KURE-v2: A 154M-Parameter Korean-English Retrieval Model Hits SOTA on Korean MTEB
antoine_chaffin · x · 2026-09-03
KURE-v2 is a new Korean-English bilingual late-interaction retrieval model achieving state-of-the-art performance, reaching 0.8160 avg nDCG@10 on Korean MTEB v2 with only 154M parameters. Model, code, and deployment reproductions are open-sourced.
More from Research
- Revera: Lean-verified POSIX regex engine with identical output in 6 languages — jedisct1 · 2026-09-03
- ChatGPT helps resolve 30-year-old stable forking conjecture in logic — Dr_Singularity · 2026-09-03
- Yale trio's new paper: mechanism design for AI agents with unknown alignment — Afinetheorem · 2026-09-03
- PufferLib 5.0 Self-Play Trains 10-Ship Duel in 5 Minutes on a $700 PC — yacineMTB · 2026-09-03
- Until Labs scales cryoprotectant discovery to 250,000+ candidate molecules with AI — lukaszkaiser · 2026-09-03
- Stanford's Michael Bernstein builds a "What-If Machine" for simulating decisions with AI — msbernst · 2026-09-03