RAG and Multimodal ML āØ
Jun 12, 10:30 PM - Jun 13, 12:30 AM (GMT)
Midtown
20 attendees
Join PyData NYC on June 12th at 6:30 pm for a talk night with Jigisha Mavani (IBM) and Shafik Quoraishee (New York Times). Please bring your š» to code along and sign up with your government official name!
š Pizza, drinks & venue sponsored by Microsoft - thank you!
Agenda:
RAG: Using Translation Augmented Generation to Break Language Barriers in the LLM Ecosystem
Speaker: Jigisha Mavani (IBM)
The training data used by most LLMs, such as the Common Crawl dataset used by the GPT series, is heavily skewed towards English content. This impacts the response quality of prompts from low-resource languages. Learn how to use Translation Augmented Generation to access the power of existing LLMs without the need for expensive fine-tuning or building from scratch and retain cultural nuance.
Multi-Modal Machine Learning and Image Visualization/Segmentation
Speaker: Shafik Quoraishee (Senior Android/ML Engineer)
This talk will take a dive into the core theories and mechanisms behind multi-modal AI models, the powerful AI systems that integrate intelligence from diverse data sources such as text, AI, and vision. While we will reference popular applications like GPT Vision, Gemini, and Sora as illustrative examples, our focus will primarily be on understanding the foundational principles that enable capabilities such as real-time image/video analysis, hyper-segmentation of images, and image-to-text extraction among others.
Networking
Connect with fellow data enthusiasts, professionals, and community leaders. Build meaningful connections and forge collaborations.
----------------------------------------------------------------
Doors open @ 6 pm
Doors close @ 7 pm
Event @ 6:30 - 8:30 pm
----------------------------------------------------------------
The building requires a government-issued photo ID for entrance.
This, and all PyData NYC events, is an all-level event. Newcomers and beginners are welcome.
This, and all NumFOCUS-affiliated events and spaces, both in-person and online, are governed by a Code of Conduct.
----------------------------------------------------------------
This event may be recorded.
RAG and Multimodal ML āØ
Host/s
Jun 12, 10:30 PM - Jun 13, 12:30 AM (GMT)
Midtown
20 attendees
š Pizza, drinks & venue sponsored by Microsoft - thank you!
Agenda:
RAG: Using Translation Augmented Generation to Break Language Barriers in the LLM Ecosystem
Speaker: Jigisha Mavani (IBM)
The training data used by most LLMs, such as the Common Crawl dataset used by the GPT series, is heavily skewed towards English content. This impacts the response quality of prompts from low-resource languages. Learn how to use Translation Augmented Generation to access the power of existing LLMs without the need for expensive fine-tuning or building from scratch and retain cultural nuance.
Multi-Modal Machine Learning and Image Visualization/Segmentation
Speaker: Shafik Quoraishee (Senior Android/ML Engineer)
This talk will take a dive into the core theories and mechanisms behind multi-modal AI models, the powerful AI systems that integrate intelligence from diverse data sources such as text, AI, and vision. While we will reference popular applications like GPT Vision, Gemini, and Sora as illustrative examples, our focus will primarily be on understanding the foundational principles that enable capabilities such as real-time image/video analysis, hyper-segmentation of images, and image-to-text extraction among others.
Networking
Connect with fellow data enthusiasts, professionals, and community leaders. Build meaningful connections and forge collaborations.
----------------------------------------------------------------
Doors open @ 6 pm
Doors close @ 7 pm
Event @ 6:30 - 8:30 pm
----------------------------------------------------------------
The building requires a government-issued photo ID for entrance.
This, and all PyData NYC events, is an all-level event. Newcomers and beginners are welcome.
This, and all NumFOCUS-affiliated events and spaces, both in-person and online, are governed by a Code of Conduct.
----------------------------------------------------------------
This event may be recorded.