Haocheng Xi
- Papers
- 12
Cite
Notes
Only stored in your browser.
Authored papers
12Flash-KMeans: Fast and Memory-Efficient Exact K-Means
arXiv 2026
Residual Context Diffusion Language Models
arXiv 2026
Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
arXiv 2025
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
arXiv 2025
Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
arXiv 2025
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
arXiv 2025
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
arXiv 2025
T-Rex: Text-assisted Retrosynthesis Prediction
arXiv 2024
NVILA: Efficient Frontier Visual Language Models
CVPR 2025 1
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
arXiv 2024
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
arXiv 2024
Training Transformers with 4-bit Integers
training-transformers-with-4-bit-integers
Affiliations
Frequent co-authors
10from 12 papers