3 papers
cs.CL2025
TensorBLEU: Vectorized GPU-based BLEU Score Implementation for Per-Sentence In-Training Evaluation
Adam Filipek
Modern natural language processing models have achieved unprecedented scale, yet the tools for their evaluation often remain a computational bottleneck, limiting the pace of resear…
cs.CL2025
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Adam Filipek
The Transformer architecture has become the de facto standard for Large Language Models (LLMs), demonstrating remarkable capabilities in language understanding and generation. Howe…
cs.LG2025
Sparse Query Attention (SQA): A Computationally Efficient Attention Mechanism with Query Heads Reduction
Adam Filipek
The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. Howe…