Late-interaction retrieval recipe paper accepted at EACL 2027: open data fueled follow-up research
antoine_chaffin · x · 2026-11-13
The (m)DenseOn / (m)LateOn open-recipe paper is accepted at EACL 2027. Author antoinechaffin highlights the models' multilingual generalization of late-interaction architectures and argues the released data enabled studies and models not possible before: "Open source creates a race to the top."
More from Research
- Open-weights AI text detector ParaTrace v8 hits 99.2% TPR at 1% FPR, 5th on RAID leaderboard — AltruisticCouple3491 · 2026-11-13
- A curated 9-paper reading path into LLM quantization for beginners — East-Muffin-6472 · 2026-11-13
- HF open-sources Ettin rerankers: six sizes, SOTA, full training recipe — antoine_chaffin · 2026-11-13
- LightOn open-sources DenseOn: SOTA single and multi-vector retrieval models — antoine_chaffin · 2026-11-13
- NVIDIA's VLA driving model hits 20 decisions/s on Jetson Thor after Embedl optimization — No-Dragonfly6246 · 2026-11-13
- DeepMind used LLMs to write 6M lines of Lean proofs, verifying Signal's crypto to machine code — pushmeet · 2026-11-13