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

00:17:08

【第193期】LM2：大型记忆模型

Seventy3 ·

2025/04/11

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：LM2: Large Memory ModelsSummaryThis paper introduces the Large Memory Model (LM2), a novel Transformer architecture enhanced with an auxiliary memory module to improve performance on tasks requiring long context and complex reasoning. The LM2's memory component stores and retrieves contextual information, interacting with input tokens via cross attention and updating through gating mechanisms, while

zh-cn

00:24:08

【第192期】Transformer架构的局限

Seventy3 ·

2025/04/10

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 Limitations of the Transformer ArchitectureSummaryThis paper explores theoretical limitations of the Transformer architecture, a cornerstone of large language models. Through the lens of Communication Complexity, the authors demonstrate that a single Transformer layer struggles with function composition when dealing with sufficiently large data domains, a weakness empirically evident even with

zh-cn

00:20:27

【第191期】Value-Based RL可拓展性研究

Seventy3 ·

2025/04/09

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：Value-Based Deep RL Scales PredictablySummaryThis research investigates the scaling properties of value-based deep reinforcement learning methods. The authors demonstrate that despite common beliefs, the performance of these methods can be predicted as computational resources and training data increase. They establish predictable relationships between key hyperparameters like batch size and learning

zh-cn

00:20:26

【第190期】LLM推理中有前景的方法综述

Seventy3 ·

2025/04/08

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：Advancing Reasoning in Large Language Models: Promising Methods and ApproachesSummaryThis document provides a survey of techniques aimed at improving the reasoning abilities of Large Language Models (LLMs), which often struggle with complex logical tasks despite their proficiency in natural language processing. The author categorizes these methods into prompting strategies, such as chain-of-thought

zh-cn

00:14:04

【第189期】MaAS：优化代理超网（agentic supernet）的多智能体系统

Seventy3 ·

2025/04/07

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：Multi-agent Architecture Search via Agentic SupernetSummaryThe provided text introduces MaAS, a novel framework for automating the design of multi-agent systems powered by Large Language Models. Instead of searching for a single optimal architecture, MaAS optimizes an agentic supernet, which is a probabilistic distribution of various agent configurations. This approach allows MaAS to dynamically

zh-cn

00:13:41

【第188期】Self-MoA：多Agent会比单个Agent强吗？

Seventy3 ·

2025/04/06

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：Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?SummaryThis paper investigates Mixture-of-Agents (MoA), a method that combines outputs from different large language models (LLMs), and introduces Self-MoA, which aggregates multiple outputs from a single top-performing LLM. Surprisingly, Self-MoA often outperforms standard MoA across various benchmarks by better

zh-cn

00:13:38

【第187期】Syntriever：用合成数据训练retriever

Seventy3 ·

2025/04/05

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：Syntriever: How to Train Your Retriever with Synthetic Data from LLMsSummaryThe provided research paper introduces Syntriever, a novel framework for training information retrieval systems by leveraging synthetic data generated from large language models (LLMs). This approach consists of two key stages: distillation, where relevant and irrelevant passages are synthesized using LLMs and used to train

zh-cn

00:12:38

【第186期】CoAT：MCTS+memory增强推理的框架

Seventy3 ·

2025/04/04

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：CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models ReasoningSummaryThe provided research paper introduces CoAT, a novel framework designed to enhance the reasoning capabilities of large language models (LLMs). Inspired by human cognition, CoAT integrates Monte Carlo Tree Search (MCTS) for structured exploration of reasoning paths with an associative memory mechanism that

zh-cn

00:18:05

【第185期】RAG Foundry：简化RAG的开源框架

Seventy3 ·

2025/04/03

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：RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented GenerationSummaryThe provided document introduces RAG FOUNDRY, an open-source framework designed to streamline the development and evaluation of Retrieval-Augmented Generation (RAG) systems for large language models. This framework integrates data handling, model training, inference, and evaluation into a unified workflow, enabling

zh-cn

00:17:19

【第184期】Diffusion Planner：基于Transformer的闭环自动驾驶算法

Seventy3 ·

2025/04/02

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：Diffusion-Based Planning for Autonomous Driving with Flexible GuidanceSummaryThe provided research paper introduces Diffusion Planner, a novel method for autonomous driving that utilizes diffusion models to achieve human-like planning in complex environments. This approach jointly models motion prediction and planning without relying on traditional rule-based refinements, addressing limitations of

zh-cn

00:12:18

【第183期】慢思考滚雪球错误如何利用

Seventy3 ·

2025/04/01

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：Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct ReasoningSummaryThis paper examines "slow-thinking" in large language models (LLMs), where increased computation time enhances reasoning. It theoretically analyzes how errors accumulate during LLM reasoning, termed "snowball errors," linking them to the decreasing probability of correct reasoning through information

