AI Day - Apr 25
19 talks in this track
Leveraging Large Language Models for Automated Generation and Validation of Financial Descriptions for Lithuanian Companies
talkScoris.lt utilized Large Language Models (LLMs) to address the challenge of improving SEO performance by generating financial descriptions for Lithuanian companies. The case study highlights the innov...
When safety is non-negotiable - 3 stages of building safety using data & AI
talkThe more users your platform attracts, the more unwanted attention you'll get from people looking to game your system. While every product is unique, the journey of tackling these bad actors tends to ...
Pydantic: Crafting confidence in AI apps
talkPydantic, Pancakes and Poter quick though deep dive into the world of response modeling
Unlocking the Power of Python and PyTorch for Biomedical Image Segmentation
talkHow can machine learning enhance biomedical image analysis? This talk explores the potential of Python and PyTorch in automating artifact and damage segmentation. From data preprocessing to clustering...
📂 Slow Productivity AI: Automating Knowledge & Task Management with Offline Hugging Face, n8n & Obsidian
talkModern work demands constant context-switching—emails, notes, meetings, and tasks pile up, leaving us overwhelmed. This talk introduces a <b>slow productivity AI</b> approach, inspired by <b>Cal Newpo...
The Emergence of Agentic Workflows in AI
talkAI is evolving from passive tools to autonomous agents, driving the rise of agentic workflows that can plan, execute, and optimize tasks with minimal human input. This session will explore how large l...
From Raw Transactions to Insights: The Power of Embeddings in Fintech
talkFinancial transactions generate vast amounts of sequential data, yet traditional risk assessment models often rely on predefined features that may not capture the full complexity of user behavior. Thi...
Surprisal and the headache of tokenizer encodings in LLMs!
talkWhat can go wrong with tokenizer encodings? Everything! I will share my experience of understanding, misunderstanding, and ultimately learning to work with tokenization in LLMs. I will discuss what su...
How We Outperformed Microsoft, Google, and OpenAI in Speech-to-Text
talkWe built a cutting-edge speech-to-text model that outperformed solutions from industry leaders like Microsoft, Google, and OpenAI. This is the story of how we identified a market gap, defined what mak...
The Best of Both Worlds: A Hybrid Approach to Lightning-Fast Product Matching
talkIn an era dominated by data, businesses struggle with processing diverse, unstructured information across systems. This research presents an AI-powered pipeline addressing product matching challenges ...
Building multi-agent AI applications made easy with LangFlow
talkAI agents are transforming the way we create applications. However, developing multi-agent applications can often feel complex and time-consuming. LangFlow simplifies this process by offering an intui...
How to evaluate fairness and safety in LLM applications?
talkFairness and safety are fundamental criteria for building trustworthy and high-quality AI systems, whether they are credit scoring models, hiring assistants, or healthcare chatbots. But what does it t...
Knowledge Bases & Memory for Agentic AI
talkSome of the latest big evolutionary steps in generative AI has been models that support function calling and “agentic” capabilities. This is provides generative models with “tools” that allow them to...
GenAI for Clients: No pain, no gain
talkWhat is the way from prove of concept to big production solutions for GenAI application? How to make it scalable and make one release by 7 sprints?
Anonymization of sensitive information in financial documents using, python, diffusion models and named entity recognition
talkUnlock sensitive data potential with anonymization! Learn how Python, diffusion models, and Named Entity Recognition (NER) empower institutions to anonymize PII in financial documents, replacing it wi...
Enhancing Model Context Protocol (MCP) with Dynamic Tool Discovery for Smarter AI
talkThe Model Context Protocol (MCP) is an emerging standard that enables structured data provisioning for LLMs and AI agents. However, the current data discovery mechanism in MCP is static. This limits ...
Code Generation in Regulated Industries: Opportunities and Challenges
talkAI-driven code generation can transform software development in regulated sectors like banking and insurance - but only if implemented securely and responsibly. In this talk, we’ll explore how to harn...
EGTL data-processing model prototype using Python
talkDiscover how EGTL (Extract, Generate, Transfer, Load) extends traditional ETL by adding a “generate” step powered by GenAI. In this talk, I’ll demonstrate how Python pipelines on top of data warehouse...
AI 360: From Theory to Transformation
talkThis talk charts the evolution of Artificial Intelligence through the dual lenses of data and models, tracing AI’s journey from early symbolic systems to today’s advanced data-driven techniques. Atten...