Les meilleurs podcasts Graph Database (2024)

1
Making Invisible Connections Visible with Tim Eastridge 37:54

4d ago37:54

37:54

Speaker Resources: Eastridge Analytics: https://www.eastridge-analytics.com/ Graph Data Science with Python and Neo4j book: https://a.co/d/hkfkxPr LinkedIn profile: https://www.linkedin.com/in/timeastridge/ NODES 2024 (look for more info on Tim's talk soon!): https://dev.neo4j.com/nodes24 Neo4j GraphAcademy: https://graphacademy.neo4j.com/ Graph Al…

1
439: Async Ruby & Rails with Trevor Turk 34:11

9h ago34:11

34:11

How can asynchronous programming transform your Ruby on Rails applications? Today, Stephanie sits down with Hello Weather co-creator Trevor Turk to unpack asynchronous programming in Ruby on Rails. Trevor Turk is a seasoned software developer known for his work on Hello Weather, a minimalist weather app that delivers essential weather data quickly …

1
Automated Design of Agentic Systems 23:55

18h ago23:55

23:55

Researchers are investing substantial effort in developing powerful general-purpose agents, wherein Foundation Models are used as modules within agentic systems (e.g. Chain-of-Thought, Self-Reflection, Toolformer). However, the history of machine learning teaches us that hand-designed solutions are eventually replaced by learned solutions. We formu…

1
Text2SQL is Not Enough: Unifying AI and Databases with TAG 42:53

1d ago42:53

42:53

AI systems that serve natural language questions over databases promise to unlock tremendous value. Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computational power of data management systems. These combined capabilities would empower users to ask arbitr…

1
Integration Tests Done Right: Testcontainers | Oleg Šelajev 30:46

5d ago30:46

30:46

Writing good integration tests is hard. Databases and other services need to be started up, the test has to be run, and everything needs to be shut down again. In this episode of Cloud Commute Oleg Šelajev from Docker talks about how Testcontainers makes our lives better. 📋 Shownotes: ► Oleg's LinkedIn ► Oleg's X/Twitter ► Oleg's Youtube ► Testcont…

1
Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders 35:05

6d ago35:05

35:05

The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves performance on resolution-sensitive tasks, such as optical character recognition and document analysis. A number of rec…

1
Sapiens: Foundation for Human Vision Models 25:58

7d ago25:58

25:58

We present Sapiens, a family of models for four fundamental human-centric vision tasks -- 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference and are extremely easy to adapt for individual tasks by simply fine-tuning models pretrained on over 300 milli…

1
OctFusion: Octree-based Diffusion Models for 3D Shape Generation 33:00

8d ago33:00

33:00

Diffusion models have emerged as a popular method for 3D generation. However, it is still challenging for diffusion models to efficiently generate diverse and high-quality 3D shapes. In this paper, we introduce OctFusion, which can generate 3D shapes with arbitrary resolutions in 2.5 seconds on a single Nvidia 4090 GPU, and the extracted meshes are…

1
438: Writing abstractions in tests 49:08

8d ago49:08

49:08

Writing abstractions in tests can be surprisingly similar to storytelling. The most masterful stories are those where the author has stripped away all of the extra information, and given you just enough knowledge to be immersed and aware of what is going on. But striking that balance can be tricky, both in storytelling and abstractions in tests. To…

1
Writing in the Margins: Better Inference Pattern for Long Context Retrieval 29:22

9d ago29:22

29:22

In this paper, we introduce Writing in the Margins (WiM), a new inference pattern for Large Language Models designed to optimize the handling of long input sequences in retrieval-oriented tasks. This approach leverages the chunked prefill of the key-value cache to perform segment-wise inference, which enables efficient processing of extensive conte…

1
Fact Finder -- Enhancing Domain Expertise of Large Language Models by Incorporating Knowledge Graphs 19:53

12d ago19:53

19:53

Recent advancements in Large Language Models (LLMs) have showcased their proficiency in answering natural language queries. However, their effectiveness is hindered by limited domain-specific knowledge, raising concerns about the reliability of their responses. We introduce a hybrid system that augments LLMs with domain-specific knowledge graphs (K…

