Shuchen Xue

1. Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
   2025/05/28 by Chengyue Wu, Wu, Chengyue, Hao Zhang +15 · 5 voices · 128 citations
   Computer Science · Social Sciences · #Topic Modeling #Generative Adversarial Networks and Image Synthesis #Computational and Text Analysis Methods
2. Accelerating Diffusion Sampling with Optimized Time Steps
   2024/02/27 by Shuchen Xue, Zhaoqiang Liu, Xue, Shuchen +11 · 15 citations
   Computer Science · #Speech and Audio Processing
3. SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models
   2023/09/10 by Shuchen Xue, Mingyang Yi, Xue, Shuchen +11 · 10 citations
   Computer Science · Engineering · Mathematics · #Bayesian Methods and Mixture Models #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistical Methods and Bayesian Inference #Traffic Prediction and Management Techniques
4. The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling
   2024/02/23 by Jiajun Ma, Shuchen Xue, Ma, Jiajun +13 · 2 citations
   Mathematics · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Survey Sampling and Estimation Techniques
5. Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
   2025/09/29 by Shuchen Xue, Xue, Shuchen, Chongjian Ge +7 · 4 citations
   Economics, Econometrics and Finance · Mathematics · #FOS: Computer and information sciences #Game Theory and Voting Systems #Machine Learning (cs.LG) #Statistical Methods and Inference
6. Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
   2025/12/19 by Shilong Zhang, Zhang, Shilong, He Zhang +25 · 1 citation
   Computer Science · Engineering · #Generative Adversarial Networks and Image Synthesis #Face recognition and analysis #3D Shape Modeling and Analysis
7. SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
   2026/07/23 by Junsong Chen, Jincheng Yu, Yitong Li +11
   #cs.CV