zh-cn

00:15:51

【第182期】庆祝更新半年文中有彩蛋 || Long CoT Reasoning in LLMs

Seventy3 ·

2025/03/31

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：Demystifying Long Chain-of-Thought Reasoning in LLMsSummaryThis paper investigates how large language models (LLMs) achieve long chain-of-thought (CoT) reasoning, which involves extended, step-by-step thought processes for complex tasks. The authors explore the roles of supervised fine-tuning (SFT) and reinforcement learning (RL) in enabling this capability. Key findings highlight that while SFT on long CoT data improves performance and facilitates

zh-cn

00:24:16

【第181期】ASAP：两阶段框架弥合仿真与现实物理之间的差距

Seventy3 ·

2025/03/30

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：ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body SkillsSummaryThe provided research paper introduces ASAP, a novel two-stage framework designed to bridge the gap between simulated and real-world physics for humanoid robots, enabling them to perform complex, agile movements. The first stage involves pre-training control policies in simulation using human motion data. The second stage deploys these policies in the

zh-cn

00:20:11

【第180期】LLM-AutoDiff：一个基于梯度的自动化提示工程

Seventy3 ·

2025/03/29

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：LLM-AutoDiff: Auto-Differentiate Any LLM WorkflowSummaryThe provided research introduces LLM-AutoDiff, a novel framework for automating prompt engineering for complex Large Language Model workflows. This system extends gradient-based optimization to multi-step and cyclic LLM applications by treating textual inputs as trainable parameters. LLM-AutoDiff constructs a graph representing the workflow, enabling a "backward engine" LLM to generate feedback

zh-cn

00:16:33

【第179期】s1: Simple test-time scaling

Seventy3 ·

2025/03/28

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：s1: Simple test-time scalingSummaryThis research explores improving language model reasoning through a technique called test-time scaling, where extra computation during inference enhances performance. The authors introduce s1K, a small, high-quality dataset of reasoning problems, and budget forcing, a method to control the model's computational effort at test time. By finetuning a language model on s1K and using budget forcing, they achieve strong

zh-cn

00:17:22

【第178期】spurious forgetting：大模型的虚假遗忘

Seventy3 ·

2025/03/27

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：Spurious Forgetting in Continual Learning of Language ModelsSummaryThis paper introduces the concept of spurious forgetting in large language models during continual learning, distinguishing it from actual knowledge loss and attributing it to the disruption of task alignment. The authors demonstrate through experiments and theoretical analysis that early training on new tasks can misalign the model, particularly in the bottom layers. To address this,

zh-cn

00:14:29

【第177期】学习率Scheduler研究分析

Seventy3 ·

2025/03/26

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 Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model TrainingSummaryThis paper explores the surprising parallels between learning-rate schedules used in large model training and theoretical performance bounds from convex optimization. It demonstrates that a simple learning-rate schedule with a constant phase followed by a linear cooldown mirrors the behavior predicted by theory, even for non-convex

zh-cn

00:15:02

【第176期】TokenVerse：文本到图像生成的新方法

Seventy3 ·

2025/03/25

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：TokenVerse: Versatile Multi-concept Personalization in Token Modulation SpaceSummaryTokenVerse introduces a new method for multi-concept personalization in text-to-image generation. The technique extracts visual elements and attributes from single or multiple images using only text captions and a pre-trained diffusion model. By leveraging the modulation space within Diffusion Transformers, TokenVerse disentangles complex concepts like objects, poses,

zh-cn

00:13:06

【第175期】TensorLLM：使用多头自注意力提升模型能力

Seventy3 ·

2025/03/24

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：TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMsSummaryThis research introduces TensorLLM, a novel framework for improving the reasoning abilities and compression of Large Language Models (LLMs) by focusing on the Multi-Head Attention (MHA) block. The method employs multi-head tensorisation and Tucker decomposition to denoise and compress MHA weights by enforcing a shared higher-dimensional subspace across

zh-cn

00:12:34

【第174期】MMOA-RAG：Multi-Agent RL for Enhanced RAG

Seventy3 ·

2025/03/23

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：Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement LearningSummaryThe paper introduces MMOA-RAG, a novel approach to improve Retrieval-Augmented Generation (RAG) by framing it as a multi-agent reinforcement learning problem. It addresses the issue of independently optimized RAG components by treating each module (query rewriting, document retrieval, etc.) as an individual agent. MMOA-RAG uses multi-agent reinforcement learning

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