1
From Teaching to Tech: The Forefront of the Kubernetes Community - Bart Farrell 27:51

12d ago27:51

27:51

In this very special episode of Cloud Commute we try something else. Joined by guest Bart Farrell, well known in the Kubernetes ecosystem for his work in the Data on Kubernetes community, as well as Kube.FM. Bart talks about his past, teaching children English after he moved from the USA to Spain, and how this shaped his view on teaching tech topic…

1
RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation 18:01

13d ago18:01

18:01

Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of their knowledge. Current research addresses this bottleneck by equipping LLMs with external knowledge, a technique known as Retrieval…

1
RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation 27:28

14d ago27:28

27:28

Despite Retrieval-Augmented Generation (RAG) showing promising capability in leveraging external knowledge, a comprehensive evaluation of RAG systems is still challenging due to the modular nature of RAG, evaluation of long-form responses and reliability of measurements. In this paper, we propose a fine-grained evaluation framework, RAGChecker, tha…

1
437: Contributing to Open Source in the Midst of Daily Work with Steve Polito 35:28

15d ago35:28

35:28

Are you passionate about open source but struggling to find time amidst your daily work? Today on the podcast, Joël Quenneville sits down with Steve Polito to discuss practical strategies for making meaningful contributions to the open-source community, even when your schedule is packed. Steve is a developer with extensive experience in the open-so…

1
DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search 47:39

19d ago47:39

47:39

We introduce DeepSeek-Prover-V1.5, an open-source language model designed for theorem proving in Lean 4, which enhances DeepSeek-Prover-V1 by optimizing both training and inference processes. Pre-trained on DeepSeekMath-Base with specialization in formal mathematical languages, the model undergoes supervised fine-tuning using an enhanced formal the…

1
Building AI Agents with Java and Semantic Kernel 30:18

19d ago30:18

30:18

In this episode of simplyblock's Cloud Commute Podcast, we dive into the intersection of Java, AI, and cloud technology with Bruno Borges, a principal product manager at Microsoft. Bruno talks about how there are millions of Java instances at Microsoft and the Microsoft Java team. He also introduces Semantic Kernel, a Java library designed to integ…

1
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs 38:53

21d ago38:53

38:53

Current long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. Through controlled experiments, we find that the model's effective generation length is inherently bounded by the sample it has seen during supervised fine-tuning (SFT). In other …

1
ControlNeXt: Powerful and Efficient Control for Image and Video Generation 26:50

22d ago26:50

26:50

Diffusion models have demonstrated remarkable and robust abilities in both image and video generation. To achieve greater control over generated results, researchers introduce additional architectures, such as ControlNet, Adapters and ReferenceNet, to integrate conditioning controls. However, current controllable generation methods often require su…

1
OpenResearcher: Unleashing AI for Accelerated Scientific Research 29:59

23d ago29:59

29:59

The rapid growth of scientific literature imposes significant challenges for researchers endeavoring to stay updated with the latest advancements in their fields and delve into new areas. We introduce OpenResearcher, an innovative platform that leverages Artificial Intelligence (AI) techniques to accelerate the research process by answering diverse…

1
How to Build a Serverless Postgres? ft Gwen Shapira 28:36

26d ago28:36

28:36

In this episode, our guest Gwen Shapira talks about her co-founded database startup Nile, a serverless Postgres database. She explains how they implemented the multi-tenant features, made sure that customers are probably isolated, how scalability works, and what the future holds. Gwen has years and years of experience using technologies as Oracle d…

1
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation 33:50

28d ago33:50

33:50

While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this…

1
AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls 41:29

29d ago41:29

41:29

We introduce AnyTool, a large language model agent designed to revolutionize the utilization of a vast array of tools in addressing user queries. We utilize over 16,000 APIs from Rapid API, operating under the assumption that a subset of these APIs could potentially resolve the queries. AnyTool primarily incorporates three elements: an API retrieve…

1
436: Creating Conditions For Your Best Work with Steph Viccari 43:09

29d ago43:09

43:09

How can we optimize our time and environment to do our best work as developers? In today’s episode, we are joined by Stephanie Viccari, former co-host of The Bike Shed and Senior Developer at thoughtbot, to unpack the steps for creating work conditions that enhance productivity. In this conversation, we delve into her unique communication style and…

1
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads 38:55

1M ago38:55

38:55

Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. This creates a bottleneck as each step necessitates moving the full model parameters from High-Bandwidth Memory (HBM) to the accelerator's cache. While methods such as speculative decoding have been…

