Zuxuan Wu
Scholar

Zuxuan Wu

Google Scholar ID: 7t12hVkAAAAJ
Fudan University
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
11,898
 
H-index
54
 
i10-index
117
 
Publications
20
 
Co-authors
0
 
Contact
Emailzxwu@fudan.edu.cnGitHubOpen ↗
Publications
85 items
VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
2026
Cited
0
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
2026
Cited
0
Channel-wise Vector Quantization
2026
Cited
0
Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
2026
Cited
0
DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders
2026
Cited
0
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
2026
Cited
0
Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations
2026
Cited
0
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
2026
Cited
0
Resume (English only)
Background
  • Associate Professor at Fudan University
  • Member of the Institute of Trustworthy Embodied Artificial Intelligence, Fudan University
  • Member of the Fudan Vision and Learning Laboratory
  • Research interests include computer vision and deep learning
  • Current research focuses on large-scale video understanding, video generation, and efficient architectures
Co-authors
0 total
Co-authors: 0 (list not available)