Minyoung Huh
8 papers · 2018–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (4) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (12) π Academic Marathon (6)
π
Cross-Pollinator
(8)
π
Conference Pioneer
Conferences
ECCV (4)
ICML (2)
CVPR (1)
NIPS (1)
Top co-authors
Keywords
neural network optimization
(2)
adversarial learning
(1)
image generation
(1)
image-to-image translation
(1)
vector quantization
(1)
alternating optimization
(1)
generative model
(1)
generative adversarial network
(1)
straight-through estimator
(1)
codebook learning
(1)
feedback learning
(1)
modular norm
(1)
weight normalization
(1)
gradient lipshitz continuity
(1)
gradient lipschitz continuity
(1)
learning rate transfer
(1)
deep learning scaling
(1)
commitment loss
(1)
discriminator feedback
(1)
spatial transform
(1)
Papers
Scalable Optimization in the Modular Norm
NIPS 2024
Position: The Platonic Representation Hypothesis
ICML 2024
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
ICML 2023
Totems: Physical Objects for Verifying Visual Integrity
ECCV 2022
Aligning and Projecting Images to Class-conditional Generative Networks
ECCV 2020
Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks
CVPR 2019
Fighting Fake News: Image Splice Detection via Learned Self-Consistency
ECCV 2018
Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence
ECCV 2018