成
在大语言模型(LLM)驱动的范式下,“摘要”已不再只是面向人类读者的短文本生成任务,而是逐渐演变为机器对机器(M2M)的语义合成算子。它的核心不只是压缩文本长度,而是建立一套从非结构化文本到结构化中间表示(IR)的编译机制,将原始材料转化为可消费、可检索、可追溯、可验证、可执行的高密度语义资产。要落地这一合成管线,系统必须依托上下文工程(Context Engineering)进行全生命周期治理:决定哪些信息可以进入,哪些信息需要保留,如何压缩、组织、呈现,以及如何评估其质量。
#AI#NLP#LLM#RAG - Nov 1, 2025
Modern Recommendation System Infrastructure
Building Modern Recommendation Systems introduces a comprehensive, end-to-end pipeline that drives intelligent recommendations. The post walks through the full machine learning workflow — from raw data preparation and feature engineering to model training, deployment, real-time inference, and system monitoring.
#System Design#RecSys#Recommendation#ML system - Jun 29, 2025
The ML Factory: Building Production ML Systems
Building production ML systems is far more than selecting a model. Success requires thinking in terms of a full lifecycle: defining precise functional and non-functional requirements, designing robust data pipelines, splitting logic between models and rules, versioning and deploying models, prompts, and embeddings as coherent units, and continuously monitoring system performance and product impact.
#ML#AI#System Design#ML system - Aug 7, 2025
深度学习模型架构的演进
本文系统回顾了深度学习的发展脉络,从基础神经网络到Attention 与 Transformer的出现,再到深度生成模型的兴起,最后介绍了多模态与统一建模架构的发展趋势,展示了当前主流的模型体系。
#DL#ML#AI#模型 - Jul 9, 2025
各领域的深度学习模型
本文简要总结了深度学习在NLP、计算机视觉、信息检索和推荐系统四大主流领域的演进脉络:从早期RNN、CNN等专用模型,到Transformer全面主导,再到如今BERT/GPT、ViT、Diffusion等预训练大模型横扫各领域。核心趋势是预训练+生成式范式取代传统任务特定模型,统一建模与生成式架构正在加速推动各领域融合与新一轮创新。
#模型#AI#NLP#CV - Jan 15, 2025
大模型(LLM)关键技术:从基础到落地
#LLM#AI#大模型#Transformer - Nov 29, 2024
机器学习模型:从传统算法到生成式AI
#ML#AI - Nov 19, 2024
ML 模型生产全流程
#ML#AI#MLops - Oct 21, 2024
NLP技术与应用:从语言理解到智能生成
#NLP#AI - May 29, 2024
Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation (RAG) combines large language models with external knowledge retrieval to produce more accurate and grounded responses. The post explains why RAG was introduced, explores its key use cases and real-world applications, and discusses challenges and considerations that impact performance in practical deployments.
#LLM#AI#GenAI#NLP - Mar 18, 2024
对话系统:从人机交流走向理解与互动
本文探讨了机器学习如何推动人与机器的自然交流,从早期的对话系统到如今能够理解意图、执行任务的智能助理。近年来的趋势是向LLM + Agent 化对话系统演进,LLM 可嵌入架构中各核心模块,增强系统的理解、生成与决策能力。最终,通过引入智能代理机制,让对话系统从“能说”进一步迈向“能做”。
#NLP#AI#LLM#ML