SlideOn hits sparse SOTA on BEIR-15 at 56.68, beating its dense baseline at 56.20
IgorCarron · x · 2026-10-19
SlideOn scores 56.68 on BEIR-15, SOTA among sparse baselines and above its dense counterpart DenseOn (56.20). Query-vector pruning (q-16 to q-full) puts it on the search-efficiency frontier: q-32 already reaches 56 BEIR-15 at 5 retrieval FLOPS, well ahead of SPLADE-v3 and other sparse baselines.
Related event: LightOn Open-Sources SOTA Sparse Retrievers SlideOn and mSlideOn(8 posts)→
More from Research
- 39-day home agent experiment shows why fully agentic development is unsolvable — RexDouglass · 2026-10-20
- Forward-only pretraining matches backprop: 3.704 val in 2.5 min on 8×H100, no autograd — tensorqt · 2026-10-20
- NeurIPS 2026 paper 'Intelligence per Watt' measures on-device AI efficiency across 1M queries — HazyResearch · 2026-10-20
- Cohere Labs talk: Goodfire's Matthew Kowal on interpretability across the model design pipeline — Cohere_Labs · 2026-10-20
- NeurIPS paper: AI models can provably hide arbitrary capabilities in encrypted weight backdoors — MoonL88537 · 2026-10-20
- 26,811-pupil study: AI lifts homework scores in China but hurts exam performance — Dr_Alex_Crimi · 2026-10-20