Reranking

Sentence Transformers 5.5.0 adds an agent skill for fine-tuning embeddings, rerankers, and sparse encoders from Claude Code, Codex, Cursor, and Gemini CLI. The author reports a one-shot German embedding run rising from 0.6720 to 0.8856 NDCG@10 on a local PC.

LightOn open-sourced DenseOn and LateOn plus the training pipeline behind them, including 1.4 billion query-document pairs and decontaminated BEIR results. Teams can use the small open retrieval models and reproduced data mixtures instead of opaque closed-data baselines.

Sentence Transformers v5.4 adds one encode API for text, image, audio, and video, plus multimodal reranking and a modular CrossEncoder stack. It also flattens Flash Attention 2 inputs for text workloads, reducing padding waste and VRAM use.

LightOn says its 150M multi-vector retriever is pushing BrowseComp-Plus close to saturation, with results showing search-call behavior and retriever choice matter nearly as much as model size. Retrieval engineers should watch multi-hop setup and tool-calling limits before copying the benchmark.

LightOn’s late-interaction retriever paired with GPT-5 reached 87.59 accuracy on BrowseComp-Plus while using fewer search calls than larger baselines. It suggests deep-research quality may now hinge more on retrieval architecture than on swapping in ever larger LLMs.

Mixedbread introduced Wholembed v3 as a retrieval model for text, image, video, audio, and multilingual search. Benchmark it on fine-grained retrieval tasks if single-vector embeddings have been collapsing in your pipeline.