Zhaoyu Chen

18

Papers

140

Total Citations

Papers (18)

OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning

De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts

dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis

Boosting Adversarial Transferability with Spatial Adversarial Alignment

Debiased Multimodal Understanding for Human Language Sequences

Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators

Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation

General Compression Framework for Efficient Transformer Object Tracking

Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection

Towards Practical Certifiable Patch Defense With Vision Transformer

Context De-Confounded Emotion Recognition

AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception

LVOS: A Benchmark for Long-term Video Object Segmentation

Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation

Efficient Decision-based Black-box Patch Attacks on Video Recognition

Shape Matters: Deformable Patch Attack

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking

NeurIPS 2025arXiv

Content-based Unrestricted Adversarial Attack