Mark Collier
8 papers · 2021–2026 · 5 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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Academic Marathon Β· Sprint πΊοΈ Taxonomy Completionist (21) π Conference Polyglot Β· Silver π Grand Slam
π₯
Mega-Team Β· Squad
π
Triple Crown
β
The Questioner
Venues
Top co-authors
Research topics
Keywords
label noise
(4)
image classification
(4)
privileged information
(3)
vision-language model
(2)
image retrieval
(1)
multimodal learning
(1)
covariance matrix
(1)
weight sharing
(1)
latent variable
(1)
pre-trained model
(1)
model scaling
(1)
parameter efficiency
(1)
clean sample selection
(1)
zero-shot classification
(1)
training data
(1)
temperature scaling
(1)
aleatoric uncertainty
(1)
heteroscedastic noise
(1)
gating mechanism
(1)
noisy data
(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
Massively Scaling Heteroscedastic Classifiers
ICLR 2023
Scaling Vision Transformers to 22 Billion Parameters
ICML 2023
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
NeurIPS 2023
When does Privileged information Explain Away Label Noise?
ICML 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