2 papers
cs.CL2026
Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning
Hongyi Cai, Jie Li, Mohammad Mahdinur Rahman +1
The effectiveness of instruction fine-tuning for Large Language Models is fundamentally constrained by the quality and efficiency of training datasets. This work introduces Low-Con…
cs.CV2025
CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection
Hongyi Cai, Mohammad Mahdinur Rahman, Wenzhen Dong +1
Feature pyramids have been widely adopted in convolutional neural networks and transformers for tasks in medical image segmentation. However, existing models generally focus on the…