GenML, returning for its second year, focuses on generative AI integration with ML models. This conference brings together researchers, data scientists, data engineers, ML experts, professionals from leading companies, and more to discuss recent developments in the field. The event will focus on research aspects related to generative AI and ML integration.
Join us at GenML to connect with industry leaders, exchange ideas with fellow practitioners, and contribute to ongoing generative AI research. This is an opportunity to learn about cutting-edge developments, share your insights, and engage with experts in this field.
Register now to secure your place at this must-attend event!
10.12.2024
09:00-17:00
ZOA House | Daniel Frisch St 1,TLV
8:30-9:30
Gathering & mingling
09:30-09:40
Opening remarks
Uri Eliabayev
Founder at MDLI
9:40-10:10
Easily build Gen AI application with RAG, Agents and Evaluation, using Amazon Bedrock
Gili Nachum
Principal Gen AI & ML Solutions Architect at AWS
10:00-13:00
Generative-AI on the go, The AI revolution on your AI-PC. Workshop for IDF reserve members or their partners.
Generative-AI on the go, The AI revolution on your AI-PC.
Join us for a hands-on workshop where you can visualize the latest AI algorithms and experience code building.
Spend 3 hours learning and tinkering with the state-of-the-art AI technologies on AI-PCs.
What will we learn
Understand the main differences between a CPU, GPU and NPU
Learn which models perform best on each type of device.
Discover how to program and maximize the potential of an AI-PC.
Explore how Large Language Models (LLMs) generate text.
Create a chatbot and delve into Retrieval Augmented Generation (RAG).
Learn how text-to-image technology works.
Generate stunning images or videos using stable diffusion and other methods.
Can LLMs generate music?
Advanced music editing and music generation on your laptop.
Who should attend
Requirements
The workshop is offered now only for IDF reserve members or their partners.
Applications require a reserve approval certificate!
Guy Tamir
Technology Evangelist, Director: oneAP at Intel
10:10-10:40
GenAI in the Wild: Protecting Your Herd from Predators
GenAI is a powerful technology that is being rapidly adopted for a plethora of use cases. However, its power also makes it a prime target for attackers looking to exploit vulnerabilities. In this talk, we will discuss the need for GenAI security and the challenges involved in defending against GenAI attacks. We will highlight the complexity of the threat landscape and the difficulties in threat detection in the context of constantly evolving use cases. Join us as we explore this unexplored and misunderstood domain and discuss our efforts to invent the wheel at Intuit with GenOS and GenSRF.
Ido Farhi
Senior Data Scientist at Intuit
10:40-11:10
Making AI development easy with Prompt Flow
Prompt Flow is an open-source development tool designed to streamline the entire development cycle of AI applications powered by LLMs. Prompt Flow simplifies the process of prototyping, experimenting, iterating, and deploying your AI applications, and has its own VSCode extension.
In this session I'll introduce Prompt Flow and demonstrate how you can use it for building a chat flow, evaluate it and use it as an LLMOps tool.
Lior King
Sr. Cloud Solutions architect - Data & AI at Microsoft
11:10-11:30
Weights & Biases
11:30-11:50
Exploring Function Calling with Gemini
Traditional LLMs have limitations. They can't access up-to-date information or interact with the real world meaningfully. Function calling solves these problems. This session explores how function calling expands the capabilities of LLMs.
Sveta Morag
Cloud Solutions Architect at Google Cloud
11:50-12:20
Break
12:20-12:40
Profiling Buyer Interests Using LLM-Generated Graphs
How can we understand the core interests and passions of our buyers? How can we use this knowledge to introduce them to products they have yet to discover?
While typical recommendations often focus on items similar to those already viewed, our goal is to identify the deeper passions that drive buyers' shopping habits. This allows us to suggest related products from entirely different categories.
We use graphs generated by Large Language Models (LLMs) to represent buyers' interests. These graphs help us distinguish between different user interests and traverse the graph to identify various levels of interest granularity.
Oded Zinman
Applied Researcher at eBay
12:40-13:00
How to build GenAI agents that actually work
Talking about GenAI agents is easy, but building ones that actually work is very hard.
