Brian Cheung
9 papers · 2018–2024 · 4 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 ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze π Academic Marathon Β· Sprint πΊοΈ Taxonomy Completionist (32) π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze
β
The Questioner
ποΈ
Keyword Collector
(50)
Venues
Top co-authors
Research topics
Machine Learning
(9)
Deep Learning
(6)
Learning Types Β· Machine Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Application Areas
(3)
Architectures
(3)
Core Methods
(3)
Optimization & Theory
(3)
Computer Vision
(2)
Analysis
(2)
Learning Types Β· Deep Learning
(2)
Interdisciplinary
(1)
Reinforcement Learning
(1)
Applications
(1)
Keywords
model compression
(2)
image classification
(2)
representation learning
(1)
network pruning
(1)
feature learning
(1)
adversarial robustness
(1)
computer vision
(1)
convergence
(1)
human visual system
(1)
neural network optimization
(1)
vector quantization
(1)
system identification
(1)
parameter sharing
(1)
model-based reinforcement learning
(1)
alternating optimization
(1)
neural network training
(1)
neural network model
(1)
semi-supervised classification
(1)
contrastive learning
(1)
generative modeling
(1)
Papers
Position: The Platonic Representation Hypothesis
ICML 2024
Compact and Optimal Deep Learning With Recurrent Parameter Generators
WACV 2023
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
ICML 2023
System Identification of Neural Systems: If We Got It Right, Would We Know?
ICML 2023
Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations
ICLR 2022
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
ICML 2020
Meta-Learning Update Rules for Unsupervised Representation Learning
ICLR 2019
Superposition of many models into one
NeurIPS 2019
Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
NeurIPS 2018