← Search

Qingcheng Zhu

2 accepted papers

2026

Efficiently Seeking Flat Minima for Better Generalization in Fine-Tuning Large Language Models and Beyond

AAAI 2026technical

Little research explores the correlation between the expressive ability and generalization ability of the low-rank adaptation (LoRA). Sharpness-Aware Minimization (SAM) improves model generalization for both Convolutional Neural Networks (CNNs) and Transformers by encouraging convergence to locally

Cited by 0SourcePDFScholar
2025

WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection

ICCV 2025poster

Leveraging the complementary characteristics of visible (RGB) and infrared (IR) imagery offers significant potential for improving object detection. In this paper, we propose WaveMamba, a cross-modality fusion method that efficiently integrates the unique and complementary frequency features of RGB…

Cited by 0SourcePDFScholar