activity
20232026
most citedMaintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning

1 citations · 1 across the 10 of their papers we have counts for

collaborators

11 papers

cs.CV2026

HyperCLIP++: Fine-tuning CLIP forOpen-vocabulary Semantic Segmentation in Hyperbolic Space

Zelin Peng, Zhengqin Xu, Changsong Wen +4

CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing CLIP's text encoder is known to preserve its ge…

cs.CV2025

Patch-Discontinuity Mining for Generalized Deepfake Detection

Huanhuan Yuan, Yang Ping, Zhengqin Xu +3

The rapid advancement of generative artificial intelligence has enabled the creation of highly realistic fake facial images, posing serious threats to personal privacy and the inte…

cs.CV2025

HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models

Zelin Peng, Zhengqin Xu, Qingyang Liu +2

Multi-modal large language models (MLLMs) have emerged as a transformative approach for aligning visual and textual understanding. They typically require extremely high computation…

cs.CV2025

NEARL: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding

Zelin Peng, Yichen Zhao, Yu Huang +5

Computer-aided medical image analysis is crucial for disease diagnosis and treatment planning. While vision-language models (VLMs) such as CLIP exhibit strong generalization abilit…

cs.CV2025

Robust SAM: On the Adversarial Robustness of Vision Foundation Models

Jiahuan Long, Zhengqin Xu, Tingsong Jiang +4

The Segment Anything Model (SAM) is a widely used vision foundation model with diverse applications, including image segmentation, detection, and tracking. Given SAM's wide applica…

cs.CV2025

Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models

Jiahuan Long, Tingsong Jiang, Wen Yao +5

Vision foundation models (VFMs) have demonstrated remarkable capabilities in learning universal visual representations. However, adapting these models to downstream tasks conventio…