Join us on September 27th for our free hybrid event, streamed live from Google for Startups in Madrid.
Powered by Ultralytics, #YV23 is the only conference in the world that focuses on open-source vision AI development and progress. Taking place both in-person and online, researchers, engineers, and practitioners will come together for the second year in a row to share knowledge, innovation, and progress. Join experts and leaders on September 27th at Google for Startups in Madrid, Spain to push the boundaries of the new frontier of Vision AI.
1
day
18
talks
2,000+
attendees online
150
attendees in person
Glenn Jocher
Founder & CEO
Glenn founded Ultralytics to lead the United States National Geospatial-Intelligence Agency (NGA) antineutrino analysis efforts, culminating in the miniTimeCube experiment and the world's first ever Global Antineutrino Map published in Nature. A deeper realization of the profound particle physics mysteries that evade us led him to Artificial General Intelligence (AGI) as the best solution for mankind to exceed the limits of our own minds and one day truly understand the universe and our place in it. Today he's driven to build the world's best vision AI as a building block to a future AGI, with Ultralytics YOLO and Ultralytics HUB as the spearheads of this obsession.
KEYONTE: Exploring Ultralytics YOLO: Advancements in State-of-the-Art Vision AI
PANEL: Making Open-Source AI Easy
Adrian Boguszewski
Software Evangelist
Adrian graduated from the Gdansk University of Technology in the field of Computer Science 8 years ago. After that, he started his career in computer vision and deep learning. As a team leader of data scientists and Android developers for the previous two years, Adrian was responsible for an application to take a professional photo (for an ID card or passport) without leaving home. He is a co-author of the LandCover.ai dataset, creator of the OpenCV Image Viewer Plugin, and a Deep Learning lecturer occasionally. His current role is to educate people about OpenVINO Toolkit. In his free time, he’s a traveler. You can also talk with him about finance, especially investments.
KEYNOTE: Skip the Line! Learn How to Build a Smart Queue Management System with YOLOv8
Elaine Wu
Edge AI Partnership & Marketing
Elaine is the Edge AI marketing and partnership manager at Seeed, an IoT hardware company since 2008 and an Elite Partner of NVIDIA Embedded. At Seeed, by aligning with developers, ecosystem and Seeed's hardware expertise, she believes and strives on the path of the most reliable hardware platform, empowering everyone to achieve their digital transformation goals as well as co-creating next-gen AI product. She tweets from @iamelainewu.
Upgrade Any Camera with YOLOv8 in a No-Code Way
Shashi Chilappagari
Chief Architect & Co-Founder
Shashi Chilappagari is the Co-Founder and Chief Architect at DeGirum Corp., a fabless semiconductor company building complete AI solutions for the edge. Prior to DeGirum, he was the Director of SSD Architecture at Marvell Semiconductor Inc. Shashi has B. Tech and M. Tech degrees from Indian Institute of Technology, Madras, India and Ph.D. from the University of Arizona, Tucson, Arizona.
Deploying Quantized YOLOv8 Models on Edge Devices
Merve Noyan
Developer Advocacy Engineer
Merve Noyan is an engineer in developer advocacy at Hugging Face, working on open-source machine learning. She's also graduate machine learning researcher and GDE in Machine Learning.
Open-Source Vision With Transformers
Amir Servi
Edge Deep Learning Product Manager
Amir is the Edge Deep Learning Product Manager at Sony. With over 15 years in the technological space, developer tools and vast experience in the AI ecosystem at both Deci, Superwise and AnyVision, Amir specializes in leading product and R&D teams to deliver bleeding-edge technology products for developers, from computer vision applications, through neural network acceleration, all the way to reshaping deep learning deployment on edge devices.
Bridging the Gap Between AI Research to Real-Time Edge
Glenn Jocher
Founder & CEO
Glenn founded Ultralytics to lead the United States National Geospatial-Intelligence Agency (NGA) antineutrino analysis efforts, culminating in the miniTimeCube experiment and the world's first ever Global Antineutrino Map published in Nature. A deeper realization of the profound particle physics mysteries that evade us led him to Artificial General Intelligence (AGI) as the best solution for mankind to exceed the limits of our own minds and one day truly understand the universe and our place in it. Today he's driven to build the world's best vision AI as a building block to a future AGI, with Ultralytics YOLO and Ultralytics HUB as the spearheads of this obsession.
