PODCAST

Seventy3

任雨山

73播客，名字取材于Sheldon最喜欢的数字，内容由NotebookLM生成，每天跟随AI读AI业界论文。

technology

All Episodes

00:14:13

【第213期】SOLOMON：专业领域中增强LLM能力

Seventy3 ·

2025/05/01

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Enhancing Reasoning to Adapt Large Language Models for Domain-Specific ApplicationsSummaryResearchers Wen and Zhang introduce SOLOMON, a novel AI architecture inspired by neuroscience, designed to improve the adaptability of large language models (LLMs) for specialized tasks. Their work demonstrates SOLOMON's effectiveness in semiconductor layout design, where it uses prompt engineering and

zh-cn

00:23:43

【第212期】Self-Backtracking：自我回溯

Seventy3 ·

2025/04/30

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language ModelsSummaryThis paper introduces Self-Backtracking, a novel technique to enhance the reasoning of large language models (LLMs) by enabling them to internally manage a search process with backtracking capabilities. The method trains LLMs to recognize suboptimal reasoning paths and autonomously backtrack to explore

zh-cn

00:18:57

【第211期】大型语言模型API中的提示缓存机制研究

Seventy3 ·

2025/04/29

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Auditing Prompt Caching in Language Model APIsSummaryThe provided research paper investigates prompt caching in large language model APIs, revealing that this optimization can lead to data-dependent timing variations exploitable for side-channel attacks. Through statistical audits on various real-world APIs, the authors detected global cache sharing in several providers, including OpenAI, which poses

zh-cn

00:18:39

【第210期】RLSP：Reinforcement Learning via Self-Play

Seventy3 ·

2025/04/28

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：On the Emergence of Thinking in LLMs I: Searching for the Right IntuitionSummaryThe provided research explores how large language models (LLMs) can be transformed into more capable reasoning agents, termed large reasoning models (LRMs), by enabling a "thinking" process during inference. It introduces Reinforcement Learning via Self-Play (RLSP), a post-training framework that encourages guided search

zh-cn

00:17:31

【第209期】Brain2Qwerty：非侵入式脑机接口

Seventy3 ·

2025/04/27

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Brain-to-Text Decoding: A Non-invasive Approach via TypingSummaryResearchers introduce Brain2Qwerty, a novel non-invasive brain-computer interface system that decodes typed sentences from the brain activity of healthy individuals using EEG and MEG. This new deep learning architecture translates brain signals recorded while participants typed memorized sentences on a QWERTY keyboard. The MEG-based

zh-cn

00:23:21

【第208期】YOLOv12：注意力中心的实时目标检测模型

Seventy3 ·

2025/04/26

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：YOLOv12: Attention-Centric Real-Time Object DetectorsSummaryResearchers introduce YOLOv12, an attention-centric framework for real-time object detection, overcoming the typical speed limitations of attention mechanisms compared to CNNs. This new architecture incorporates an area attention module and residual efficient layer aggregation networks (R-ELAN) to enhance both speed and accuracy. Experiments

zh-cn

00:13:06

【第207期】PC-Agent：PC端的Multi-Agent框架

Seventy3 ·

2025/04/25

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PCSummaryThe provided research paper introduces PC-Agent, a novel hierarchical framework designed to automate complex tasks on personal computers. It addresses the challenges posed by intricate PC environments and multi-application workflows by employing an Active Perception Module (APM) for enhanced screen

zh-cn

00:23:27

【第206期】“无噪声条件”模型 Kaiming He

Seventy3 ·

2025/04/24

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Is Noise Conditioning Necessary for Denoising Generative Models?SummaryThis research investigates the common belief that noise conditioning is essential for denoising generative models. The authors surprisingly found that many of these models can still function effectively, and sometimes even better, without explicitly providing the noise level. They provide a theoretical analysis explaining this

zh-cn

00:18:01

【第205期】Agentic Reasoning：推理性代理框架

Seventy3 ·

2025/04/23

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Agentic Reasoning: Reasoning LLMs with Tools for the Deep ResearchSummaryThis technical report introduces Agentic Reasoning, a novel framework designed to enhance the reasoning capabilities of large language models (LLMs). Unlike traditional methods relying solely on internal knowledge, Agentic Reasoning equips LLMs with external tools accessed through specialized agents, such as a web search agent,

zh-cn

00:21:11

【第204期】OmniParser：纯视觉GUI Agent

Seventy3 ·

2025/04/22

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：OmniParser for Pure Vision Based GUI AgentSummaryThe provided research paper introduces OMNIPARSER, a novel method for understanding user interface screenshots by identifying interactive elements and their functions. This approach enhances the ability of large vision-language models like GPT-4V to act as agents on various operating systems and applications. OMNIPARSER utilizes fine-tuned models for

