Inside LinkedIn's L1/L2 rankers: twin MLP models scoring topic fit and dwell time
_jaydeepkarale · x · 2026-11-06
LinkedIn's multi-stage ranking uses L1 and L2 rankers with nearly identical architectures (text embedding models + MLP), differing only in size and features. Candidates shrink from thousands to hundreds after L1. Each stage outputs on-topicness and long-dwell scores, combined by a multi-objective score combiner to determine final ranking.
More from Research
- UBC and Sony release Solv3R, turning a looped Transformer into a reusable 3D geometry solver — CSProfKGD · 2026-11-06
- Discovery Loop member launches $DISCODEV open AI materials-discovery loop — arkitus · 2026-11-06
- Northwestern turns ordinary smartwatches into hand and gesture sensors with TransfHAR and electrode-based system — realkaranahuja · 2026-11-06
- Three researchers solo-prompting Bing Chat for four weeks gets roasted as a study — Sauers_ · 2026-11-06
- New attention kernels meet real models: where interpretability overlaps systems research — QuentinAnthon15 · 2026-11-06
- MoE All-to-All Comms Eat 60% of Training Steps; Correlated Placement Cuts 58% of Dispatched Rows — QuentinAnthon15 · 2026-11-06