[Paper] F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

Summary

F2LLM-v2 introduces a new family of general-purpose multilingual embedding models, ranging from 80M to 14B parameters. These models support over 200 languages, with a significant emphasis on improving performance for previously underserved mid- and low-resource languages. Utilizing a two-stage LLM-based training pipeline with techniques like matryoshka learning and knowledge distillation, F2LLM-v2 aims for inclusive, performant, and efficient language understanding globally.

Continue Reading

Explore related coverage about research paper and adjacent AI developments: [Paper] Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning, [Paper] MedObvious: Exposing the Medical Moravec's Paradox in VLMs via Clinical Triage, [Paper] In-Place Test-Time Training, [Paper] HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models.

Related Articles

• [Paper] Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning

  March 30, 2026

• [Paper] MedObvious: Exposing the Medical Moravec's Paradox in VLMs via Clinical Triage

  March 25, 2026

• [Paper] In-Place Test-Time Training

  April 8, 2026

• [Paper] HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models

  April 8, 2026