Kunat Pipatanakul

benchmark evaluation (3) text recognition (2) zero-shot learning (2) large audio model (2) document understanding (2) vision-language model (2) prompt engineering (2) in-context learning (2) user preference (1) spoken question answering (1) optical character recognition (1) context extension (1) speech evaluation (1) audio-language model (1) handwritten content (1) large language model (1) reinforcement fine-tuning (1) interactive evaluation (1) positional augmentation (1) reinforcement learning (1)