KEYONTE: Exploring Ultralytics YOLO: Advancements in State-of-the-Art Vision AI
PANEL: Making Open-Source AI Easy
Adrian Boguszewski
Software Evangelist
Adrian graduated from the Gdansk University of Technology in the field of Computer Science 8 years ago. After that, he started his career in computer vision and deep learning. As a team leader of data scientists and Android developers for the previous two years, Adrian was responsible for an application to take a professional photo (for an ID card or passport) without leaving home. He is a co-author of the LandCover.ai dataset, creator of the OpenCV Image Viewer Plugin, and a Deep Learning lecturer occasionally. His current role is to educate people about OpenVINO Toolkit. In his free time, he’s a traveler. You can also talk with him about finance, especially investments.
KEYNOTE: Skip the Line! Learn How to Build a Smart Queue Management System with YOLOv8
Elaine Wu
Edge AI Partnership & Marketing
Elaine is the Edge AI marketing and partnership manager at Seeed, an IoT hardware company since 2008 and an Elite Partner of NVIDIA Embedded. At Seeed, by aligning with developers, ecosystem and Seeed's hardware expertise, she believes and strives on the path of the most reliable hardware platform, empowering everyone to achieve their digital transformation goals as well as co-creating next-gen AI product. She tweets from @iamelainewu.
Upgrade Any Camera with YOLOv8 in a No-Code Way
Shashi Chilappagari
Chief Architect & Co-Founder
Shashi Chilappagari is the Co-Founder and Chief Architect at DeGirum Corp., a fabless semiconductor company building complete AI solutions for the edge. Prior to DeGirum, he was the Director of SSD Architecture at Marvell Semiconductor Inc. Shashi has B. Tech and M. Tech degrees from Indian Institute of Technology, Madras, India and Ph.D. from the University of Arizona, Tucson, Arizona.
Deploying Quantized YOLOv8 Models on Edge Devices
Merve Noyan
Developer Advocacy Engineer
Merve Noyan is an engineer in developer advocacy at Hugging Face, working on open-source machine learning. She's also graduate machine learning researcher and GDE in Machine Learning.
Open-Source Vision With Transformers
Amir Servi
Edge Deep Learning Product Manager
Amir is the Edge Deep Learning Product Manager at Sony. With over 15 years in the technological space, developer tools and vast experience in the AI ecosystem at both Deci, Superwise and AnyVision, Amir specializes in leading product and R&D teams to deliver bleeding-edge technology products for developers, from computer vision applications, through neural network acceleration, all the way to reshaping deep learning deployment on edge devices.
Bridging the Gap Between AI Research to Real-Time Edge
Kalen Michael
Head of Product
A coder since he was gifted his first computer at 13, Kalen enjoys solving challenges in the most efficient way possible. Programming and sourcing solutions is something that really drives him, and there is nothing more exciting than the rush he receives when his code compiles bug-free. The more languages he learns the more he craves, and he is just waiting for the day we can download skills like in the Matrix.
AI for Everyone: Ultralytics HUB Levels the Playing Field
Erica Brescia
Managing Director
Erica Brescia joined Redpoint Ventures as a managing director in 2022, where she focuses on
investments in infrastructure, AI, developer tools and security. She currently serves on the
boards of Dagger, Railway, Xata and Poolside and has led other unannounced infrastructure
investments. Prior to Redpoint, Erica was the COO of GitHub. Prior to GitHub, Erica was the co-
founder and COO of Bitnami, an open source application packaging and deployment company,
which was acquired by VMware. She was also co-founder and CEO of BitRock, which
developed software packaging technology. Erica has been a leader in the open source
community for over 15 years and has served on the board of the Linux Foundation since 2016.
Prior to joining Redpoint, Erica was an angel investor and advisor to companies such as Netlify,
Coda, Whimsical, Xata and Byteboard. She lives in Walnut Creek, CA with her husband, son
and their hilarious lab-chihuahua mix.