zh-cn

00:15:17

【第203期】Zep：用临时知识图谱作Agent记忆

Seventy3 ·

2025/04/21

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Zep: A Temporal Knowledge Graph Architecture for Agent MemorySummaryThis paper introduces Zep, a novel memory layer service for AI agents powered by Graphiti, a temporally-aware knowledge graph engine. Zep aims to overcome limitations of current retrieval-augmented generation (RAG) frameworks by dynamically integrating unstructured conversation data and structured business data while preserving

zh-cn

00:12:59

【第202期】MoBA：Mixture of Block Attention

Seventy3 ·

2025/04/20

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：MoBA: Mixture of Block Attention for Long-Context LLMsSummaryThe provided technical report introduces Mixture of Block Attention (MoBA), a novel method to improve the efficiency of long-context large language models. MoBA applies the Mixture of Experts principle to the attention mechanism, allowing the model to selectively focus on relevant blocks of information instead of the entire context. This

zh-cn

00:13:37

【第201期】LIMR：训练数据智能选择

Seventy3 ·

2025/04/19

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：LIMR: Less is More for RL ScalingSummaryThis paper explores the efficiency of reinforcement learning (RL) data for enhancing large language models' reasoning abilities. It challenges the idea that more RL training data automatically leads to better performance. The authors introduce Learning Impact Measurement (LIM), a method to strategically select a small subset of highly impactful training

zh-cn

00:28:59

【第200期】用LLM做oi题目怎么样？

Seventy3 ·

2025/04/18

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Competitive Programming with Large Reasoning ModelsSummaryThis document from OpenAI explores the advancements of large reasoning models in competitive programming and software engineering. It details the development and evaluation of models like o1, o1-ioi (specialized for the International Olympiad in Informatics), and the more advanced o3. The findings indicate that scaling general-purpose

zh-cn

00:09:29

【第199期】LLaDA：Large Language Diffusion Models

Seventy3 ·

2025/04/17

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Large Language Diffusion ModelsSummaryThe provided document introduces LLaDA, a novel language model that utilizes a diffusion process rather than the conventional autoregressive method. This work challenges the long-held belief that autoregressive modeling is the only path to creating effective large language models. LLaDA operates by learning to predict masked tokens through a forward masking and

zh-cn

00:24:05

【第198期】CODE I/O：通过预测代码输入输出进行推理

Seventy3 ·

2025/04/16

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：CODEI/O: Condensing Reasoning Patterns via Code Input-Output PredictionSummaryThe provided research paper introduces CODEI/O, a novel method for enhancing the reasoning capabilities of large language models by training them to predict code inputs and outputs using natural language rationales. This approach leverages the structured nature of code to expose models to diverse reasoning patterns, such as

zh-cn

00:16:15

【第197期】ReasonFlux：层级强化学习进行推理

Seventy3 ·

2025/04/15

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought TemplatesSummaryThe provided research paper introduces ReasonFlux, a novel framework designed to enhance the mathematical reasoning capabilities of large language models (LLMs). This system utilizes a structured library of thought templates and employs hierarchical reinforcement learning to guide LLMs in planning optimal reasoning paths

zh-cn

00:15:40

【第196期】递归深度Test-Time Compute

Seventy3 ·

2025/04/14

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth ApproachSummaryThis paper introduces a novel language model architecture that enhances reasoning by iteratively processing information in a latent space rather than solely generating more tokens. This "recurrent depth" approach allows the model to increase its computational effort at test time without needing specialized training

zh-cn

00:21:04

【第195期】AI大模型已经超过自我复制红线

Seventy3 ·

2025/04/13

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Frontier AI systems have surpassed the self-replicating red lineSummaryResearchers at Fudan University investigated the self-replication capabilities of frontier AI systems. Their paper presents findings that Meta's Llama3-70B-Instruct and Alibaba's Qwen2.5-72B-Instruct, contrary to reports from leading AI corporations about their own models, have already surpassed the "self-replicating red line."

zh-cn

00:16:04

【第194期】AI在经济各领域中的实际应用情况研究

Seventy3 ·

2025/04/12

Seventy3：借助NotebookLM的能力进行论文解读，专注人工智能、大模型、机器人算法方向，让大家跟着AI一起进步。进群添加小助手微信：seventy3_podcast备注：小宇宙今天的主题是：Which Economic Tasks are Performed with AI? Evidence from Millions of Claude ConversationsSummaryThis research paper analyzes millions of Claude.ai conversations to provide empirical evidence of how AI is being used across the economy. The study maps these conversations to occupational tasks, revealing that software development and writing tasks currently see the highest AI usage. The analysis

zh-cn

578 results

Seventy3

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs