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

00:14:46

【第153期】Chain-of-Agents框架

Seventy3 ·

2025/03/02

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 TasksSummaryLarge language models (LLMs) struggle with long contexts due to limitations in processing extensive information. The "Chain-of-Agents" (CoA) framework addresses this by using multiple LLM agents that collaborate to process long documents. CoA divides the input into segments, assigns each segment to a worker agent, and then uses a manager agent to integrate the information

zh-cn

00:22:03

【第152期】Kimi k1.5

Seventy3 ·

2025/03/01

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 LLMsSummaryThis technical report introduces Kimi k1.5, a multimodal large language model trained with reinforcement learning (RL). The report highlights the model's training techniques, including long context scaling and policy optimization, emphasizing a simplistic yet effective RL framework. Kimi k1.5 achieves state-of-the-art reasoning performance across several benchmarks, even outperforming models

zh-cn

00:11:51

【第151期】Humanity’s Last Exam

Seventy3 ·

2025/02/28

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：Humanity’s Last ExamSummary"Humanity's Last Exam" (HLE) introduces a new benchmark designed to assess the knowledge of large language models (LLMs) at the frontier of human expertise. This dataset contains 3,000 multiple-choice and short-answer questions across various subjects, emphasizing deep reasoning skills and resistance to simple internet retrieval. The questions undergo a rigorous review process by subject-matter experts to ensure difficulty

zh-cn

00:15:30

【第150期】DeepSeek-R1

Seventy3 ·

2025/02/27

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：DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningSummaryDeepSeek-AI introduces DeepSeek-R1-Zero and DeepSeek-R1, reasoning-focused large language models. DeepSeek-R1-Zero uses reinforcement learning (RL) without supervised fine-tuning (SFT) to achieve remarkable reasoning capabilities. DeepSeek-R1 builds upon this by incorporating multi-stage training and "cold-start" data before RL, achieving results comparable to

zh-cn

00:30:53

【第149期】Mind Evolution：一种进化搜索策略

Seventy3 ·

2025/02/26

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：Evolving Deeper LLM ThinkingSummaryThis paper introduces Mind Evolution, a novel evolutionary search strategy for enhancing the problem-solving capabilities of Large Language Models (LLMs) in natural language planning. The method uses an LLM to generate, combine, and refine potential solutions iteratively, guided by feedback from an evaluator. Mind Evolution outperforms existing inference strategies by effectively leveraging inference time compute

zh-cn

00:16:57

【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 ·

2025/02/25

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：Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and GenerationSummaryThis paper introduces Embodied-RAG, a novel framework designed to equip robots with enhanced memory and reasoning capabilities in complex environments. It tackles challenges in applying Retrieval-Augmented Generation (RAG) to robotics by constructing a hierarchical semantic forest for efficient knowledge storage and retrieval. Embodied-RAG integrates multimodal data

zh-cn

00:13:40

【第147期】VideoRAG

Seventy3 ·

2025/02/24

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：VideoRAG: Retrieval-Augmented Generation over Video CorpusSummaryVideoRAG is a novel framework that enhances Retrieval-Augmented Generation (RAG) by incorporating video content. Unlike traditional RAG, which primarily uses text, VideoRAG dynamically retrieves relevant videos and integrates both visual and textual information from them to generate more accurate and contextually rich answers. This approach leverages Large Video Language Models (LVLMs) to

zh-cn

00:22:01

【第146期】如何训练能量模型EBM

Seventy3 ·

2025/02/23

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：How to Train Your Energy-Based ModelsSummaryEnergy-Based Models (EBMs) offer a flexible approach to probabilistic modeling by specifying probability up to a normalizing constant, enabling the use of versatile architectures. The challenge lies in training these models due to the intractable normalizing constant. This document introduces and compares modern EBM training methods, focusing on Maximum Likelihood with Markov Chain Monte Carlo (MCMC), Score

zh-cn

00:16:55

【第145期】扩散模型的Inference-Time Scaling

Seventy3 ·

2025/02/22

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：Inference-Time Scaling for Diffusion Models beyond Scaling Denoising StepsSummaryThis research explores enhancing diffusion models by scaling inference-time computation beyond simply increasing denoising steps. The authors propose a search framework that identifies better noises for the diffusion sampling process. This framework considers verifiers for feedback and algorithms to find noise candidates. Experiments on image generation show that

zh-cn

00:23:51

【第144期】Transformer-Squared：自适应LLM框架

Seventy3 ·

2025/02/21

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：Transformer-Squared: Self-adaptive LLMsSummaryThis research paper introduces Transformer2, a novel self-adaptive large language model (LLM) framework. Transformer2 uses Singular Value Fine-tuning (SVF), a parameter-efficient method, to train "expert" vectors for specific tasks using reinforcement learning. During inference, a two-pass mechanism dynamically combines these experts based on the input prompt, significantly improving performance over

