Scholar
Xinle Cheng
Google Scholar ID: 9RJdEXMAAAAJ
Princeton University
Citations & Impact
Citations
112
H-index
3
i10-index
3
Publications
5
Co-authors
4
list available
Publications
Resume (English only)
Academic Achievements
- Playing with Transformer at 30+ FPS via Next-Frame Diffusion
- VidTok: A Family of Versatile and State-Of-The-Art Video Tokenizers
- CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models (NeurIPS'24 Workshop AFM)
- Zero-Shot Image Feature Consensus with Deep Functional Maps (ECCV 2024)
- DPO Meets PPO: Reinforced Token Optimization for RLHF (ICML'25 Spotlight)
- Reviewer for ACL 2025, ICLR 2025, CVPR 2024–2025
Background
- First-year Ph.D. student in Computer Science at Princeton University
- Research interests lie at the intersection of machine learning and systems
- In machine learning, focuses on Generative AI, including Large Language Models and Diffusion Models
- In systems, interested in building efficient and scalable systems for machine learning applications
- Enthusiastic about fostering synergy between machine learning and systems
