Xianlong Wang
Scholar

Xianlong Wang

Google Scholar ID: EgsgIq0AAAAJ
Ph.D. student, City University of Hong Kong
Trustworthy LLM/VLMEmbodied AIUnlearnable Example3D Point CloudPoisoning/Adversarial Attack
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
172
 
H-index
7
 
i10-index
7
 
Publications
11
 
Co-authors
0
 
Contact
No contact links provided.
Publications
5 items
Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs
2026
Cited
0
ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
2025
Cited
0
PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
2024
Cited
2
TrojanRobot: Physical-World Backdoor Attacks Against VLM-based Robotic Manipulation
2024
Cited
0
BadRobot: Jailbreaking Embodied LLMs in the Physical World
2024
Cited
3
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)