zh-cn

00:20:44

【第143期】构建能够终身学习的大型语言模型（LLM）代理

Seventy3 ·

2025/02/20

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：Lifelong Learning of Large Language Model based Agents: A RoadmapSummaryThis paper surveys techniques for building large language model (LLM) agents capable of lifelong learning. It categorizes key agent components into perception, memory, and action modules, emphasizing how these modules enable continuous adaptation and mitigate catastrophic forgetting. The authors explore various strategies for each module, including multimodal perception, diverse

zh-cn

00:11:35

【第142期】Titans：神经长期记忆模块

Seventy3 ·

2025/02/19

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：Titans: Learning to Memorize at Test TimeSummaryThis research paper introduces Titans, a novel family of neural architectures designed to improve long-term memory in sequence modeling. Titans incorporate a new neural long-term memory module that learns to memorize historical context at test time, addressing the limitations of Transformers and existing recurrent models. The model uses a "surprise" metric to determine what information to remember and a

zh-cn

00:18:15

【第141期】O1 Replication Journey：Part 3

Seventy3 ·

2025/02/18

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：O1 Replication Journey -- Part 3: Inference-time Scaling for Medical ReasoningSummaryThis research paper investigates the effectiveness of inference-time scaling in large language models (LLMs) for medical reasoning tasks. The authors explore how increasing the processing time during inference improves the accuracy of LLMs on complex medical benchmarks like MedQA and JAMA Clinical Challenges. They introduce a novel journey learning approach, using

zh-cn

00:17:57

【第140期】CNCD：新类型发现

Seventy3 ·

2025/02/17

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：CLIP-guided continual novel class discoverySummaryThis research paper introduces a novel method for Continual Novel Class Discovery (CNCD), a challenging machine learning problem focusing on teaching a model new classes without forgetting previously learned ones, especially when old data is unavailable. The proposed method leverages the CLIP model for guidance in identifying new classes and uses techniques like CutMix and prototype adaptation to

zh-cn

00:12:25

【第139期】多语种控制机器人的能力评估

Seventy3 ·

2025/02/16

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：Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art ModelsSummaryThis research paper evaluates the performance of several multilingual Small Language Models (SLMs) and one Arabic-centric Large Language Model (LLM) on vision-and-language navigation (VLN) tasks. Using the NavGPT framework and a bilingual (English and Arabic) version of the R2R dataset, the study assesses the models' reasoning and planning

zh-cn

00:16:45

【第138期】ParGo：弥合视觉与语言之间的鸿沟

Seventy3 ·

2025/02/15

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：ParGo: Bridging Vision-Language with Partial and Global ViewsSummaryThis research introduces ParGo, a novel vision-language projector designed to improve multimodal large language models (MLLMs). ParGo bridges the gap between vision and language by integrating both global and partial views of images, addressing the limitations of previous methods that overemphasize prominent regions. A new dataset, ParGoCap-1M-PT, containing one million

zh-cn

00:30:01

【第137期】Agents, Sims and Assistants

Seventy3 ·

2025/02/14

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：Agents Are Not EnoughSummaryThis research paper argues that current AI agents, while experiencing a resurgence, are insufficient for creating truly effective and sustainable AI systems. The authors analyze past failures of various agent architectures, identifying limitations in generalization, scalability, coordination, robustness, and ethical considerations. They propose a new ecosystem incorporating Agents, Sims (user representations), and Assistants

zh-cn

00:14:30

【第136期】R3GAN：简化的生成对抗网络

Seventy3 ·

2025/02/13

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：The GAN is dead; long live the GAN! A Modern GAN BaselineSummaryThis NeurIPS 2024 paper introduces R3GAN, a simplified Generative Adversarial Network (GAN) that achieves state-of-the-art performance. The authors achieve this by developing a novel, mathematically well-behaved loss function that eliminates the need for the ad-hoc training tricks common in previous GANs. This improved loss enables the use of modern neural network architectures, resulting

zh-cn

00:10:51

【第135期】Search-o1：文档中的推理

Seventy3 ·

2025/02/12

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：Search-o1: Agentic Search-Enhanced Large Reasoning ModelsSummaryThe paper introduces Search-o1, a framework enhancing large reasoning models (LRMs) by integrating an agentic search workflow. This allows the LRM to dynamically retrieve external knowledge when encountering uncertainties during complex reasoning tasks. A key component is the Reason-in-Documents module, which refines retrieved information to maintain coherent reasoning. Experiments across

zh-cn

00:16:38

【第134期】DPO Kernels：通过结合核方法来增强直接偏好优化

Seventy3 ·

2025/02/11

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：DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference OptimizationSummaryThis research paper introduces DPO-Kernels, an improved method for aligning large language models (LLMs) with human preferences. It enhances Direct Preference Optimization (DPO) by incorporating kernel methods for richer feature transformations and diverse divergence measures for increased robustness. A data-driven approach

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