Series As for Open Source: What Investors are Looking for
Dr. Ramit Debnath
Co-Founder
Assistant Professor of Computational Social Science & Design, at Cambridge University, Director for the Collective Intelligence & Design Group (Cambridge University) and the first Cambridge Zero fellow, co-leading a global research effort to improve public understanding of climate change by collaborating with leading academic institutions such as Caltech, Harvard University, Boston University, MCC-Berlin, leading public policy organisations such as United Nations Environmental Programme (UNEP), International Energy Agency (IEA), and other pioneers in the climate and sustainability space.
Visiting Faculty Associate, Caltech. Previously worked at Stanford University, IEA and IIT Bombay. Gates Scholar.
Human and Machine Intelligence for Planetary Climate Action
Seán Boyle
Co-Founder
Acted as Twitter’s first Head of Sustainability, launched the first company-wide climate action strategy, co-produced the inaugural climate change miss/disinformation policy and partnered with leading climate action organisations including United Nations Framework Convention on Climate Change (UNFCCC), United Nations Environmental Programme (UNEP), COP27, FridaysForFuture, WeDontHaveTime, leading academic institutions including Cambridge University and other pioneers in the climate action space.
Worked at Twitter for 8 years. Previously held roles at Meta and KPMG.
Advisory Board Member to WeDontHaveTime. Honorary Fellow of Sigma Squared.
Human and Machine Intelligence for Planetary Climate Action
Yonatan Geifman
Co-Founder & CEO
Yonatan Geifman is the CEO and Co-Founder of Deci, the deep learning development platform. Before co-founding Deci, Yonatan was a member of Google AI’s MorphNet team. He holds a PhD in Computer Science from the Technion-Israel Institute of Technology and a B.Sc. and M.Sc. in Computer Science from Ben-Gurion University in Israel. His research focused on making Deep Neural Networks (DNNs) more applicable for mission-critical tasks. It has been published and presented at leading global conferences including the Conference on Neural Information Processing Systems (NeurIPS) and International Conference on Machine Learning (ICML).
PANEL: Making Open-Source Vision AI Easy
Lakshantha Dissayanake
Application Engineer
Lakshantha is Senior Application Engineer for Edge AI at Seeed Studio. He actively stays updated with the latest AI trends and delivers embedded AI applications to the developer community in the means of step-by-step wiki tutorials for NVIDIA Jetson. Also, he delivers technical workshops and takes part in resolving technical issues faced by the community.
Show and Tell: How to Deploy YOLO to (Almost) Anything: Simpler and Faster!
Joseph Nelson
Co-Founder & CEO
Joseph is co-founder/CEO at Roboflow, a company that makes computer vision developer tools (used by over 100k devs) that has raised over 22M from Y Combinator, Craft Ventures, Lachy Groom, the founders of OpenAI, and others. He previously cofounded/sold an NLP startup (Represently), taught at General Assembly, and worked at a few other technology companies. He tweets from @josephofiowa.
Building with Open Source and YOLOv8
Davit Buniatyan
Founder & CEO
At the age of 18, Davit Buniatyan first gained recognition when TechCrunch featured him. After completing a Computer Science degree at University College London (UCL), he began pursuing a Ph.D. at Princeton University at age 20. While at Princeton, Davit concentrated on research at the prestigious Princeton Neuroscience Lab under the guidance of Professor Sebastian Seung.
Davit has been honored with the Gordon Wu Fellowship and the AWS Machine Learning Research Award. His groundbreaking research involved mapping the connectome of the mouse brain. As he grappled with challenges in analyzing extensive, multi-modal datasets at the Neuroscience Lab, Davit discovered a number of pressing challenges in Machine Learning. That is how Davit transitioned into the role of founding CEO for Activeloop. Backed by Y-Combinator and other prominent Silicon Valley funds and angels, Activeloop is building Deep Lake, a Vector Database designed to accommodate all AI data.
