TensorBLEU: Vectorized GPU-based BLEU Score Implementation for Per-Sentence In-Training Evaluation Paper β’ 2510.05485 β’ Published Oct 7, 2025 β’ 8
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models Paper β’ 2510.03561 β’ Published Oct 3, 2025 β’ 25
Sparse Query Attention (SQA): A Computationally Efficient Attention Mechanism with Query Heads Reduction Paper β’ 2510.01817 β’ Published Oct 2, 2025 β’ 16