4 papers
ExpertHTR: Unified Handwritten Text Recognition with Multi-Task Learning and Sparse Mixture-of-Experts
Dang Hoai Nam, Nguyen Duy Hieu, Quang Huu Hieu +1
Handwritten text recognition resources are often small and distributed across collections that differ in language, script, document structure, and annotation format, making joint p…
ALRA: Adaptive Local Relational Alignment for Logit-Based Pre-training Distillation of Autoregressive Language Models
Quang Hoang Trung, Quang Huu Hieu, Nguyen Van Hoang Phuc +1
Logit-based knowledge distillation for autoregressive language models usually aligns teacher and student next-token distributions over the entire vocabulary. However, this global o…
SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation
Nguyen Duy Hieu, Dang Hoai Nam, Pham Hoang Giap +2
Training robust handwriting recognition (HTR) systems requires massive amounts of annotated data, which is often difficult to acquire. While synthetic handwriting generation offers…
Adaptive Two-Phase Finetuning LLMs for Japanese Legal Text Retrieval
Quang Hoang Trung, Nguyen Van Hoang Phuc, Le Trung Hoang +2
Text Retrieval (TR) involves finding and retrieving text-based content relevant to a user's query from a large repository, with applications in real-world scenarios such as legal d…