KaLM releases R2 reranker on HF: 92% nDCG@10 retained even at 128x compression
tomaarsen · x · 2026-10-30
The KaLM-Embedding team released KaLM-Reranker-V1-Nano-R2 on Hugging Face (built on t5gemma-2-270m, Apache 2.0, sentence-transformers support). According to the authors, even at 128x compression all three R2 models retain over 92% of average nDCG@10 at 2x compression on BEIR and MIRACL, letting users trade reranking quality for compute.
Related event: KaLM R2 Reranker Open-Sourced, Retains 92% Recall at 128x Compression(2 posts)→
More from Research
- PostTrainBench traces hit 104k monthly downloads — author warns it's likely reward hacking — maksym_andr · 2026-10-31
- OpenAI's Navier-Stokes solution accused of specification gaming via unrealistic forcing — dhadfieldmenell · 2026-10-31
- Researchers encode 200+ properties of SGLang inference server, uncover 10 bugs — LingmingZhang · 2026-10-31
- Expert panels map 21 clinical AI risks; adversarial tests show autonomous care still unsafe — AleksandraFaust · 2026-10-31
- Handwritten RAGEN code becomes the #3 hardest task in FrontierCS 2 — wzenus · 2026-10-31
- Fudan, Tencent Hunyuan and Tsinghua unveil ExplorationBench to test AI rule discovery — jiqizhixin · 2026-10-31