Xun Zhou
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
arXiv 2025
HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
arXiv 2025
Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models
arXiv 2025
UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning
arXiv 2025
WebLLM: A High-Performance In-Browser LLM Inference Engine
arXiv 2024
MARS: Unleashing the Power of Variance Reduction for Training Large Models
arXiv 2024
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
arXiv 2024
Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
arXiv 2024
World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering
arXiv 2024
GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond
arXiv 2023
Affiliations
Frequent co-authors
10from 10 papers