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

00:17:49

【第173期】Docling：开源的文档转换工具包

Seventy3 ·

2025/03/22

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：Docling: An Efficient Open-Source Toolkit for AI-driven Document ConversionSummaryDocling is a new open-source toolkit for document conversion, designed to parse various document formats into a structured representation using AI models for layout analysis and table recognition. It aims to provide an efficient and customizable solution for tasks like document understanding and information extraction, and it supports local execution, integrations with

zh-cn

00:13:00

【第172期】AI 安全性方面使用强化学习（RL）的挑战

Seventy3 ·

2025/03/21

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：Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning StrategiesSummaryThe provided paper investigates the challenges of using Reinforcement Learning (RL) to ensure AI safety, particularly in models like DeepSeek-R1. It highlights limitations such as reward hacking, language inconsistencies, and difficulties in generalizing to new situations. The paper compares RL with Supervised Fine-Tuning (SFT), noting

zh-cn

00:18:07

【第171期】DivPO：Diverse Preference Optimization

Seventy3 ·

2025/03/20

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：Diverse Preference OptimizationSummaryThe research introduces Diverse Preference Optimization (DivPO), a novel training method designed to enhance the diversity of language model outputs while maintaining quality. Current optimization techniques often lead to a reduction in diversity, especially in creative tasks. DivPO addresses this by selecting preference pairs based on both quality and diversity, contrasting diverse, high-reward responses with less

zh-cn

00:10:03

【第170期】Chain of RAG

Seventy3 ·

2025/03/19

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-Retrieval Augmented GenerationSummaryThis paper introduces Chain-of-Retrieval Augmented Generation (CoRAG), a method that allows language models to iteratively retrieve and reason over relevant information. Unlike traditional RAG, CoRAG dynamically reformulates queries based on the evolving information state. To train CoRAG, the authors use rejection sampling to generate intermediate retrieval chains and fine-tune models to predict the next

zh-cn

00:10:29

【第169期】LiT：Linear Diffusion Transformer

Seventy3 ·

2025/03/18

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：LiT: Delving into a Simplified Linear Diffusion Transformer for Image GenerationSummaryThe provided document introduces LiT, a Linear Diffusion Transformer, designed for efficient image generation. LiT simplifies linear attention mechanisms and employs a novel training strategy involving weight inheritance and hybrid knowledge distillation. This approach allows LiT to achieve competitive image generation results with significantly reduced training

zh-cn

00:27:39

【第168期】多机器人系统中的“观察-计算-移动”方法

Seventy3 ·

2025/03/17

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：Knowledge in multi-robot systems: an interplay of dynamics, computation and communicationSummaryThis paper bridges the gap between control theory, distributed computing, and temporal epistemic logic to analyze multi-robot systems. It formulates robot behaviors using both hybrid dynamical systems and state machines executing look-compute-move cycles, demonstrating compatibility between these models. The authors introduce the concept of "time paths" to

zh-cn

00:23:24

【第167期】GCBF+：安全的多智能体避障控制算法

Seventy3 ·

2025/03/16

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：GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent ControlSummaryThis research introduces a novel framework, GCBF+, for safe and scalable control of multi-agent systems using Graph Control Barrier Functions (GCBFs). The framework employs graph neural networks to learn GCBFs and distributed control policies, enabling agents to avoid collisions and reach goals using only local information. A key contribution is a

zh-cn

00:17:34

【第166期】underthinking：模型思考不够深入的问题

Seventy3 ·

2025/03/15

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：Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMsSummaryThis research investigates "underthinking" in large language models (LLMs), where models prematurely switch between reasoning strategies on complex tasks. The authors found that this frequent thought-switching correlates with incorrect answers and propose a metric to quantify this inefficiency. To address this, they introduce a "thought switching penalty" (TIP) during decoding,

zh-cn

00:16:09

【第165期】DeepSeek-R1 和 OpenAI 的 o3-mini 安全性比较

Seventy3 ·

2025/03/14

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：o3-mini vs DeepSeek-R1: Which One is Safer?SummaryThe study assesses the safety of two large language models (LLMs), DeepSeek-R1 and OpenAI's o3-mini, using an automated testing tool called ASTRAL. It explores how these models respond to unsafe prompts across various categories, writing styles, and persuasion techniques. The research indicates that DeepSeek-R1 exhibits significantly more unsafe behaviors compared to o3-mini, particularly in categories

zh-cn

00:17:45

【第164期】CodeMonkeys：软件工程中一种test time compute方法

Seventy3 ·

2025/03/13

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：CodeMonkeys: Scaling Test-Time Compute for Software EngineeringSummaryThe "CodeMonkeys" paper introduces a system that improves large language model (LLM) performance on software engineering tasks by scaling test-time compute. This scaling is achieved by iteratively generating and testing code edits, both serially (more iterations per attempt) and in parallel (multiple attempts simultaneously). The system identifies relevant code context, generates

