Xianfeng Wu
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
54DLangVGGT: 4D Language-Visual Geometry Grounded Transformer
arXiv 2025
Go with Your Gut: Scaling Confidence for Autoregressive Image Generation
arXiv 2025
Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models
ICCV 2025
LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization
arXiv 2025
Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly
CVPR 2025 1
Affiliations
No known affiliations.
Frequent co-authors
10from 5 papers