A 64-slide lecture gives a broad tour of multi-vector search models
IgorCarron · x · 2026-07-24
A set of slides from Amelie Tabatta’s guest lecture on AI-powered search is being shared, with the thread highlighting that it gives a strong overview of multi-vector models and the current frontier of the field.
The original talk grew out of a deep dive into the “multi-vector rabbit hole,” and the posted material is framed as a substantial 64-slide deck rather than a quick summary.
Related event: 64-Slide Deck Systematically Reviews Multi-Vector Search(2 posts)→
More from Research
- Physics-IQ audit finds ambiguous prompts and artifacts can reshuffle video-model rankings — DynamicWebPaige · 2026-07-25
- Apple-π benchmarks video models on physical-law reasoning — ziqi_huang_ · 2026-07-25
- Podcast preview: HUG explores human universal grasping for robots — chris_j_paxton · 2026-07-25
- New preprint uses AlphaFold3 ensembles to predict TCR–pMHC binding — quaidmorris · 2026-07-25
- Stanford HAI warns that averaging expert safety scores can erase good chatbot advice — StanfordHAI · 2026-07-25
- Claude Opus 4.8 hits 16.5% on ProgramBench’s almost-resolved metric — jyangballin · 2026-07-25