Seulki Lee
8 papers · 2023–2026 · 7 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird 🏆 Grand Slam
⚡
Prolific Year · Productive
Top co-authors
Research topics
Machine Learning
(6)
Application Areas
(5)
Artificial Intelligence
(3)
Optimization & Theory
(3)
Core AI
(2)
Data Science & Analytics
(1)
Deep Learning
(1)
Core Methods
(1)
Learning Paradigms · Artificial Intelligence
(1)
Learning Paradigms · Machine Learning
(1)
Learning Types
(1)
Methods
(1)
Models
(1)
Techniques
(1)
Keywords
memory efficiency
(2)
diffusion model
(2)
matrix factorization
(1)
self-supervised learning
(1)
attention mechanism
(1)
time series classification
(1)
vector quantization
(1)
classification accuracy
(1)
adaptive learning rate
(1)
regret bound
(1)
data heterogeneity
(1)
gradient approximation
(1)
activation memory
(1)
text-to-video generation
(1)
client selection
(1)
non-iid data
(1)
transformer training
(1)
model efficiency
(1)
on-device inference
(1)
pretext task
(1)
Papers
Mobile-Oriented Video Diffusion: Enabling Text-to-Video Generation on Mobile Devices Without Retraining, Compression, or Pruning
WACV 2026
Bayesian Code Diffusion for Efficient Automatic Deep Learning Program Optimization
OSDI 2025
Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards
ICML 2025
PPT: Patch Order Do Matters In Time Series Pretext Task
ICLR 2025
SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization
AAAI 2025
TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation
ICML 2025
On-Demand Federated Learning for Arbitrary Target Class Distributions
AISTATS 2024
Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks
NeurIPS 2023