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

00:18:23

【第93期】TARFLOW：一种基于 Transformer 的正则化流

Seventy3 ·

2025/01/01

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：Normalizing Flows are Capable Generative ModelsSummaryThis research paper introduces TARFLOW, a novel Transformer-based Normalizing Flow (NF) architecture for generative modeling of images. TARFLOW significantly improves upon previous NF models by achieving state-of-the-art results in likelihood estimation and generating high-quality samples comparable to diffusion models. Key advancements include a more scalable architecture, Gaussian noise

zh-cn

00:26:09

【第92期】Agentless：软件开发的Agent

Seventy3 ·

2024/12/31

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：Agentless: Demystifying LLM-based Software Engineering AgentsSummaryThis research paper introduces AGENTLESS, a novel approach to automated software development that eschews complex autonomous agents. Instead, AGENTLESS employs a simpler three-phase process: localization, repair, and patch validation, leveraging large language models (LLMs) for each phase. The authors benchmark AGENTLESS against existing agent-based systems on SWE-bench Lite,

zh-cn

00:15:00

【第91期】[Mask] is all you need

Seventy3 ·

2024/12/30

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：[MASK] [MASK] [MASK] [MASK] [MASK][MASK] is [MASK] You [MASK][MASK] is All You NeedSummaryThis research paper introduces Discrete Interpolants, a novel framework that bridges Masked Generative Models and Diffusion Models for image and video generation. The framework uses discrete-state models and offers a unified design space analysis, exploring various schedulers and sampling methods. The authors demonstrate its versatility by recasting image

zh-cn

00:20:37

【第90期】SAT：Segment Any Text

Seventy3 ·

2024/12/29

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：Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence SegmentationSummaryThis research paper introduces Segment Any Text (SAT), a novel sentence segmentation model that surpasses existing methods. SAT achieves robustness by reducing reliance on punctuation during training, demonstrates adaptability through parameter-efficient fine-tuning across diverse domains (e.g., lyrics, legal texts), and boasts high efficiency,

zh-cn

00:23:39

【第89期】PRoC3S：一种新颖的机器人规划系统

Seventy3 ·

2024/12/28

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：Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint SatisfactionSummaryThis research paper introduces PRoC3S, a novel robotic planning system that leverages large language models (LLMs) to generate and execute plans involving continuous parameters. Unlike previous LLM-based approaches limited to discrete actions, PRoC3S handles complex, real-world constraints by separating planning into LLM program generation and

zh-cn

00:18:14

【第88期】LLM Agent能否模拟人的信任行为？

Seventy3 ·

2024/12/27

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：Can Large Language Model Agents Simulate Human Trust Behavior?SummaryThis research paper investigates whether Large Language Models (LLMs) can simulate human trust behavior. Using Trust Games, the study finds that LLMs, particularly GPT-4, exhibit trust behaviors aligning significantly with human patterns, demonstrating a high degree of behavioral alignment. The research also explores biases in LLM trust behavior, the impact of external manipulation

zh-cn

00:10:47

【第87期】Coconut：连续Latent空间的LLM推理

Seventy3 ·

2024/12/26

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：Training Large Language Models to Reason in a Continuous Latent SpaceSummaryThis research paper introduces Coconut, a novel method for enhancing Large Language Model (LLM) reasoning capabilities. Instead of relying solely on language-based chain-of-thought (CoT) reasoning, Coconut utilizes the LLM's hidden state ("continuous thought") as input, enabling reasoning in an unrestricted latent space. Experiments on various reasoning tasks demonstrate that

zh-cn

00:21:17

【第86期】RLZero："imagine", "project" and "imitate"

Seventy3 ·

2024/12/25

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：RL Zero: Zero-Shot Language to Behaviors without any SupervisionSummaryThis research paper introduces RLZero, a novel method for translating natural language instructions into robot behaviors without using hand-designed reward functions. RLZero leverages unsupervised reinforcement learning and large video-language models to "imagine," "project," and "imitate" desired actions. The method first generates a video illustrating the task, then finds similar

zh-cn

00:17:35

【第85期】GENMAC：用多智能体模式生成复杂动态视频

Seventy3 ·

2024/12/24

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：GenMAC: Compositional Text-to-Video Generation with Multi-Agent CollaborationSummaryThe paper introduces GENMAC, a novel multi-agent framework for generating complex, dynamic videos from text prompts. GENMAC uses a three-stage iterative process (DESIGN, GENERATION, REDESIGN) with specialized agents in the REDESIGN stage to verify, suggest corrections, and refine the generated video. This multi-agent approach overcomes limitations of single-agent

zh-cn

00:44:34

【第84期】FedBone：大规模多任务联邦学习

Seventy3 ·

2024/12/23

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：FedBone: Towards Large-Scale Federated Multi-Task LearningSummaryThe paper introduces FedBone, a novel federated multi-task learning framework designed for large-scale models and heterogeneous tasks. It employs split learning to distribute computation efficiently between a cloud server and resource-constrained edge clients. A gradient projection method addresses conflicts arising from heterogeneous tasks during model aggregation. FedBone incorporates

