6 papers · 1 filter
Token-Level Inference-Time Alignment for Vision-Language Models
Kejia Chen, Jiawen Zhang, Jiacong Hu +4
Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visu…
SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner
Kejia Chen, Jiawen Zhang, Jiacong Hu +4
Large Visual Language Models (LVLMs) increasingly rely on preference alignment to ensure reliability, which steers the model behavior via preference fine-tuning on preference data…
Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Pathology Analysis
Shengxuming Zhang, Weihan Li, Tianhong Gao +6
Pathological diagnosis is vital for determining disease characteristics, guiding treatment, and assessing prognosis, relying heavily on detailed, multi-scale analysis of high-resol…
Improving Adversarial Robustness via Feature Pattern Consistency Constraint
Jiacong Hu, Jingwen Ye, Zunlei Feng +5
Convolutional Neural Networks (CNNs) are well-known for their vulnerability to adversarial attacks, posing significant security concerns. In response to these threats, various defe…
Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
Jiacong Hu, Jing Gao, Jingwen Ye +4
With the rapid development of deep learning, the increasing complexity and scale of parameters make training a new model increasingly resource-intensive. In this paper, we start fr…
Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers
Zunlei Feng, Jiacong Hu, Sai Wu +3
Recently, Convolutional Neural Network (CNN) has achieved excellent performance in the classification task. It is widely known that CNN is deemed as a 'black-box', which is hard fo…