Kan Wu
11 papers · 2018–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (9) π§ Keyword Pioneer π Renaissance Researcher (7) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (19)
π
Conference Polyglot
(8)
π
Academic Marathon
(7)
π
Century Club
(11)
π
Trend Setter
β
The Questioner
Conferences
CVPR (2)
ICCV (2)
IJCAI (2)
ECCV (1)
ICML (1)
NIPS (1)
NSDI (1)
OSDI (1)
Top co-authors
Keywords
vision transformer
(3)
model compression
(2)
neural architecture search
(2)
parameter efficiency
(2)
knowledge distillation
(2)
network efficiency
(1)
clip model
(1)
zero-shot learning
(1)
social network
(1)
search space
(1)
weight sharing
(1)
remote memory
(1)
factor graph
(1)
memory disaggregation
(1)
graph pattern mining
(1)
memory management
(1)
object tracking
(1)
memory allocation
(1)
self-attention mechanism
(1)
one-shot learning
(1)
Papers
Scaling Laws for FloatingβPoint Quantization Training
ICML 2025
FineMem: Breaking the Allocation Overhead vs. Memory Waste Dilemma in Fine-Grained Disaggregated Memory Management
OSDI 2025
TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
ICCV 2023
Arya: Arbitrary Graph Pattern Mining with Decomposition-based Sampling
NSDI 2023
TinyViT: Fast Pretraining Distillation for Small Vision Transformers
ECCV 2022
MiniViT: Compressing Vision Transformers With Weight Multiplexing
CVPR 2022
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
CVPR 2021
Rethinking and Improving Relative Position Encoding for Vision Transformer
ICCV 2021
Searching the Search Space of Vision Transformer
NIPS 2021
Where Have You Been? Inferring Career Trajectory from Academic Social Network
IJCAI 2018
Weakly Learning to Match Experts in Online Community
IJCAI 2018