Yujun Lin
12 papers · 2018–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (5) π Conference Polyglot (5) π Academic Marathon (7) πΊοΈ Taxonomy Completionist (16)
π
Conference Polyglot
(5)
π
Academic Marathon
(7)
π
Renaissance Researcher
(5)
π€
Dynamic Duo
(12)
π
Conference Pioneer
π
Century Club
(12)
π
Trend Setter
Conferences
ICLR (4)
NIPS (3)
CVPR (2)
ICML (2)
ECCV (1)
Top co-authors
Keywords
neural architecture search
(2)
model quantization
(2)
reinforcement learning
(1)
semantic segmentation
(1)
object detection
(1)
point cloud
(1)
network pruning
(1)
efficient inference
(1)
efficient computing
(1)
model pruning
(1)
memory optimization
(1)
evolutionary search
(1)
mixed precision
(1)
automated machine learning
(1)
local computation
(1)
part segmentation
(1)
iot device
(1)
hardware-aware quantization
(1)
neural network
(1)
3d deep learning
(1)
Papers
SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
ICLR 2025
Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
ICML 2025
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
ICML 2025
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers
ICLR 2025
Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning
NIPS 2021
APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
CVPR 2020
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
ECCV 2020
Lite Transformer with Long-Short Range Attention
ICLR 2020
MCUNet: Tiny Deep Learning on IoT Devices
NIPS 2020
Point-Voxel CNN for Efficient 3D Deep Learning
NIPS 2019
HAQ: Hardware-Aware Automated Quantization With Mixed Precision
CVPR 2019
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
ICLR 2018