Xiuhong Li
5 papers · 2024–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (3) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
CVPR (2)
ICML (2)
NIPS (1)
Top co-authors
Keywords
efficient computing
(2)
post-training quantization
(1)
computer graphics
(1)
3d gaussian splatting
(1)
vision-language model
(1)
real-time rendering
(1)
key-value cache
(1)
latency optimization
(1)
memory management
(1)
adaptive scheduling
(1)
gpu kernel
(1)
llm inference
(1)
modality-balanced quantization
(1)
quantization sensitivity
(1)
high-resolution rendering
(1)
cuda optimization
(1)
batching throughput
(1)
model compression
(1)
page-based cache
(1)
Papers
FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering
CVPR 2025
MBQ: Modality-Balanced Quantization for Large Vision-Language Models
CVPR 2025
MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
ICML 2025
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
NIPS 2024
MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving
ICML 2024