Haocheng Xi
9 papers · 2023–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
👥
Mega-Team · Squad
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Machine Learning
(8)
Application Areas
(8)
Deep Learning
(7)
Architectures
(5)
Artificial Intelligence
(4)
Core AI
(4)
Computer Vision
(3)
Generation · Computer Vision
(3)
Models
(2)
Optimization & Theory · Deep Learning
(2)
Optimization & Theory · Machine Learning
(2)
Natural Language Processing
(1)
Generation · Natural Language Processing
(1)
Techniques
(1)
Keywords
activation quantization
(2)
efficient computing
(2)
model quantization
(2)
video generation
(1)
edge device
(1)
weight quantization
(1)
neural network training
(1)
sparsity
(1)
diffusion model
(1)
memory efficiency
(1)
low-precision training
(1)
attention head
(1)
low-rank decomposition
(1)
sparse attention
(1)
vision transformer
(1)
transformer block
(1)
video diffusion model
(1)
matrix multiplication
(1)
gradient quantization
(1)
quantization
(1)
Papers
DeltaQuant: 4-bit Video Diffusion Models with Spatiotemporal Delta Smoothing
CVPR 2026
COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training
ICLR 2025
NVILA: Efficient Frontier Visual Language Models
CVPR 2025
Oscillation-Reduced MXFP4 Training for Vision Transformers
ICML 2025
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
ICML 2025
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
ICML 2025
Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
ICML 2025
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
ICML 2024
Training Transformers with 4-bit Integers
NeurIPS 2023