In this talk I will shorty introduce what GenAI agents are and will talk about the three biggest challenges in implementing them:
Accuracy and user trust, latency and cost.
I will share a general framework for building GenAI agents using different techniques including different building blocks, planning and methods of evaluation.
I will also discuss how we, at AI21 labs are using these methods to deliver agent based products that actually work
Amit Mandelbaum
Tech Lead at AI21 Labs
13:00-13:20
Agentic AI in Production
What are AI agents?
How do they differ from non-agentic AI products?
What real-world problems do they solve?
What are the essential components for developing agentic pipelines?
How can we scale AI agents, and what is the technology stack in this field?
Lior Cohen
Senior Data Scientist at Nvidia
13:20-13:40
Near-Realtime RAG on Production Data: Bringing AI to the Data
Retrieval-augmented generation (RAG) implementations are becoming increasingly popular, and there is a growing demand for these systems to operate at near-realtime speeds and at scale.
In this session, we present our approach to meet these challenges by bringing the algorithms closer to the data. This involves integrating vector search capabilities with popular databases, enabling RAG implementations on production data.
Specifically, we discuss the necessity of vector data types and the development of advanced index solutions, such as graph-based or inverted-file vector indices, to handle large-scale data efficiently.
By incorporating these features into existing database systems, we aim to unlock the potential for generative AI applications on a grand scale. This session will explore the current state of vector search capabilities, RAG implementations, and other generative AI-related features in a leading database system, highlighting the opportunities and challenges of deploying near-realtime RAG on production data.
Boris Dahav
Data, Analytics & AI Domain Specialist at IMOD Division, Oracle
13:40-14:00
Building the Future: AI Infrastructure in the GenAI Era
Ronen Dar
Co-Founder and CTO at Run:ai
14:00-15:00
Break
15:00-15:20
Is My LLM Doing a Good Job? Evaluating LLMs at Scale: Lessons Learned from Lightricks
As large language models (LLMs) become increasingly integrated into industry workflows, a pressing question arises: how do we know if our LLMs are truly delivering value across different user interactions?
This talk, drawing on lessons learned at Lightricks, explores real-world challenges in evaluating LLMs at scale, particularly for creativity-related use cases where there is no single correct answer. We’ll dive into the challenges we faced and share the evaluation framework we developed to align with specific business objectives and user experiences. Attendees will gain practical insights into measuring LLM effectiveness in dynamic, real-world environments, ensuring models are efficient and impactful for their intended use cases.
Asi Messica
VP Data Science at Lightricks
15:20-15:40
AI-Driven Meeting Prep summaries: Helping Client preparation
In this talk, I’ll present how we developed an AI-powered tool at HoneyBook that automatically generates tailored meeting summaries for members. The tool analyzes key data points, including previous meeting notes, client context, shared files, and business insights, to provide members with actionable snapshots before each meeting. This enables them to be better prepared, engage more effectively with clients, and make data-driven decisions. Attendees will learn how AI can enhance productivity through personalized, context-rich insights, and I will explore the technical implementation, challenges faced and results
Doron Bartov
Staff Data Scientist at HoneyBook
15:40-16:00
Taking AI to the smallest scale
AI and LLM are in the world on a vast scale. But you can take ML model and LLM to a tiny scale – to the IoT world! You can run models even on tiny microprocessors that cost $4. In this session, you will learn how to work with LLM and ML models on small IoT devices to create exciting and smart devices with low cost and effort
Ran Bar-Zik
Senior Software Architect at CyberArk
16:00-16:20
Training State-of-the-Art Language Models, Lessons from reaching OpenLLM's Leaderboard 1st spot
Yam Peleg
Founder & CEO at Deep Trading
Only 100 tickets are available. For purchasing more than one ticket, please contact [email protected]
355 ILS
Buy NowFor purchasing more than 3 tickets, please contact [email protected]
465 ILS
Buy NowThe workshop is offered only for IDF reserve members or their partners at a special price. Applications require a reserve approval certificate. Limited to 30 tickets.
279 ILS
Buy Now