Xingcheng Zhou
Scholar

Xingcheng Zhou

Google Scholar ID: FPYXLpQAAAAJ
Technical University of Munich
Autonomous DrivingVision Language ModelLarge Language ModelComputer Vision
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
522
 
H-index
9
 
i10-index
9
 
Publications
18
 
Co-authors
0
 
Contact
Emailxingcheng.zhou@tum.de
Publications
13 items
EchoRL: Reinforcement Learning via Rollout Echoing
2026
Cited
0
ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes
2026
Cited
0
CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs
2026
Cited
0
SGTA: Scene-Graph Based Multi-Modal Traffic Agent for Video Understanding
2026
Cited
0
SegRGB-X: General RGB-X Semantic Segmentation Model
2026
Cited
0
TUMTraf EMOT: Event-Based Multi-Object Tracking Dataset and Baseline for Traffic Scenarios
2025
Cited
0
Safety-Critical Learning for Long-Tail Events: The TUM Traffic Accident Dataset
2025
Cited
0
Generative AI for Autonomous Driving: Frontiers and Opportunities
2025
Cited
0
Resume
Academic Achievements
  • Supervised numerous Master’s theses and guided research projects, including:
  • - 3D Object Detection Generalization in Static LiDAR Applications
  • - Real-time Multi-view Road-side 3D Object Detection
  • - Domain Adaptation for Road-Side Vision-Based 3D Object Detection
  • - Supervised 3D Perception on Roadside LiDARs Under Different Weather Situations
  • - CLIP-Enhanced 3D Object Detection
  • - Knowledge Distilled Traffic Environment Understanding
  • - A Multi-Modal Benchmark for Visual Question Answering in Transportation Scenes
  • - LiDAR-guided Monocular 3D Object Detection for Railway Monitoring
  • - Exploring Large Vision-Language Models in Intelligent Traffic Surveillance