PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States Paper • 2610.29545 • Published 8 days ago • 24
FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition Paper • 2512.13884 • Published Dec 15, 2025 • 15
PISA-Bench: The PISA Index as a Multilingual and Multimodal Metric for the Evaluation of Vision-Language Models Paper • 2510.24792 • Published Oct 27, 2025
PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States Paper • 2610.29545 • Published 8 days ago • 24
Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling Paper • 2604.28075 • Published Apr 30 • 18
Pre-Training Curriculum for Multi-Token Prediction in Language Models Paper • 2505.22757 • Published May 28, 2025
Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling Paper • 2604.28075 • Published Apr 30 • 18
MastermindEval: A Simple But Scalable Reasoning Benchmark Paper • 2503.05891 • Published Mar 7, 2025 • 1
Empirical Evaluation of Knowledge Distillation from Transformers to Subquadratic Language Models Paper • 2504.14366 • Published Apr 19, 2025 • 1
Sample-Efficient Language Modeling with Linear Attention and Lightweight Enhancements Paper • 2511.05560 • Published Nov 4, 2025 • 1