LightOn Unveils Reranker Model Series
tomaarsen · x · 2026-07-17
@LightOnIO released LightOn-rerank, a series of rerankers capable of scoring queries against text passages or document page images.
Key features:
- A total of 6 models across 0.8B / 2B / 4B scale parameters;
- Each scale offers both pointwise and generative listwise variants;
- Designed for retrieval/reranking scenarios involving text and images.
This is primarily a retrieval infrastructure release rather than a standard demo.
Related event: LightOn-rerank Targets Mixed-Corpus RAG With Multimodal Rerankers(10 posts)→
More from Research
- UK AISI: under $80 of fine-tuning fully restores filtered bio capabilities in open-weight models — connoraxiotes · 2026-10-27
- RFD4-Proteina runs on an RTX 3060: protein design from $0.001 per design — AllThingsApx · 2026-10-27
- University of Freiburg's Generative Intelligence Lab recruiting funded PhDs via ELLIS, apply by Oct 31 — yuyinzhou_cs · 2026-10-27
- Nature Physics: reprogrammable refractive index enables arbitrary multimode wave control for ML — MarioKrenn6240 · 2026-10-27
- Wakaru open-sources ontologize: labeling datasets from model activations — amplifiedamp · 2026-10-27
- EMNLP Oral paper traces multilingual representations in LLMs with cross-layer transcoders — ZhijingJin · 2026-10-27