ACM TechTalks

ACM members and non-members alike are welcome to attend our popular series of free TechTalks by expert industry professionals, distinguished ACM award laureates, and visionary researchers from industry and academia. Focused on keeping our global audience of busy practitioners at the forefront of technical trends, professional development, and emerging technologies, the TechTalks are also popular with students and educators. Recent talks have covered topics in Artificial Intelligence and Machine Learning, Big Data and Data Science, Blockchain, Computer Vision, Deep Learning, JavaScript, Microservices, Python, Quantum Computing, and more. Registration is free and the TechTalks can be attended both live and on-demand, on desktop and mobile devices. Check this page frequently for upcoming events as well as our on-demand archive. To subscribe to our TechTalk announcements, email [email protected].

ACM TechTalks

View Our Recent TechTalk

Research to Reality Building Production Ready LLM Apps Users Can Trust

Large Language Models have revolutionized AI applications, but transitioning from research prototypes to production-ready systems presents significant challenges in reliability, accuracy, and deployment readiness. This talk presents battle-tested strategies for building trustworthy LLM applications, with a special focus on RAG pipelines, chatbots, and AI agents. Drawing from real-world implementations across different industries, we'll explore practical techniques for minimizing hallucinations, optimizing performance, and ensuring ethical deployment.

Overview
We'll begin by examining the reliability challenges facing LLM applications in production environments, from hallucinations to consistency issues. The talk will then dive into architectural patterns for building trusted RAG pipelines and implementing effective hallucination prevention systems, illustrated through a live example of building reliable agents. We'll explore the emerging field of reliable AI agents, covering essential safety mechanisms and validation frameworks.

Target Audience
This talk is designed for software engineers, ML practitioners, and technical leads who are working to deploy LLM applications in production environments. Attendees should have basic familiarity with LLMs, but deep expertise is not required.

Takeaways
Attendees will leave with practical implementation patterns, validation frameworks for chatbots and agents, and strategies for building reliable LLM applications that users can trust.

ACM Learning Center TechTalk Archive

ACM award winners, leading researchers, industry veterans, thought leaders, and innovators address today and tomorrow's hottest topics and issues in computing for busy practitioners, as well as educators, students, and researchers. Check out our archive of these ACM TechTalks, free for members and non-members alike.

TechTalks on Artificial Intelligence & Machine Learning

Talks from some of the leading visionaries and bleeding-edge researchers in AI/ML: Fei-Fei Li on visual intelligence in computers and ImageNet; Eric Horvitz on AI solutions in the open world; and Tom Mitchell on using ML to study how the brain creates and represents language.

30 October 2024 :

Developing Vascular Digital Twins to Shift from Reactive to Proactive Care with Amanda Randles

2 October 2024 :

Lessons Learned from Building GitHub Copilots with Eddie Aftandilian

12 September 2024 :

Introduction to Retrieval Augmented Generation with Abhinav Kimothi

ACM TechTalks

Wei-Meng Lee TechTalk

Register now for the next free ACM TechTalk, "Unlock Hugging Face: Simplify AI with Transformers, LLMs, RAG, Fine-Tuning," presented on Wednesday, February 12 at 12:00 PM ET/17:00 UTC by Wei-Meng Lee, Founder of Developer Learning Solutions. Marlene Mhangami, Senior Developer Advocate at Microsoft, will moderate the questions and answers session following the talk. Continue the discussion on ACM's Discourse Page.

ACM TechTalks

Scott Tilley TechTalk

View the recent ACM TechTalk, "Testing the System: A Holistic Approach to Security in Systems Development," presented by Scott Tilley, an Emeritus Professor at the Florida Institute of Technology. Will Tracz, former Chair of ACM SIGSOFT and member of the ACM Professional Development Committee, moderated the questions and answers session following the talk. Continue the discussion on ACM's Discourse Page.

ACM TechTalks

View Our Recent TechTalk

ACM Learning Center TechTalk Archive

TechTalks on Artificial Intelligence & Machine Learning

View Latest Learning Center TechTalks

Developing Vascular Digital Twins to Shift from Reactive to Proactive Care with Amanda Randles

Lessons Learned from Building GitHub Copilots with Eddie Aftandilian

Introduction to Retrieval Augmented Generation with Abhinav Kimothi

Wei-Meng Lee TechTalk

Scott Tilley TechTalk