Warit Sirichotedumrong

document understanding (2) text recognition (2) benchmark evaluation (2) vision-language model (2) zero-shot learning (2) human preference (1) rotary position embedding (1) large audio model (1) optical character recognition (1) context extension (1) speech evaluation (1) audio-language model (1) handwritten content (1) positional augmentation (1) handwritten content extraction (1) in-context learning (1) prompt engineering (1) multimodal learning (1) thai language (1)