Xuanlei Zhao
4
Papers
23
Total Citations
Papers (4)
DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers
ICML 2025
10
citations
REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
NeurIPS 2025
8
citations
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
NeurIPS 2025
3
citations
StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training
NeurIPS 2025
2
citations