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

00:19:16

【第73期】HiAR-ICL：LLM推理的ICL

Seventy3 ·

2024/12/12

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：Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTSSummaryThis research paper introduces HiAR-ICL, a novel framework for improving in-context learning (ICL) in large language models (LLMs), particularly for complex mathematical reasoning. Instead of relying solely on example demonstrations, HiAR-ICL uses Monte Carlo Tree Search (MCTS) to automatically generate and select higher-level reasoning patterns, effectively

zh-cn

00:23:00

【第72期】LLM-Brained GUI Agents: A Survey

Seventy3 ·

2024/12/11

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：Large Language Model-Brained GUI Agents: A SurveySummaryThis paper surveys the development and application of Large Language Model (LLM)-powered Graphical User Interface (GUI) agents for automating tasks across various platforms (web, mobile, desktop). It examines the evolution of GUI automation from rule-based systems to intelligent agents leveraging LLMs, computer vision, and reinforcement learning. The authors detail the architecture and workflow of

zh-cn

00:27:35

【第71期】英伟达的audio大模型Fugatto

Seventy3 ·

2024/12/10

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：Fugatto 1：Foundational Generative Audio Transformer Opus 1SummaryThe document describes Fugatto, a novel generalist audio synthesis and transformation model capable of following diverse text instructions, optionally incorporating audio inputs. It addresses challenges in audio generation by introducing a specialized dataset creation strategy and ComposableART, an inference-time technique for composing instructions. ComposableART extends classifier-free

zh-cn

00:14:58

【第70期】O1 Replication Journey：Part 2

Seventy3 ·

2024/12/09

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：O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?SummaryThis research paper examines the replication of OpenAI's O1 model, focusing on a knowledge distillation method. The authors demonstrate that a simpler distillation approach, combined with fine-tuning, surpasses the O1-preview model's performance on mathematical reasoning tasks. They also explore the generalization capabilities of

zh-cn

00:15:36

【第69期】O1 Replication Journey：Part 1

Seventy3 ·

2024/12/08

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：O1 Replication Journey: A Strategic Progress Report -- Part 1SummaryThis research report details a team's effort to replicate OpenAI's O1 language model, focusing on transparent documentation of their process, including successes and failures. A key finding is the "journey learning" paradigm, which prioritizes learning the complete problem-solving process, not just the solution, showing significant performance improvements. The report contrasts this

zh-cn

00:19:07

【第68期】stream-x算法，省去Experience Replay的在线强化学习

Seventy3 ·

2024/12/07

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：Deep Reinforcement Learning Without Experience Replay, Target Networks, or Batch UpdatesSummaryThis research paper introduces stream-x algorithms, a novel class of deep reinforcement learning algorithms designed for streaming data. Unlike traditional deep RL methods that rely on computationally expensive batch updates and experience replay, stream-x processes individual samples in real time. The authors address the "stream barrier"—the instability and

zh-cn

00:13:24

【第67期】BABY-AIGS：AI-Generated Science

Seventy3 ·

2024/12/06

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：AIGS: Generating Science from AI-Powered Automated FalsificationSummaryThis research paper introduces BABY-AIGS, a multi-agent system designed to autonomously conduct scientific research. The system uses large language models (LLMs) to propose hypotheses, conduct experiments, and perform falsification, a crucial aspect of the scientific method. BABY-AIGS is evaluated on three machine learning tasks, demonstrating its capacity to generate meaningful

zh-cn

00:19:48

【第66期】Anthropic研究：给LLM评估加点“统计学”

Seventy3 ·

2024/12/05

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：Adding Error Bars to Evals: A Statistical Approach to Language Model EvaluationsSummaryThis paper advocates for improved statistical rigor in evaluating large language models (LLMs). It introduces methods for calculating and reporting confidence intervals, accounting for clustered data, and reducing variance in estimates. The authors propose specific techniques, such as using paired analyses and resampling, to enhance the precision of LLM evaluations

zh-cn

00:18:57

【第65期】Liquid Time-constant Networks：液体（神经）网络是什么？

Seventy3 ·

2024/12/04

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：Liquid Time-constant NetworksSummaryThis research introduces Liquid Time-Constant Networks (LTCs), a novel type of continuous-time recurrent neural network. LTCs improve upon existing models by incorporating a dynamically adjusted time constant, leading to enhanced stability and expressivity. The authors provide theoretical analyses demonstrating these improvements, including bounds on network dynamics and a novel expressivity measure based on

zh-cn

00:21:55

【第64期】NeuroClips：从fMRI数据还原大脑中视频

Seventy3 ·

2024/12/03

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：NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video ReconstructionSummaryThe study introduces NeuroClips, a novel framework for reconstructing videos from fMRI brain activity. NeuroClips uses a two-pronged approach, employing separate components for reconstructing keyframes (high-level semantics) and low-level perceptual details to create smooth, high-fidelity videos. The framework significantly improves upon existing methods, achieving longer

