Podcast Episodes
Back to Search
【第49期】Responsibility in Multi-Agent Systems
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：
Measuring Responsibility in Multi-Agent Systems
Summary
This research paper introduces a novel framewor…
1 year, 7 months ago
【第48期】测试时训练TTT（test-time training）
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：
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning
Summary
This research paper i…
1 year, 7 months ago
【第47期】LoRA vs Full Fine-tuning
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：
LoRA vs Full Fine-tuning: An Illusion of Equivalence
Summary
This research paper investigates the diffe…
1 year, 7 months ago
【第46期】大模型的数据会用完吗？
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：
Will we run out of data? Limits of LLM scaling based on human-generated data
Summary
This research pape…
1 year, 7 months ago
【第45期】SeqComm：多智能体通讯机制
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：
Multi-Agent Coordination via Multi-Level Communication
Summary
This research paper introduces a novel m…
1 year, 7 months ago
【第44期】MIPRA解读
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：
A New Generation of Rules-based Approach: Mivar-based Intelligent Planning of Robot Actions (MIPRA) a…
1 year, 7 months ago
【第43期】Reward Centering
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：
Reward Centering
Summary
This research paper investigates the effectiveness of reward centering, a tech…
1 year, 7 months ago
【第42期】SELA：使用MCTS增强LLM
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：
SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning
Summary
The source explores a new …
1 year, 7 months ago
【第41期】Multimodal RAG
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：
Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications
Summary
This research pa…
1 year, 7 months ago
【第40期】LLM使用bag of heuristics求解数学问题
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：
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
Summary
This researc…
1 year, 7 months ago