zh-cn

00:21:45

【第83期】Datalab：LLM Power BI 工作流

Seventy3 ·

2024/12/22

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：DataLab: A Unified Platform for LLM-Powered Business IntelligenceSummaryThe paper introduces DataLab, a unified business intelligence platform leveraging large language models (LLMs). DataLab integrates an LLM-based agent framework with a computational notebook interface to streamline various BI tasks across different data roles. Key features include a domain knowledge incorporation module to enhance LLM understanding of enterprise data, an inter-agent

zh-cn

00:22:48

【第82期】ALAMA：LLM自动选择思考策略

Seventy3 ·

2024/12/21

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：Towards Adaptive Mechanism Activation in Language AgentSummaryThis research paper introduces ALAMA, a novel method for enhancing Language Agents (LAs) by enabling adaptive mechanism activation. ALAMA uses a unified framework (UniAct) to integrate various mechanisms like reasoning and planning, and employs self-exploration to generate training data, optimizing mechanism selection based on task characteristics. The authors demonstrate ALAMA's

zh-cn

00:11:22

【第81期】reverse thinking

Seventy3 ·

2024/12/20

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：Reverse Thinking Makes LLMs Stronger ReasonersSummaryThis research introduces REVTHINK, a framework designed to improve Large Language Models (LLMs) reasoning abilities by incorporating "reverse thinking." REVTHINK augments datasets with teacher-model-generated forward and backward reasoning examples, then trains a student model using multi-task learning objectives to generate both forward and backward reasoning. Experiments across diverse datasets

zh-cn

00:16:33

【第80期】Navigation World Models：Yann LeCun的世界模型

Seventy3 ·

2024/12/19

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：Navigation World ModelsSummaryThis research introduces a Navigation World Model (NWM), a novel video generation model that predicts future visual observations for navigation. Employing a Conditional Diffusion Transformer (CDiT), NWM is trained on a massive dataset of human and robotic navigation videos, reaching 1 billion parameters. The model excels at planning navigation trajectories in known environments, either independently or by ranking

zh-cn

00:11:31

【第79期】VisionZip：降低Visual token冗余度

Seventy3 ·

2024/12/18

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：VisionZip: Longer is Better but Not Necessary in Vision Language ModelsSummaryThe paper introduces VisionZip, a method to improve the efficiency of vision-language models (VLMs) by reducing redundancy in visual tokens. The authors observe that existing VLMs use excessively long visual token sequences, leading to high computational costs. VisionZip selects informative tokens, significantly improving inference speed and maintaining or even exceeding

zh-cn

00:21:53

【第78期】OSDFace：单步人脸重建

Seventy3 ·

2024/12/17

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：OSDFace: One-Step Diffusion Model for Face RestorationSummaryThe paper introduces OSDFace, a novel one-step diffusion model for high-speed face restoration. OSDFace uses a visual representation embedder (VRE) to capture detailed facial information from low-quality images, improving realism and identity consistency. The model incorporates a facial identity loss and a GAN for enhanced alignment with ground truth images. Experimental results show OSDFace

zh-cn

00:12:00

【第77期】VisVM：Vision Value Model

Seventy3 ·

2024/12/16

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：Scaling Inference-Time Search with Vision Value Model for Improved Visual ComprehensionSummaryThis research paper introduces the Vision Value Model (VisVM), a novel approach to improve the visual comprehension of vision-language models (VLMs). VisVM guides inference-time search in VLMs by predicting the long-term value of generated sentences, reducing hallucinations and increasing detail in image descriptions. Experiments demonstrate that VisVM-guided

zh-cn

00:20:44

【第76期】OmniFlow：Any-to-Any多模态rectified flow

Seventy3 ·

2024/12/15

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：OmniFlow: Any-to-Any Generation with Multi-Modal Rectified FlowsSummaryThe provided text details OmniFlow, a novel generative model designed for any-to-any generation tasks (text-to-image, text-to-audio, etc.). It extends the rectified flow framework to handle multiple modalities, outperforming previous models in various benchmarks. Key contributions include a multi-modal rectified flow formulation, a modular architecture enabling efficient

zh-cn

00:12:51

【第75期】cDPO：通过发掘critical tokens去修正回答

Seventy3 ·

2024/12/14

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：Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM’s Reasoning CapabilitySummaryThis research paper introduces cDPO, a novel approach to improve the reasoning capabilities of Large Language Models (LLMs). cDPO identifies "critical tokens"—tokens crucial to correct or incorrect reasoning—using contrastive estimation by comparing models trained on correct and incorrect reasoning trajectories. This allows for token-level reward

zh-cn

00:15:32

【第74期】苏格拉底游戏：AI Agent的脑内活动

Seventy3 ·

2024/12/13

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：Boundless Socratic Learning with Language GamesSummaryThis position paper explores the concept of Socratic learning, a type of recursive self-improvement in a closed system where an agent learns solely through language interactions. The authors posit three necessary conditions for this: sufficiently informative feedback, broad data coverage, and sufficient capacity. They propose language games as a framework to achieve this, arguing that multiple,

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