3 papers
cs.CV2026
SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs
Zi-Hao Bo, Yaqian Li, Anzhou Hou +6
Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert routing remains under-explor…
cs.CV2025
ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection
Haowei Zhu, Tianxiang Pan, Rui Qin +2
The scale and quality of datasets are crucial for training robust perception models. However, obtaining large-scale annotated data is both costly and time-consuming. Generative mod…
cs.CV2024
Semantic Hierarchical Prompt Tuning for Parameter-Efficient Fine-Tuning
Haowei Zhu, Fangyuan Zhang, Rui Qin +3
As the scale of vision models continues to grow, Visual Prompt Tuning (VPT) has emerged as a parameter-efficient transfer learning technique, noted for its superior performance com…