zh-cn

00:16:17

【第163期】Encoder-Decoder架构的SLM

Seventy3 ·

2025/03/12

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：Return of the Encoder: Maximizing Parameter Efficiency for SLMsSummaryThis paper challenges the current trend of using decoder-only architectures for language models, particularly for smaller language models (SLMs). It argues that encoder-decoder architectures offer superior efficiency and performance in resource-constrained environments, especially regarding latency and throughput on edge devices. The researchers introduce a knowledge distillation

zh-cn

00:15:25

【第162期】ICRL：一种通用问题解决方法

Seventy3 ·

2025/03/11

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：RL + Transformer = A General-Purpose Problem SolverSummaryThis paper introduces an innovative approach called In-Context Reinforcement Learning (ICRL) that utilizes a pre-trained transformer model to solve problems, even those it hasn't seen before. The model, Llama 3.1 8B, is fine-tuned with reinforcement learning, enabling it to meta-learn and adapt to new environments with remarkable efficiency. The ICRL-trained transformer demonstrates the ability

zh-cn

00:16:25

【第161期】VideoWorld：从无标签视频数据中学习复杂知识

Seventy3 ·

2025/03/10

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：VideoWorld: Exploring Knowledge Learning from Unlabeled VideosSummaryThe paper introduces VideoWorld, a novel approach to learning complex knowledge directly from unlabeled video data. It presents a video generation model that, unlike traditional language models, learns rules, reasoning, and planning skills solely from visual input, exemplified through tasks like video-based Go and robotic control. A key finding is that visual change representation is

zh-cn

00:19:22

【第160期】AI Red Teaming实践经验总结

Seventy3 ·

2025/03/09

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：Lessons From Red Teaming 100 Generative AI ProductsSummaryAI red teaming, a practice for assessing the safety and security of generative AI systems, is explored in this paper, drawing from Microsoft's experience red teaming over 100 GenAI products. The authors share their internal threat model ontology and eight lessons learned, highlighting the importance of understanding system capabilities, prioritizing simple attack techniques, and recognizing that

zh-cn

00:18:58

【第159期】TheAgentCompany：评估 AI 代理在真实工作场景中执行任务的新基准

Seventy3 ·

2025/03/08

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：TheAgentCompany: Benchmarking LLM Agents on Consequential Real World TasksSummaryTheAgentCompany is introduced as a new benchmark for evaluating AI agents on real-world workplace tasks. This benchmark simulates a software company environment where agents perform tasks like web browsing, coding, and communication with simulated colleagues. The paper assesses the performance of various large language models (LLMs) on these tasks, revealing that even the

zh-cn

00:17:31

【第158期】图像生成CoT是什么样的

Seventy3 ·

2025/03/07

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：Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by StepSummaryThis research explores enhancing autoregressive image generation using Chain-of-Thought (CoT) reasoning strategies commonly applied to language models. The study adapts techniques like test-time verification and preference alignment to improve image quality and text alignment. The authors introduce a Potential Assessment Reward Model (PARM) and PARM++ to

zh-cn

00:21:18

【第157期】DiffuEraser：利用稳定扩散技术修复视频

Seventy3 ·

2025/03/06

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：DiffuEraser: A Diffusion Model for Video InpaintingSummaryDiffuEraser is a novel video inpainting model leveraging stable diffusion to address limitations in existing methods. Current video inpainting techniques often struggle with blurring and temporal inconsistencies, especially with large masked areas. DiffuEraser enhances detail and coherence by incorporating prior information to guide the diffusion process and suppress unwanted artifacts. To

zh-cn

00:12:15

【第156期】Mobile-Agent-E：智能手机上的Agent

Seventy3 ·

2025/03/05

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 TasksSummaryThis research introduces Mobile-Agent-E, an innovative mobile assistant designed to handle complex, real-world tasks on smartphones. The system employs a hierarchical multi-agent framework with a self-evolution module, enabling it to learn from past experiences and improve its performance over time. Mobile-Agent-E separates high-level planning from low-level action execution,

zh-cn

00:12:38

【第155期】IntellAgent：多智能体框架

Seventy3 ·

2025/03/04

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 SystemsSummaryThis document introduces IntellAgent, a novel, open-source multi-agent framework designed to evaluate conversational AI systems. IntellAgent addresses the shortcomings of traditional methods by automating the creation of diverse, realistic scenarios using policy-driven graph modeling, event generation, and user-agent simulations. The framework leverages a policy graph

zh-cn

00:13:14

【第154期】Agentic RAG survey

Seventy3 ·

2025/03/03

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 RAGSummaryThe provided text is a survey of Agentic Retrieval-Augmented Generation (RAG), a paradigm that enhances large language models by integrating autonomous AI agents into the RAG pipeline. This allows for dynamic retrieval strategies, contextual understanding, and iterative refinement, addressing the limitations of traditional RAG systems. The survey covers the evolution of RAG

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