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

00:22:21

【第133期】Meta-CoT：朝着系统2推理的方向发展

Seventy3 ·

2025/02/10

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：Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-ThoughtSummaryThe paper "Towards System 2 Reasoning in LLMs" explores methods for improving the reasoning capabilities of large language models (LLMs). It introduces Meta Chain-of-Thought (Meta-CoT), a framework that models the reasoning process itself, going beyond traditional Chain-of-Thought prompting. The authors investigate using search algorithms, synthetic data, and

zh-cn

00:26:34

【第132期】Agent Laboratory：科学研究助手

Seventy3 ·

2025/02/09

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：Agent Laboratory: Using LLM Agents as Research AssistantsSummaryThe document details Agent Laboratory, an open-source framework using large language models (LLMs) to automate the scientific research process. It progresses through literature review, experimentation, and report writing stages, with human researchers providing feedback. Experiments show that Agent Laboratory significantly reduces research costs and that the o1-preview LLM backend produces

zh-cn

00:12:19

【第131期】Orient Anything：一种用于估计图像中物体方向的模型

Seventy3 ·

2025/02/08

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：Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D ModelsSummaryThe paper introduces Orient Anything, a novel model for estimating object orientation in images. It addresses the challenge of limited labeled data by generating a large dataset of rendered 3D models with precise orientation annotations. The model uses a probability distribution fitting approach for robust orientation prediction, improving accuracy on both

zh-cn

00:20:21

【第130期】OS-Genesis：可为GUI Agent提供数据

Seventy3 ·

2025/02/07

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：OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task SynthesisSummaryThis research paper introduces OS-Genesis, a novel pipeline for synthesizing high-quality and diverse data for training Graphical User Interface (GUI) agents. Unlike existing methods that rely on pre-defined tasks or human supervision, OS-Genesis uses an interaction-driven approach, allowing agents to explore environments and retrospectively derive tasks. A

zh-cn

00:14:51

【第129期】Sa2VA：Sam2+LLaVA

Seventy3 ·

2025/02/06

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：Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and VideosSummaryThe research introduces Sa2VA, a unified model for understanding images and videos. Sa2VA combines the strengths of SAM-2 (video segmentation) and LLaVA (vision-language model) to perform various tasks like referring segmentation and conversation. A new dataset, Ref-SAV, with complex video scenes, was created to improve model performance. Experiments show Sa2VA

zh-cn

00:17:56

【第128期】MeCo：元数据调节与冷却

Seventy3 ·

2025/02/05

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：Metadata Conditioning Accelerates Language Model Pre-trainingSummaryThis research paper introduces Metadata Conditioning then Cooldown (MeCo), a novel method for improving the efficiency and controllability of large language model pre-training. MeCo incorporates readily available metadata, such as URLs, to enhance the model's understanding of diverse data sources during training, then uses a "cooldown" phase to ensure functionality without metadata

zh-cn

00:15:38

【第127期】隐式 PRM：过程奖励模型

Seventy3 ·

2025/02/04

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：Free Process Rewards without Process LabelsSummaryThis research paper proposes a cost-effective method for training process reward models (PRMs), which evaluate the intermediate steps of a reasoning process. Unlike existing PRMs requiring costly step-level labels, the authors demonstrate that a strong PRM can be implicitly learned at no extra cost by training an outcome reward model (ORM) with a specific reward parameterization. Their method, termed

zh-cn

00:17:24

【第126期】ICAL：VLM的上下文抽取学习

Seventy3 ·

2025/02/03

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：VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of ThoughtSummaryThis NeurIPS 2024 paper introduces In-Context Abstraction Learning (ICAL), a method that allows Vision-Language Models (VLMs) to learn from suboptimal demonstrations and human feedback. ICAL generates its own high-quality examples by abstracting noisy trajectories, correcting errors, and annotating cognitive abstractions like causal relationships and

zh-cn

00:19:36

【第125期】GraphAgent：一种用于分析结构化（图形）和非结构化（文本）数据的自动化代理

Seventy3 ·

2025/02/02

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：GraphAgent: Agentic Graph Language AssistantSummaryThis paper introduces GraphAgent, a novel automated agent pipeline designed for analyzing both structured (graph) and unstructured (textual) data. GraphAgent uses three key agents: a Graph Generator Agent to create knowledge graphs from text, a Task Planning Agent to interpret user queries, and a Task Execution Agent to perform predictive or generative tasks. The system is evaluated on various

zh-cn

00:18:16

【第124期】面向通用机器人控制的VLA模型

Seventy3 ·

2025/02/01

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：Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action ModelsSummaryThis research paper explores the creation of Vision-Language-Action (VLA) models for generalist robot control. The authors investigate key design choices in VLAs, including the selection of Vision-Language Model (VLM) backbones, optimal VLA architectures, and the effective use of cross-embodiment data. Through extensive experimentation, they identify

zh-cn

00:11:10

【第123期】Cache-augmented generation (CAG)

