Jae W. Lee
8 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(5)
🌉
Interdisciplinary Bridge
🐝
Cross-Pollinator
(15)
Conferences
ICML (3)
ECCV (2)
AAAI (1)
ICCV (1)
OSDI (1)
Top co-authors
Keywords
model quantization
(1)
neural network pruning
(1)
point cloud
(1)
neural network optimization
(1)
efficient computing
(1)
model pruning
(1)
model inference
(1)
inference efficiency
(1)
gpu acceleration
(1)
point cloud processing
(1)
error correction
(1)
farthest point sampling
(1)
activation outlier
(1)
sparse convolution
(1)
large language model
(1)
computation reduction
(1)
low-bit precision
(1)
residual matrix
(1)
Papers
FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials
ICML 2025
GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
ICML 2025
DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization
OSDI 2025
FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction
ICCV 2025
Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
ICML 2024
Frugal 3D Point Cloud Model Training via Progressive Near Point Filtering and Fused Aggregation
ECCV 2024
Not All Neighbors Matter: Point Distribution-Aware Pruning for 3D Point Cloud
AAAI 2023
"L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training"
ECCV 2022