Major sentence-transformers release adds ColBERT-style late interaction
antoine_chaffin · x · 2026-08-19
A major release of sentence-transformers by Tomaarsen, LightOn, and Hugging Face introduces MultiVectorEncoder support, significantly boosting search and RAG performance. It adopts ColBERT-style late interaction, using 128-dim vectors per token instead of lossy single-vector compression. Key features include a unified API for PyLate/ColBERT/ColPali, Zero-OCR visual document search, and token-level interpretability.
More from Models
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16