Scholar
Xiangyuan Lan
Google Scholar ID: c3iwWRcAAAAJ
Pengcheng Laboratory
Multimodal LLM
Place Recognition
Visual Tracking
Person Re-identification
Object Detection
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
4,696
H-index
32
i10-index
55
Publications
20
Co-authors
20
list available
Publications
25 items
Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models
2026
Cited
0
OccAnyScene: Towards Unified Indoor-Outdoor 3D Occupancy Predictio
2026
Cited
0
UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
2026
Cited
0
Adaptive Coarse-to-Fine Subgoal Refinement for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
2026
Cited
0
X2SAM: Any Segmentation in Images and Videos
2026
Cited
0
Efficient Adversarial Training via Criticality-Aware Fine-Tuning
2026
Cited
0
Dynamic Dual-Granularity Skill Bank for Agentic RL
2026
Cited
0
AlignMamba-2: Enhancing Multimodal Fusion and Sentiment Analysis with Modality-Aware Mamba
2026
Cited
0
Load more
Co-authors
20 total
P C Yuen
Professor of Computer Science, Hong Kong Baptist University
Mang Ye
Professor, Wuhan University
Shengping Zhang
Professor, Harbin Institute of Technology, China
Rui Shao
Professor, Harbin Institute of Technology (Shenzhen)
Bineng Zhong 钟必能
Guangxi Normal University, Professor; NEU, HIT, Huaqiao University
yaowei wang
HITSZ & PCL
Rama Chellappa
Bloomberg Distinguished Professor, Johns Hopkins University
Zheng Wang
Wuhan University
