Keyu Tian
5 papers · 2020–2024 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Deep Learning
(4)
Learning Types · Deep Learning
(4)
Machine Learning
(2)
Application Areas
(2)
Architectures
(2)
Artificial Intelligence
(1)
Computer Vision
(1)
Mathematics & Optimization
(1)
Core AI
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Optimization
(1)
Optimization & Theory
(1)
Techniques
(1)
Keywords
data augmentation
(2)
image generation
(1)
self-supervised learning
(1)
image reconstruction
(1)
neural architecture search
(1)
continuous optimization
(1)
weight sharing
(1)
diffusion model
(1)
autoregressive model
(1)
convolutional neural network
(1)
scaling law
(1)
stochastic gradient langevin dynamics
(1)
zero-shot generalization
(1)
image transformation
(1)
diffusion transformer
(1)
visual autoregressive
(1)
next-scale prediction
(1)
hierarchical decoder
(1)
masked image modeling
(1)
sparse convolution
(1)
Papers
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
NeurIPS 2024
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
ICLR 2023
A Continuous Mapping For Augmentation Design
NeurIPS 2021
Improving Auto-Augment via Augmentation-Wise Weight Sharing
NeurIPS 2020
Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
ECCV 2020