7 papers
When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression
Tien-Phat Nguyen, Ngai-Man Cheung
Vision Transformers (ViTs) are strong backbones for semantic segmentation, but their computational cost limits deployment. Recent token compression methods for efficient transforme…
CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning
Jingze Ge, Xue Geng, Yun Liu +6
To mitigate the memory constraints associated with fine-tuning large pre-trained models, existing parameter-efficient fine-tuning (PEFT) methods, such as LoRA, rely on low-rank upd…
Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging
Phat Nguyen, Xue Geng, Kaixin Xu +3
Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main c…
How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
Guimeng Liu, Tianze Yu, Somayeh Ebrahimkhani +3
Generalist multimodal large language models (MLLMs) have achieved impressive performance across a wide range of vision-language tasks. However, their performance on medical tasks,…
On the Adversarial Robustness of 3D Large Vision-Language Models
Chao Liu, Ngai-Man Cheung
3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks. However, their adversarial rob…
Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI
Phat Nguyen, Ngai-Man Cheung
Token compression techniques have recently emerged as powerful tools for accelerating Vision Transformer (ViT) inference in computer vision. Due to the quadratic computational comp…