The Map Is Not The Territory – Highly Multimodal Search

Hosted by Bryan Bischof and Ayush Chaurasia

Fri, Jul 11, 2025

5:00 PM UTC (45 minutes)

Virtual (Zoom)

Free to join

782 students

Invite your network

Go deeper with a course

Save 20% til Sunday

AI Evals For Engineers & PMs
Hamel Husain and Shreya Shankar
View syllabus

What you'll learn

Why a single representation for your data isn’t enough

A document isn’t only it’s bag of words, chunks, or latent features – it’s the modes which a user may query it!

How the old concepts of search are still relevant

Multi-index, Query Understanding, and Query Rewriting are more powerful than ever before; how should you use them?

How we built a modern search engine for multimodal data

We’ll discuss the technical challenges and how we overcame them.

Why this topic matters

For AI applications, or for any retrieval based product, neural search continues to prove itself as one of the most essential technologies for powering the web. Unfortunately, amidst the noise of new techniques and applications, it’s easy to miss the path from the old techniques. www.google.com

You'll learn from

Bryan Bischof

Head of AI at Theory Ventures

Bryan leads AI at Theory. Bryan has worked all across the data, ML, and AI stacks. Most recently, Bryan Bischof was the Head of AI at Hex, where he led the team of engineers building Magic—the data science and analytics copilot. He started the data team at Blue Bottle Coffee, led several projects at Stitch Fix, and built the data teams at Weights and Biases. Bryan previously co-authored the book Building Production Recommendation Systems with O’Reilly, and teaches Data Science and Analytics in the graduate school at Rutgers. His Ph.D. is in pure mathematics.

Ayush Chaurasia

Founding ML Engineer, LanceDB

Ayush Chaurasia is a founding ML Engineer at LanceDB, with 7+ years of experience in AI, computer vision, and software engineering. He’s contributed to open-source projects like YOLOv8 (Ultralytics). At LanceDB, Ayush works on hybrid search, multi-modal retrieval, and reranker architectures.

Previously at

Weights & Biases
LanceDB
Stitch Fix

Learn directly from Bryan Bischof and Ayush Chaurasia

By continuing, you agree to Maven's Terms and Privacy Policy.

© 2025 Maven Learning, Inc.