sentence-transformers maintainer releases new embedding pooling training method, code & checkpoints
tomaarsen · x · 2026-11-11
tomaarsen, maintainer of sentence-transformers, released a blog with the method, training code, checkpoints, and evaluation for a new embedding pooling training approach, building on Learn to Pool and LightOnIO's pooling regularization work, plus H Company's Late Interaction Kernels. More features are planned; he's soliciting feedback on ST bottlenecks.
More from coding & agent
- Databricks launches autonomous AI coworker Genie: 91% on enterprise tasks with half the tokens — Yuchenj_UW · 2026-11-12
- Loom founder launches Roma 2.0, a shared to-do list that orchestrates AI agents — thetripathi58 · 2026-11-12
- Developer proposes a 'blast radius' test for AI agents before building — Few-Garlic2725 · 2026-11-12
- Sosumi Eval: Apple Docs Access Lifts Coding Agent Pass Rates from ~33% to 94-98% — JordanMorgan10 · 2026-11-12
- CypherGuard fixes structurally wrong LLM Cypher queries, hitting 88.5% on CypherBench — JeremyCMorgan · 2026-11-12
- Building an End-to-End Hedge Fund in Python with Claude Code: A 5-Step Workflow — mdancho84 · 2026-11-12