zh-cn

00:12:05

【第63期】无论DPO还是PPO，Preference Feedback应该怎么用？

Seventy3 ·

2024/12/02

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：Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference FeedbackSummaryThis NeurIPS 2024 paper investigates the effectiveness of different components in preference-based learning for language models. The authors systematically compare Proximal Policy Optimization (PPO) and Direct Preference Optimization (DPO) algorithms, examining the influence of preference data quality, reward model design, and policy training prompts on

zh-cn

00:25:19

【第62期】sCMs：比Diffusion更快的图像生成算法

Seventy3 ·

2024/12/01

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：Simplifying, stabilizing, and scaling continuous-time consistency modelsSummaryThis research paper introduces simplified, stable, and scalable continuous-time consistency models (sCMs) for image generation. The authors propose TrigFlow, a new framework unifying existing diffusion model formulations, and implement key improvements to stabilize training. These improvements include refined time conditioning, adaptive normalization, and adaptive weighting

zh-cn

00:14:36

【第61期】大模型的「推理」是在做什么？

Seventy3 ·

2024/11/30

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：Procedural Knowledge in Pretraining Drives Reasoning in Large Language ModelsSummaryThis research investigates how large language models (LLMs) learn to reason, contrasting their strategies for reasoning tasks with those used for factual recall. The study analyzes the influence of pretraining data on model outputs for mathematical reasoning and factual questions, revealing that LLMs utilize procedural knowledge from the pretraining data rather than

zh-cn

00:19:38

【第60期】RLTools：基于C++的开源强化学习工具

Seventy3 ·

2024/11/29

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：RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous ControlSummaryRLtools, a new open-source C++ library, significantly accelerates deep reinforcement learning (RL) for continuous control problems. Its header-only, dependency-free design enables fast training and inference across diverse platforms, from high-performance computers to microcontrollers. This speed improvement is demonstrated through benchmarks showing substantial

zh-cn

00:11:32

【第59期】SymDPO：多模态In-context learning提升技巧

Seventy3 ·

2024/11/28

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：SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference OptimizationSummaryThis research introduces SymDPO, a novel method to improve the in-context learning capabilities of Large Multimodal Models (LMMs). Current LMMs often prioritize textual information over visual context in demonstrations, leading to inaccurate results. SymDPO addresses this "visual context overlook" by replacing text answers with

zh-cn

00:17:30

【第58期】AM-RADIO，融合多种视觉大模型

Seventy3 ·

2024/11/27

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：AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into OneSummaryThis paper proposes a new approach to training vision foundation models (VFMs) called AM-RADIO, which agglomerates the unique strengths of multiple pretrained models like CLIP, DINOv2, and SAM into a single model. The framework uses multi-teacher distillation to achieve this, and the resulting models outperform individual teacher models on various downstream tasks like

zh-cn

00:12:29

【第57期】降低数值精度影响LLM数学推理能力

Seventy3 ·

2024/11/26

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：How Numerical Precision Affects Mathematical Reasoning Capabilities of LLMsSummaryThis research paper investigates how the numerical precision of a Transformer-based Large Language Model (LLM) affects its ability to perform mathematical reasoning tasks. The authors demonstrate through theoretical analysis and empirical experiments that LLMs with low numerical precision struggle with complex arithmetic tasks, such as iterated addition and integer

zh-cn

00:13:41

【第56期】o1的self-correction是一种In context Alignment

Seventy3 ·

2024/11/25

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：A Theoretical Understanding of Self-Correction through In-context AlignmentSummaryThis research paper examines the ability of large language models (LLMs) to self-correct, specifically focusing on how this capability arises from an in-context alignment perspective. The authors present a theoretical analysis demonstrating that standard transformer architectures can perform gradient descent on common alignment objectives in an in-context manner,

zh-cn

00:23:03

【第55期】RLInspect

Seventy3 ·

2024/11/24

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：RLInspect: An Interactive Visual Approach to Assess Reinforcement Learning AlgorithmSummaryThis technical paper presents RLInspect, an interactive visual analytic tool designed to assist users in understanding and potentially debugging the training process of reinforcement learning (RL) algorithms. RLInspect provides users with a visual representation of various components of RL, such as state, action, agent architecture, and reward, which can help

zh-cn

00:12:08

【第54期】Impacts of AI on Innovation

Seventy3 ·

2024/11/23

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：Artificial Intelligence, Scientific Discovery, and Product InnovationSummaryThis document is a research paper that explores the impact of AI on the materials discovery process within a large R&D lab. The paper uses a randomized controlled trial to analyze the effects of introducing an AI tool to scientists, examining how it impacts the discovery, patenting, and commercialization of new materials. It finds that AI significantly accelerates the pace

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