
00:00 Intro01:31 Leo's story09:59 SPLADE: single model to solve both dense and sparse?21:06 DeepImpact29:58 NMSLIB: what are non-metric spaces34:21 How HNSW and NMSLIB joined forces41:11 Why FAISS did not choose NMSLIB's algorithm43:36 Serendipity of discovery and the creation of industries47:06 Vector Search: intellectually rewarding, professionally undervalued52:37 Why RDBMS Still Struggles with Scalable Vector and Free-Text Search1:00:16 Leo's recent favorite papersLeo Boytsov on LinkedIn: https://www.linkedin.com/in/leonidboytsov/ and X: https://x.com/srchvrsLeo Boytsov’s paper list: https://scholar.google.com/citations?hl=en&user=I79y2i4AAAAJ&view_op=list_works&sortby=pubdateLots of papers and other material from Leo: https://www.youtube.com/watch?v=gzWErcOXIKk
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.

AI Webinar - Building an AI-Ready Data Backbone

Trey Grainger - Wormhole Vectors

Economical way of serving vector search workloads with Simon Eskildsen, CEO Turbopuffer

Adding ML layer to Search: Hybrid Search Optimizer with Daniel Wrigley and Eric Pugh
Free AI-powered recaps of Vector Podcast and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.