Mark Collier
8 papers · 2021–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🐝 Cross-Pollinator (10) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (4) 🧭 Keyword Pioneer 🏃 Academic Marathon (5)
🌍
Conference Polyglot
(4)
🐣
Hot Topic Early Bird
👥
Mega-Team
(42)
👑
Triple Crown
🏆
Keyword Champion
(2)
🏆
Grand Slam
❓
The Questioner
Conferences
ICML (4)
AAAI (1)
CVPR (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
label noise
(3)
image classification
(3)
privileged information
(2)
vision transformer
(1)
image retrieval
(1)
covariance matrix
(1)
weight sharing
(1)
latent variable
(1)
vision language model
(1)
vision-language model
(1)
model scaling
(1)
parameter efficiency
(1)
clean sample selection
(1)
pretrained model
(1)
training datum
(1)
aleatoric uncertainty
(1)
heteroscedastic noise
(1)
noisy datum
(1)
neural network
(1)
shape texture bia
(1)
Papers
Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling
AAAI 2026
Pi-DUAL: Using privileged information to distinguish clean from noisy labels
ICML 2024
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
NIPS 2023
When does Privileged information Explain Away Label Noise?
ICML 2023
Scaling Vision Transformers to 22 Billion Parameters
ICML 2023
Massively Scaling Heteroscedastic Classifiers
ICLR 2023
Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
ICML 2022
Correlated Input-Dependent Label Noise in Large-Scale Image Classification
CVPR 2021