Seventy3 ·

2025/01/31

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：Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge TasksSummaryThis research paper introduces cache-augmented generation (CAG) as a more efficient alternative to retrieval-augmented generation (RAG) for knowledge-intensive tasks. CAG preloads all relevant knowledge into a large language model (LLM), eliminating the need for real-time retrieval and its associated latency and errors. Experiments using SQuAD and HotPotQA datasets

zh-cn

00:20:36

【第122期】HuatuoGPT-o1：医学推理大模型

Seventy3 ·

2025/01/30

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：HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMsSummaryThis research introduces HuatuoGPT-o1, a large language model (LLM) specialized for complex medical reasoning. The model is trained using a novel two-stage approach: first, a search-based strategy learns complex reasoning trajectories from a newly created dataset of 40,000 verifiable medical problems; second, reinforcement learning further refines this ability using verifier feedback

zh-cn

00:14:07

【第121期】一种新型的蒙特卡罗符合性预测

Seventy3 ·

2025/01/29

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：Conformal prediction under ambiguous ground truthSummaryThis research paper proposes a novel Monte Carlo Conformal Prediction (CP) method to address uncertainty quantification in classification tasks with ambiguous ground truth labels. Standard CP methods often rely on "voted" labels derived from aggregated expert opinions, ignoring inherent label uncertainty. The proposed Monte Carlo CP leverages expert opinions to create a non-degenerate label

zh-cn

00:09:41

【第120期】iTransformer：Inverted Transformers理解时间序列问题

Seventy3 ·

2025/01/28

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：iTransformer: Inverted Transformers Are Effective for Time Series ForecastingSummaryThe paper introduces iTransformer, a novel architecture for time series forecasting that inverts the standard Transformer structure. Instead of embedding multiple variates at each timestamp, iTransformer embeds each time series individually as a token, applying attention to capture multivariate correlations and feed-forward networks to learn series-specific

zh-cn

00:12:47

【第119期】DRT-o1：一种旨在改进包含明喻和隐喻句子翻译的新型神经机器翻译模型

Seventy3 ·

2025/01/27

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：DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-ThoughtSummaryThe paper introduces DRT-o1, a novel neural machine translation model designed to improve the translation of sentences containing similes and metaphors. DRT-o1 leverages a multi-agent framework to simulate extended reasoning during the translation process, generating a long chain of thought. This framework comprises a translator, an advisor, and an evaluator, iteratively

zh-cn

00:11:00

【第118期】Mulberry：使用CoMCTS做类o1的多模态大模型

Seventy3 ·

2025/01/26

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：Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree SearchSummaryThis research paper introduces Mulberry, a series of multimodal large language models (MLLMs) designed for improved reasoning and reflection. The key innovation is CoMCTS, a novel Collective Monte Carlo Tree Search method that leverages multiple models to collaboratively identify effective reasoning paths. CoMCTS generates the Mulberry-260k

zh-cn

00:25:42

【第117期】ExploreToM：一种用于生成复杂且多样化的心智理论

Seventy3 ·

2025/01/25

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：Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoningSummaryThe paper introduces ExploreToM, a novel framework for generating complex and diverse theory-of-mind (ToM) datasets for evaluating and training large language models (LLMs). ExploreToM uses an A* search algorithm and a domain-specific language to create challenging story scenarios, revealing significant weaknesses in current LLMs' ToM abilities. The

zh-cn

00:17:18

【第116期】LLM Inference-Time自我提升综述

Seventy3 ·

2025/01/24

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：A Survey on LLM Inference-Time Self-ImprovementSummaryThis research survey explores Large Language Model (LLM) Inference-Time Self-Improvement (ITSI), techniques enhancing LLM performance at inference without retraining. The authors categorize ITSI methods into three groups: Independent, improving decoding processes; Context-Aware, leveraging external context or data; and Model-Aided, using other models for collaboration. A comprehensive taxonomy of

zh-cn

00:18:15

【第115期】ModernBERT

Seventy3 ·

2025/01/23

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：Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and InferenceSummaryThis research paper introduces ModernBERT, a significantly improved encoder-only transformer language model. ModernBERT boasts state-of-the-art performance across various natural language understanding and information retrieval tasks, including code-related applications. Key improvements include a modernized

zh-cn

00:25:50

【第114期】DeepSeek V3技术报告

Seventy3 ·

2025/01/22

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：DeepSeek-V3 Technical ReportSummaryThe document details DeepSeek-V3, a 671B-parameter Mixture-of-Experts large language model. It covers the model's architecture, including Multi-Head Latent Attention and an innovative auxiliary-loss-free load balancing strategy for DeepSeekMoE. The training process, encompassing pre-training on 14.8 trillion tokens and post-training using supervised fine-tuning and reinforcement learning, is described. Extensive

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