专栏文章 - 百家AI

2026-1-19

2026 AI Memory最新综述：从理论到实战，一文读懂AI记忆的进化全景 2026 AI Memory Survey: From Theory to Practice, Understanding the Evolution of AI Memory

2025-12-19

智能体自主优化！LightSearcher工具调用减 39.6%、推理快 48.6% Agent Self-Optimization! LightSearcher reduces tool calls by 39.6% and speeds up inference by 48.6%

2025-12-04

WSDM 2026| 句子级溯源大模型C²-Cite 重塑大模型可信度 WSDM 2026 | Sentence-level Attribution Model C²-Cite Reshapes LLM Trustworthiness

2025-10-15

LLM工业级自进化：北邮与腾讯AI Lab提出MoE-CL架构，解决大模型持续学习核心痛点 Industrial LLM Self-Evolution: BUPT & Tencent AI Lab propose MoE-CL for Continual Learning

2025-06-08

告别 "失忆" AI！首个大模型记忆操作系统（MemoryOS）开源框架来了！ No More "Amnesia" AI! The first MemoryOS open-source framework for LLMs is here!

2025-05-28

GMoE| 大模型优化密钥：GMoE 用图神经网络破解 MoE「冷热失衡」 GMoE | The Optimization Key: Solving MoE Load Imbalance via Graph Neural Networks

2025-05-26

KG-Retriever | 北邮百家AI团队解锁垂域KG检索新范式 KG-Retriever | BUPT Baijia AI Team Unlocks New Paradigm for Domain KG Retrieval

2025-04-27

北邮-腾讯联合提出多任务提示调优推荐框架MPT-Rec，实现效率性能双突破！ BUPT & Tencent jointly propose MPT-Rec: Multi-Task Prompt Tuning for Recommender Systems

2025-01-06

北邮百家（BaiJia）大模型：用AI对话古人，开启沉浸式历史体验 BUPT BaiJia LLM: Conversing with the Ancients via AI for Immersive History

专栏文章 Articles