🎥 Once a month, we'll meet, socialize, and hear speakers present topics on unstructured data and generative AI. This event was sponsored by Zilliz.
Timeline:
00:30 - Speaker Stephen Batifol - Exploring Multimodal Embeddings with Milvus
18:40 - Speakers Robert Caulk & Elin Törnquist - Multi-lingual narrative tracking in the news - real-time experiments
38:43 - Speakers Iaroslav Amerkhanov & Nikolay Ulyanov - "I see eyes in my soup": How Delivery Hero implemented the safety system for AI-generated images
~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~
🎥 Playlist • Unstructured Data Meetup
🖥️ Website: www.meetup.com...
X Twitter - / milvusio
🔗 Linkedin: / zilliz
😺 GitHub: github.com/mil...
🦾 Invitation to join discord: / discord
~~~~~~~~~~~~~~ MEETUP VIDEO CONTENTS ~~~~~~~~~~~~~~
1. Speaker & Host: Stephen Batifol, Zilliz
LinkedIn: / stephen-batifol
Title: Exploring Multimodal Embeddings with Milvus
Abstract: Explore how multimodal embeddings work with Milvus. We will see how you can explore a popular multimodal model - CLIP - on a popular dataset - CIFAR 10. You use CLIP to create the embeddings of the input data, Milvus to store the embeddings of the multimodal data (sometimes termed “multimodal embeddings”), and we will then explore the embeddings.
2. Speakers: Robert Caulk & Elin Törnquist, Emergent Methods.ai
Title: Multi-lingual narrative tracking in the news - real-time experiments
Abstract: We present an architecture of embedding models, vector databases, LLMs, and narrow ML for tracking global news narratives across a variety of countries/languages/news sources. As an example, we explore the real-time application of this architecture for tracking the news narrative surrounding the death of Russian opposition leader Alexei Navalny coming from Russian, French, and English sources.
3. Speakers: Iaroslav Amerkhanov & Nikolay Ulyanov, Delivery Hero
Title: "I see eyes in my soup": How Delivery Hero implemented the safety system for AI-generated images
Abstract: In this talk, we are going to cover the use-case of food image generation at Delivery Hero, its impact and the challenges.
In particular, we will present our image scoring solution for filtering out inappropriate images and elaborate on the models we are using.
▼ ▽ LINKS & RESOURCES
📒 Stephen’s slides (Zilliz): www.slideshare...
📒 Robert & Elin’s slides (Emergent Methods): www.slideshare...
📒 Iaroslav & Nikolay’s slides (Delivery Hero): www.slideshare...
3 окт 2024