1
A Time-Series Database in Postgres - WHY? 29:22

1M ago29:22

29:22

In this episode of Simplyblock's Cloud Commute Podcast, host Chris Engelbert interviews Mike Freedman, co-founder and CTO of Timescale. Timescale enhances Postgres to manage time series data, analytics, and AI applications efficiently. Mike explains how Timescale's automated partitioning and lifecycle management transform data from row-based to com…

1
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders 29:11

1M ago29:11

29:11

Large decoder-only language models (LLMs) are the state-of-the-art models on most of today's NLP tasks and benchmarks. Yet, the community is only slowly adopting these models for text embedding tasks, which require rich contextualized representations. In this work, we introduce LLM2Vec, a simple unsupervised approach that can transform any decoder-…

1
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers 31:47

1M ago31:47

31:47

Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing many challenges: The potential huge computation cost makes the training from scratch unaffordable; The scarcity and weak relevance of text-video datasets hinder the model …

1
MindSearch: Mimicking Human Minds Elicits Deep AI Searcher 26:22

1M ago26:22

26:22

Information seeking and integration is a complex cognitive task that consumes enormous time and effort. Inspired by the remarkable progress of Large Language Models, recent works attempt to solve this task by combining LLMs and search engines. However, these methods still obtain unsatisfying performance due to three challenges: (1) complex requests…

1
Introduction to Side Channel Attacks using CacheWarp 31:43

1M ago31:43

31:43

In this week's episode we have a very special guest, Michael Schwarz from CISPA. A security researcher specialized in CPU side channel attacks. He explains how side-channel attacks work in general, but most specifically with the example of his team's most recent find: #CacheWarp. He was also involved in the finding of #Meltdown and #Spectre. To con…

1
Pragmatic Knowledge Graphs with Ashleigh Faith 52:17

1M ago52:17

52:17

Speaker Resources: Ashleigh’s YT Channel: https://www.youtube.com/@AshleighFaith Tools of the Month: Abk: Any Airline using Windows 3.1 😆 Ashleigh: Zentity: https://zentity.io/ Jason: Cypher Co-pilot: https://neo4j.com/developer-blog/cypher-co-pilot/ Alison: System https://www.system.com Announcements / News: Articles: Turning Your Tabular Data Int…

1
Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models 34:03

1M ago34:03

34:03

Diffusion models have achieved great progress in image animation due to powerful generative capabilities. However, maintaining spatio-temporal consistency with detailed information from the input static image over time (e.g., style, background, and object of the input static image) and ensuring smoothness in animated video narratives guided by text…

1
435: Cohesive Code with Jared Norman 28:45

1M ago28:45

28:45

How easy is it for a layperson to understand your systems? Jared Norman is a software consultant, speaker, and host of the Dead Code Podcast who specializes in building e-commerce applications in Ruby on Rails. This episode follows two recent talks at RailsConf and covers a theme that emerged from both of them: coupling and cohesion. Tuning in, you…

1
FinanceBench: A New Benchmark for Financial Question Answering 41:34

1M ago41:34

41:34

FinanceBench is a first-of-its-kind test suite for evaluating the performance of LLMs on open book financial question answering (QA). It comprises 10,231 questions about publicly traded companies, with corresponding answers and evidence strings. The questions in FinanceBench are ecologically valid and cover a diverse set of scenarios. They are inte…

1
Stable-Hair: Real-World Hair Transfer via Diffusion Model 30:25

1M ago30:25

30:25

Current hair transfer methods struggle to handle diverse and intricate hairstyles, thus limiting their applicability in real-world scenarios. In this paper, we propose a novel diffusion-based hair transfer framework, named \textit{Stable-Hair}, which robustly transfers a wide range of real-world hairstyles onto user-provided faces for virtual hair …

1
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? 31:03

2M ago31:03

31:03

Data science and engineering workflows often span multiple stages, from warehousing to orchestration, using tools like BigQuery, dbt, and Airbyte. As vision language models (VLMs) advance in multimodal understanding and code generation, VLM-based agents could potentially automate these workflows by generating SQL queries, Python code, and GUI opera…

1
Automatically secure your application with your personal Application Firewall 25:21

2M ago25:21

25:21

In this week's episode of the Cloud Commute podcast by simplyblock, host Chris Engelbert talks to Hannes Ullman from bifrost security, a company building an automatic application firewall. Bifrost is built upon AppArmor, using a training phase to learn the application's network behavior, necessary system calls, and more. Using the data acquired dur…

