Kejia Zhang's Homepage

TARS: MinMax Token-Adaptive Preference Strategy for MLLM Hallucination Reduction

Wed, 30 Jul 2025 00:00:00 +0000

When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios

Tue, 29 Jul 2025 00:00:00 +0000

From Scratch to Submission: A Complete Guide to Academic Conference Paper Writing

Thu, 26 Jun 2025 00:00:00 +0000

Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment

Thu, 26 Jun 2025 00:00:00 +0000

Our paper has been accepted by ICCV-25

Wed, 25 Jun 2025 00:00:00 +0000

🎉 Exciting News! Our paper titled “Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment” has been accepted to ICCV 2025!

Special thanks to all co-authors for their hard work and dedication!

📌 Stay tuned for our camera-ready version.

Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness

Fri, 20 Jun 2025 00:00:00 +0000

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs

Sat, 01 Feb 2025 00:00:00 +0000

My Friends

Sun, 01 Sep 2024 00:00:00 +0000

AdverRobust: A Modular Framework for Adversarial Robustness

Thu, 27 Jun 2024 00:00:00 +0000

🛡️ Overview

AdverRobust is a PyTorch-based repository that provides a highly modular and extensible framework for adversarial training and robustness evaluation in computer vision. It integrates multiple state-of-the-art methods, offering researchers a flexible playground for robust deep learning.

✅ Built-in support for PGD-AT, TRADES, MART, AWP, FSR, and FPCM
🔁 Configurable via YAML, easy to adapt to different datasets and model architectures
📦 Preconfigured for CIFAR-10/100, TinyImageNet, and Imagenette

⚙️ Features

🎯 Adversarial Training Frameworks

Method	Description	Reference
PGD-AT	Iterative gradient-based training	Madry et al., ICLR 2018
TRADES	Minimizes KL divergence	Zhang et al., ICML 2019
MART	Targets misclassified samples	Wang et al., ICLR 2020
AWP	Adversarial weight perturbation	Wu et al., NeurIPS 2020
FSR	Feature recalibration defense	Kim et al., CVPR 2023
FPCM	Frequency-domain robustness	Bu et al., ICCV 2023

🚀 Getting Started

git clone https://github.com/KejiaZhang-Robust/AdverRobust
cd AdverRobust
conda env create -f environment.yaml
conda activate at_robust

Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness

Wed, 01 May 2024 00:00:00 +0000

Extracting Higher Order Topological Semantic via Motif-Based Deep Graph Neural Networks

Sun, 21 Apr 2024 00:00:00 +0000

This is the first paper in my research career. I dedicate it to commemorate and express my gratitude to Professor Haifeng Zhang for his invaluable support. I also extend my thanks to the Network Science Research Group at Anhui University for the enriching experiences during my time there.

Contact

Mon, 24 Oct 2022 00:00:00 +0000

Tour

Mon, 24 Oct 2022 00:00:00 +0000

Mon, 01 Jan 0001 00:00:00 +0000