KejiaZhang

VAP. [NeurIPS 2025] Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs

Academic-paper-writing. From Scratch to Submission: A Complete Guide to Academic Conference Paper Writing

TARS. TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

AI-Agent-papers. Collection of recent works on AI Agents.

DHAT. [ICCV 2025] Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment

AdverRobust. An Adversarial Training Framework for Adversarial Robustness in Deep Learning Models

HFDR. [Neural Networks 2025] Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness

Adversarial-Robustness-Papers. Recent works regarding adversarial robustness

Motif-based-GNN. [IEEE TCSS] Extracting Higher Order Topological Semantic via Motif-Based Deep Graph Neural Networks

KejiaZhang-Robust.

Awesome-Multimodal-Token-Compression. Survey: https://arxiv.org/pdf/2507.20198