LightOn and search experts to teach free Late Interaction course with 5-30x index compression tricks
IgorCarron · x · 2026-10-12
LightOn's Amélie Chatelain, Trey Grainger and Doug Turnbull will host a free Maven session (Oct 19) on Late Interaction in 2026: why single-vector search loses context, how token-level embeddings improve retrieval across text/code/visual, index optimizations like NextPlaid beyond naive MaxSim, and production tricks to shrink indexes 5-30x at tens-of-ms latency.
More from Research
- Free-threaded Python 3.14t plus fastsimd parses JSON at 65.7 GB/s on 64 cores — lemire · 2026-10-12
- NVIDIA's open-source SDM library unifies tabular foundation models — pandeyparul · 2026-10-12
- Qwen releases QwenGyre: elastic GPU scheduling speeds long-horizon agent RL training by up to 1.85x — Alibaba_Qwen · 2026-10-12
- Crowdsourced push on integer multiplication bounds stalls: κ improves only 0.7%, geometry experts sought — iskander · 2026-10-12
- Turning classification into answer tokens: a head-free recipe for decision models — LysandreJik · 2026-10-12
- Sandberg: treat papers like software projects in need of patching — anderssandberg · 2026-10-12