Similar Items: Cubit: Token Mixer with Kernel Ridge Regression
- PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
- Efficient Pre-Training with Token Superposition
- The First Token Knows: Single-Decode Confidence for Hallucination Detection
- A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language
- Patch-Effect Graph Kernels for LLM Interpretability
- Litespark Inference on Consumer CPUs: Custom SIMD Kernels for Ternary Neural Networks