Jonathan Uesato
10 papers · 2017–2022 · 6 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (20) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§
Keyword Pioneer
π
Keyword Trendsetter Combo
(3)
π§¬
Topic Evolution
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
β
The Questioner
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(5)
Core AI
(5)
Learning Types Β· Machine Learning
(5)
Optimization & Theory Β· Machine Learning
(5)
Deep Learning
(3)
Application Areas
(2)
Learning Types Β· Deep Learning
(2)
Natural Language Processing
(1)
Applications
(1)
Core Methods
(1)
Optimization & Theory Β· Deep Learning
(1)
Techniques
(1)
Keywords
adversarial robustness
(6)
neural network verification
(4)
toxicity detection
(2)
convex relaxation
(2)
large language model
(2)
adversarial training
(2)
language model evaluation
(1)
robust classification
(1)
semidefinite programming
(1)
loss landscape
(1)
harmful content
(1)
first-order method
(1)
interval bound propagation
(1)
adversarial perturbation
(1)
responsible ai
(1)
out-of-distribution detection
(1)
decision boundary
(1)
language model
(1)
bias mitigation
(1)
model safety
(1)
Papers
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models
NeurIPS 2022
Challenges in Detoxifying Language Models
EMNLP 2021
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications
NeurIPS 2021
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
NeurIPS 2020
Are Labels Required for Improving Adversarial Robustness?
NeurIPS 2019
Robustness via Curvature Regularization, and Vice Versa
CVPR 2019
Scalable Verified Training for Provably Robust Image Classification
ICCV 2019
Verification of Non-Linear Specifications for Neural Networks
ICLR 2019
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
ICML 2018
RobustFill: Neural Program Learning under Noisy I/O
ICML 2017