Podcast Episodes
Back to Search
【第156期】Mobile-Agent-E:智能手机上的Agent
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
Summary
This research introduces Mobil…
1 year, 1 month ago
【第155期】IntellAgent:多智能体框架
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems
Summary
This document int…
1 year, 1 month ago
【第154期】Agentic RAG survey
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
Summary
The provided text is a survey o…
1 year, 1 month ago
【第153期】Chain-of-Agents框架
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
Summary
Large language model…
1 year, 1 month ago
【第152期】Kimi k1.5
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Summary
This technical report introduces Kimi k1.5,…
1 year, 1 month ago
【第151期】Humanity’s Last Exam
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
Humanity’s Last Exam
Summary
"Humanity's Last Exam" (HLE) introduces a new benchmark designed to assess…
1 year, 2 months ago
【第150期】DeepSeek-R1
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Summary
DeepSeek-AI …
1 year, 2 months ago
【第149期】Mind Evolution:一种进化搜索策略
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
Evolving Deeper LLM Thinking
Summary
This paper introduces Mind Evolution, a novel evolutionary search …
1 year, 2 months ago
【第148期】Embodied-RAG:赋予机器人在复杂环境中更强的记忆和推理能力
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
Summary
This paper in…
1 year, 2 months ago
【第147期】VideoRAG
Seventy3: 用NotebookLM将论文生成播客,让大家跟着AI一起进步。
今天的主题是:
VideoRAG: Retrieval-Augmented Generation over Video Corpus
Summary
VideoRAG is a novel framework that e…
1 year, 2 months ago