PatentPT: Building an LLM-Powered Solution with Enterprise-Grade Memory Agents
Soumik Rakshit
ML Engineer
ML Engineer at Weights & Biases and Google Developer Expert in JAX. I also work on open-source computer vision projects with research interests in the domains of generative computing, image restoration, and computer graphics. I contribute to the open source actively, primarily through the implementation of research papers, end-to-end ML examples, and MLOps integrations for open-source repositories like Ultralytics, Diffusers, Keras, etc.
Supercharging Ultralytics with Weights & Biases
Bo Zhang
Algorithm Strategist
Bo Zhang is an algorithm strategist in Meituan Vision. He received his Master's degree in Informatics at the University of Trento, Italy in 2013. His previous efforts have been put into Automated Machine Learning and Computer Vision. He has collaborated rigorously on the YOLOv6 project.
PANEL: Making Open-Source Vision AI Easy
Yono Mittlefehldt
Machine Learning Advocate
Yono is very interested in all things related to software development and machine learning. He's a Machine Learning Advocate at DagsHub and has previously worked on everything from iOS apps to backend development to high-speed microprocessor circuit design. Yono loves learning new things and sharing knowledge through writing and giving talks. His favorite emoticon is ಠ_ಠ
Building an Active Learning Pipeline, the Easy Way
Dr. Bram Verhoef
Head of Machine Learning
Bram Verhoef has a background in Statistics, Psychology and Neuroscience. After receiving his PhD in 2010 from KU Leuven, he conducted post-doctoral research at Harvard University and The University of Chicago, focusing on the Computational Neuroscience underlying attention mechanisms.
In 2017, he returned to Belgium to work at Imec as a Principal Member of Technical Staff, leading the algorithm development related to a novel analog compute-in-memory Deep Learning chip. In 2021, he Co-Founded Axelera AI and is currently Head of Machine Learning, leading the algorithm optimization efforts for Axelera AI’s state-of-the-art Deep Learning Accelerator.
YOLO Supercharged: Harnessing AI-Native Power
José Benítez Genes
Founder and Director of AI
As the Founder and Director of AI at Intuitivo, I lead a world-class team specializing in computer vision. With a focus on multi-task learning and meta-learning algorithms, we are pioneering innovative solutions that redefine the boundaries of what computer vision models can achieve. I was honored to be recognized as an MIT Innovator Under 35 in 2022, which underscores my commitment to pushing the envelope in AI research and applications. Additionally, I am an active member of the IEEE Computer Society and the Computer Vision Foundation, organizations that further enrich my expertise and network in the fast-evolving field of AI.
Accelerating Retail Transformation with the Power of Foundation Models
Mónica Villas
Technical Advisor and Lecturer
Former IBM executive working in IT for more than 20 years. Currently working as a Technical advisor and lecturer. After many years in IT, I know how technology can be applied to change and improve the business. I am passionate about new ways to teach and learn, and I have deep knowledge of Cloud, Analytics, Artificial Intelligence, and Exponential Technologies, while I continue learning every day.As an Engineer, I love technology and changing the world. I have great abilities to make complex things simple, problem-solving & teamwork. Apart from technology, one of my other passions is people. Leading people was really rewarding and during my 15 years as a leader, I always tried to lead by example. People followed me, which in the end is the main objective of a leader. In all my career the 3 things that helped me the most were people, perseverance, and passion.
AI Ethical Challenges
Glenn Jocher of Ultralytics (YOLOv5 and YOLOv8), Yonatan Geifman of Deci (YOLO-NAS), and Bo Zhang of Meituan (YOLOv6) come together on this panel to explore the state of open-source vision AI. This panel will delve into the challenges and priorities encountered during model implementation, providing valuable insights for seamless AI adoption. Additionally, the panelists will address deployment on edge devices, examine the potential for object re-identification modules, provide insights on model deployment, and more.
There are about 1 billion network cameras worldwide deployed. Smart cameras powered by advanced AI can focus on what matters most and bring spaces safety for everyone from drivers and pedestrians to retailers and shoppers. We will walk you through overall edge performance for video analytics applications inferencing on NVIDIA Jetson and you can upgrade any legacy camera with YOLOv8 model without any line of code.
