2 papers
cs.AI2026
Bridging the Training-Deployment Gap: Gated Encoding and Multi-Scale Refinement for Efficient Quantization-Aware Image Enhancement
Dat To-Thanh, Nghia Nguyen-Trong, Hoang Vo +2
Image enhancement models for mobile devices often struggle to balance high output quality with the fast processing speeds required by mobile hardware. While recent deep learning mo…
cs.CV2025
STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models
Tinh-Anh Nguyen-Nhu, Triet Dao Hoang Minh, Dat To-Thanh +3
Vision-language models (VLMs) have emerged as powerful tools for enabling automated traffic analysis; however, current approaches often demand substantial computational resources a…