Similar Items: PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
- Efficient Pre-Training with Token Superposition
- Cubit: Token Mixer with Kernel Ridge Regression
- 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
- Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
- Why Expert Alignment Is Hard: Evidence from Subjective Evaluation