LightOn open-sources SOTA sparse retrievers SlideOn at 174M and 339M params
antoine_chaffin · x · 2026-10-20
LightOn R&D released SlideOn and mSlideOn, fully open-source SOTA sparse retrievers at 174M and 339M parameters. Framing it as the next wave after dense and late-interaction retrieval, the team shared weights and a blog. Resharer bclavie highlighted the idea of stacking an SAE on a good retriever so concepts 'want to shout', predicting interpretability will become a major contributor to retrieval research.
Related event: LightOn Open-Sources SOTA Sparse Retrievers SlideOn and mSlideOn(9 posts)→
More from Models
- Users slam Anthropic's bio safeguards for triggering on harmless, unrelated prompts — BlackHC · 2026-10-20
- MiniCPM-V 4.7 runs locally at 100 tok/s on just ~3 GB of memory — NielsRogge · 2026-10-20
- DeepSeek v4.1 flash model now live on Tinker — cHHillee · 2026-10-20
- The deslop experiment: 161 training answers on a MacBook Air zeroed out em dashes — wateriscoding · 2026-10-20
- DeepSeek and MiniMax Show Strikingly Similar Chain-of-Thought Styles, Sparking Distillation Talk — teortaxesTex · 2026-10-20
- Gemini Pro user rants: Argon usage cap hits after just 5 prompts — Atomicfarms · 2026-10-20