1
FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs 34:06

2M ago34:06

34:06

This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative models: SenseVoice, which handles multilingual speech recognition, emotion recognition, and audio event detection; and CosyVoice, which facilitates natural speech generatio…

1
Patch-Level Training for Large Language Models 24:02

2M ago24:02

24:02

As Large Language Models (LLMs) achieve remarkable progress in language understanding and generation, their training efficiency has become a critical concern. Traditionally, LLMs are trained to predict the next token in a sequence. Despite the success of token-level training, it suffers from considerable computational costs due to the need to proce…

1
434: Git and GitHub Workflows 47:42

2M ago47:42

47:42

It's Calls for Proposals (CFP) season, and in the process of helping our friends and colleagues flesh out their CFPs, we came up with a few questions to help them frame their proposals for success. After learning about the importance of finding your audience and angle of approach for your CFP, we dive into today's main topic – our Git and GitHub wo…

1
Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models 35:12

2M ago35:12

35:12

We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages. This underexplored problem poses new challenges at the pre-writing stage, including how to research the topic and prepare an outline prior to writing. We propose STORM, a writing system f…

1
IMAGDressing-v1: Customizable Virtual Dressing 27:37

2M ago27:37

27:37

Latest advances have achieved realistic virtual try-on (VTON) through localized garment inpainting using latent diffusion models, significantly enhancing consumers' online shopping experience. However, existing VTON technologies neglect the need for merchants to showcase garments comprehensively, including flexible control over garments, optional f…

1
A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights 36:34

2M ago36:34

36:34

Human video generation is a dynamic and rapidly evolving task that aims to synthesize 2D human body video sequences with generative models given control conditions such as text, audio, and pose. With the potential for wide-ranging applications in film, gaming, and virtual communication, the ability to generate natural and realistic human video is c…

1
How to connect millions of devices every day 29:04

2M ago29:04

29:04

In this episode of the Cloud Commute Podcast, Chris Engelbert talks with Dominik Obermaier, CTO and co-founder of HiveMQ. They delve into the technical aspects of MQTT, a lightweight communication protocol designed for the Internet of Things (IoT). Dominik explains how MQTT, an ISO standard, is ideal for connecting millions of devices due to its pu…

1
Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence 49:58

2M ago49:58

49:58

The rapid advancement of large language models (LLMs) has paved the way for the development of highly capable autonomous agents. However, existing multi-agent frameworks often struggle with integrating diverse capable third-party agents due to reliance on agents defined within their own ecosystems. They also face challenges in simulating distribute…

1
SEED-Story: Multimodal Long Story Generation with Large Language Model 22:27

2M ago22:27

22:27

With the remarkable advancements in image generation and open-form text generation, the creation of interleaved image-text content has become an increasingly intriguing field. Multimodal story generation, characterized by producing narrative texts and vivid images in an interleaved manner, has emerged as a valuable and practical task with broad app…

1
433: Riffing with Kasper Timm Hansen 37:20

2M ago37:20

37:20

Have you ever wondered how improvisation can revolutionize coding? In today’s episode, Stephanie sits down with Kasper Timm Hansen to discuss his innovative “riffing” approach to code development. Kasper is a long-time Ruby developer and former member of the Rails core team. He focuses on Ruby and domain modeling, developing various Ruby gems, and …

1
Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models 39:20

2M ago39:20

39:20

While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search (LATS) -- the first general framework that synergizes the capabilities of LMs in reasoning, acting, and plannin…

1
LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control 39:35

2M ago39:35

39:35

Portrait Animation aims to synthesize a lifelike video from a single source image, using it as an appearance reference, with motion (i.e., facial expressions and head pose) derived from a driving video, audio, text, or generation. Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-b…

1
Getting Started with Graph Databases with Jennifer Reif from Neo4j 26:43

2M ago26:43

26:43

In this week's episode of simplyblock's Cloud Commute podcast, host Chris Engelbert sits down with Jennifer Reif, a developer advocate at Neo4j. Jennifer dives into the fascinating world of graph databases, explaining how Neo4j stores data as entities and relationships, making it perfect for complex queries involving networks, social structures, su…

Podcasts qui valent la peine d'être écoutés

Graph Database Podcasts

Podcasts qui valent la peine d'être écoutés

Guide de référence rapide