Lily Weng
8 papers · 2018–2023 · 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 ↓+3 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (20) 🐣 Hot Topic Early Bird
🧭
Keyword Pioneer
🧬
Topic Evolution
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(5)
Core AI
(5)
Deep Learning
(4)
Learning Types · Machine Learning
(4)
Optimization & Theory · Machine Learning
(4)
Architectures
(2)
Core Methods
(2)
Optimization & Theory · Deep Learning
(2)
Robotics
(1)
Application Areas
(1)
Learning Types · Deep Learning
(1)
Systems
(1)
Techniques
(1)
Keywords
adversarial robustness
(4)
neural network
(3)
neural network verification
(2)
adversarial attack
(2)
adversarial perturbation
(2)
formal verification
(1)
neural architecture search
(1)
robust optimization
(1)
neural network robustness
(1)
generalization bound
(1)
recurrent neural network
(1)
randomized smoothing
(1)
adversarial defense
(1)
neighborhood component analysis
(1)
decision boundary
(1)
gradient flow
(1)
linear programming
(1)
robust control
(1)
certified robustness
(1)
contrastive learning
(1)
Papers
Analyzing Generalization of Neural Networks through Loss Path Kernels
NeurIPS 2023
Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
ICML 2022
Fast Training of Provably Robust Neural Networks by SingleProp
AAAI 2021
Hidden Cost of Randomized Smoothing
AISTATS 2021
Neural Network Control Policy Verification With Persistent Adversarial Perturbation
ICML 2020
POPQORN: Quantifying Robustness of Recurrent Neural Networks
ICML 2019
PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach
ICML 2019
Towards Fast Computation of Certified Robustness for ReLU Networks
ICML 2018