Join us to see how Axelera AI’s Metis platform delivers industry-leading performance and usability, just at a fraction of the cost and power consumption of solutions available today. Discover the impressive results of our hardware and software solution, optimizing YOLO models for inference on edge devices.
AI is transforming various sectors, commodities, and fundamental functionalities. Nevertheless, deep neural networks consume excessive resources in terms of memory, computational power, and energy. To ensure the widespread adoption of AI, it must operate efficiently on end-user devices, adhering to strict power and thermal constraints. Techniques such as quantization and compression play a pivotal role in mitigating these challenges.
In this webinar, Sony’s product manager, Amir Servi, will walk you through Sony’s Model Compression Toolkit for quantizing and accelerating deep learning models for efficient edge deployment. You’ll learn how to do the same for your own model! What you’ll learn:
- Our latest research in quantization techniques and its implementation into a practical product
- Importance of hardware-aware compression for inferencing on edge
- How engineers and researchers can implement these techniques through Sony MCT
Ultralytics HUB lowers the barriers to entering into the world of ML, making it accessible to individuals and businesses alike, regardless of coding expertise. Learn how this platform is set to revolutionize the way we approach machine learning, empowering a new generation of data enthusiasts to turn their ideas into reality with unprecedented ease.
And don't miss out on our big announcement...
Deploying state-of-the-art models on embedded devices from Edge GPU of NVIDIA Jetson to tiny MCUs presents challenges and limitations. We will walk through how to deploy these models including YOLOv8 in the streamlined approach and overall edge performance for video analytics applications inferencing on NVIDIA Jetson.
Glenn is on a relentless pursuit to develop the finest Vision AI in the world. For him, this is not just a technological achievement, but a vital stepping stone toward realizing the potential of AGI. The spearheads of this relentless pursuit are none other than YOLOv5, YOLOv8, and the Ultralytics HUB.
So, what makes Ultralytics YOLO the best in the world?
Recent advancements in computer vision have been significantly propelled by the introduction of transformer architecture and the user-friendly abstractions to pre-train, fine-tune and infer in 🤗 transformers library. This talk provides an overview of the latest transformer-based vision models, explores the utilities available within the 🤗 transformers library, and offers practical insights into the philosophy behind it.
Tired of long lines at retail checkout? Our Intelligent Queue Management system is the answer! Join us for a step-by-step tutorial on how to create such a system using OpenVINO and YOLOv8. We'll walk you through the process of integrating these powerful open-source tools to develop an end-to-end solution that can be deployed in retail checkout environments. You'll learn how to optimize the application to achieve outstanding performance. Whether you're an experienced developer or new to AI, this session will provide practical tips and best practices for building intelligent systems using OpenVINO. By the end of the presentation, you'll have the knowledge and resources to build your own solution.
In an era defined by rapid advancements in artificial intelligence (AI), navigating the ethical landscape of this technology is paramount. In this session, Mónica will unravel the intricate web of ethical dilemmas that accompany AI's transformative power. From addressing bias and fairness to exploring transparency, accountability, and the profound impact of AI on society, Monica will provide insights that shed light on the ethical considerations surrounding AI.
This talk is your opportunity to gain a fundamental understanding of the ethical challenges and responsibilities associated with AI. Mónica will equip you with knowledge that is essential for anyone engaged in AI development, decision-making, or policy formation.
Foundation Models can be demanding in terms of GPU computation and may not be suitable for real-time applications, especially if you want to scale millions of Autonomous Points of Purchase. But we take advantage of the method called knowledge distillation, where we put our foundation models for complex tasks such as annotations and transfer this knowledge into smaller and cost effective models. This allows us to speed up our annotation process up to 90 times faster than human traditional labeling.
Pssst. Want to hear a secret? What if I told you that active learning doesn't have to be hard. What if there were... an easy way? You're in luck. This talk will show you exactly how to implement an active learning pipeline using DagsHub's Data Engine. And 90% of the pipeline can run directly in a Jupyter Notebook or on Google Colab! By the end of the talk, you'll have the information necessary to convert your existing project into one that uses active learning to efficiently and quickly improve your models' metrics!
