DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
Paper • 2608.13517 • Published • 33
Papers
Papers related to Danish Foundation Models
-
-
Dynaword: From One-shot to Continuously Developed Datasets
Paper • 2508.02271 • Published • 15 -
Last Translation Benchmark
Paper • 2609.04173 • Published • 44 -
MVEB: Massive Video Embedding Benchmark
Paper • 2606.14958 • Published • 16 -
MAEB: Massive Audio Embedding Benchmark
Paper • 2602.16008 • Published • 25 -
MMTEB: Massive Multilingual Text Embedding Benchmark
Paper • 2502.13595 • Published • 50 -
Improving reasoning at inference time via uncertainty minimisation
Paper • 2603.07159 • Published • 1 -
The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding
Paper • 2406.02396 • Published • 1 -
One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
Paper • 2605.22544 • Published • 2 -
HUME: Measuring the Human-Model Performance Gap in Text Embedding Task
Paper • 2510.10062 • Published • 10 -
Maintaining MTEB: Towards Long Term Usability and Reproducibility of Embedding Benchmarks
Paper • 2506.21182 • Published • 3 -
Naturalistic measure of social norms alignment
Paper • 2605.23420 • Published • 1