Using open source tools with YOLOv8 can help you get your next vision AI project up and running, fast. There are repositories of open source images, libraries to help automate data labeling, tools for tracking or counting, and servers for deploying your models. Learn how to use them with YOLOv8 to build your next application.
The ongoing global race for bigger and better artificial intelligence (AI) systems is expected to have a profound societal and environmental impact by altering job markets, disrupting business models, and enabling new governance and societal welfare structures that can affect global consensus for climate action pathways. However, the current AI systems are trained on biased datasets that could destabilize political agencies impacting climate change mitigation and adaptation decisions and compromise social stability, potentially leading to societal tipping events. Thus, the appropriate design of a less biased AI system that reflects both direct and indirect effects on societies and planetary challenges is a question of paramount importance.
Quantization of machine learning (ML) models can lead to significant decrease in the model size as well as reduction in inference latency due to lower bandwidth requirements. When deployed on hardware options that support integer computations efficiently, the performance gains can be even more dramatic. However, quantization can sometimes lead to unacceptable degradation in accuracy. In this talk, we present an overview of the methods to efficiently quantize YOLOv8 models making them an excellent choice for various real-time edge AI applications. We also introduce a class of YOLOv8 models with ReLU6 activation function that show excellent post training quantization results on a variety of model architectures and datasets. Finally, we illustrate how the quantized models can be deployed on multiple hardware options such as CPUs, Edge TPUs, and Orca (DeGirum’s AI HW accelerator) using simple APIs.
Ultralytics is the home for cutting-edge, state-of-the-art computer vision models for tasks like image classification, object detection, image segmentation, and pose estimation. Weights & Biases is a developer-first MLOps platform that when integrated with an Ultralytics workflow, enables us to easily manage our experiments, model checkpoints, and visualize the results of our experiments in an insightful and intuitive manner. In this session, we will explore how we can effectively supercharge our computer vision workflows using Ultralytics and Weights & Biases.
Learn how we created PatentPT, an advanced language model solution that greatly enhances patent search and interaction capabilities. The presentation offers practical insights on fine-tuning and deploying large language models and leveraging enterprise-grade memory agents to autocomplete patents, generate abstracts and claims, and conduct advanced patent search functions using the rich patent corpus. We’ll walk you through how to develop a similar solution using cutting-edge Activeloop’s Deep Lake, the Database for AI, open-source LLM models, Habana Gaudi HPU hardware, and Amazon Sagemaker’s LLM inference APIs.
We will walk you through architectural blueprints and all the steps we took to build the solution – from training our LLM model and finetuning it, creating custom features, and deploying search APIs.
Whether you’re an AI practitioner looking for practical guides on finetuning LLMs, a legal professional interested in leveraging AI for patent search, or simply curious about the future of AI-enhanced solutions, our talk provides a glimpse into the process and potential of using LLMs in a specialized field. Join us as we share our journey of building custom LLM-powered apps powered by Deep Lake, the Database for AI for companies big and small.
Open source companies are built differently. In this talk, we'll cover what investors will be looking for when considering investing at the Series A. Spoiler: you might not need revenue, but you definitely need momentum! We'll share best-in-class metrics from other OSS companies to help you figure out when to raise.
We'll kick the day off at Google for Startups in Madrid with coffee. The morning features a series of talks, followed by a lunch break hosted by Ultralytics at Google for Startups. After lunch, we'll dive back into more sessions. To cap off YV23, join us for an official networking happy hour, also hosted at Google for Startups.
Attending in person allows you to immerse yourself in the event atmosphere, interact with speakers and fellow attendees, and participate in networking sessions. It's a unique opportunity to engage directly with the vision AI community.
Tickets for YV23 are entirely free, whether you choose to join us virtually or in person.
Calle de Moreno Nieto, 2, 28005 Madrid, Spain.
YV23 offers both virtual and in-person attendance options. To secure your spot, simply complete the registration form located on this page.
If you are in China please find the virtual Bilibili stream here. If you are joining from the rest of the world, please tune in using the virtual Youtube stream here.