Binghui Li
6 papers · 2022–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(18)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(6)
Deep Learning
(4)
Learning Types · Machine Learning
(4)
Optimization & Theory · Machine Learning
(4)
Artificial Intelligence
(3)
Architectures
(3)
Core AI
(2)
Optimization & Theory · Deep Learning
(2)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Applications
(1)
Core Methods
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Methods
(1)
Keywords
neural network
(3)
adversarial example
(2)
adversarial robustness
(2)
gradient descent
(2)
feature learning
(2)
adversarial training
(2)
chain-of-thought reasoning
(1)
vc dimension
(1)
kernel regression
(1)
expressive power
(1)
convergence rate
(1)
convolutional network
(1)
generalization capability
(1)
robust overfitting
(1)
learning rate schedule
(1)
robust generalization
(1)
relu network
(1)
cross-lingual stance detection
(1)
chain-of-thought alignment
(1)
representation complexity
(1)
Papers
Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup–Stable–Decay (Extended Abstract)
COLT 2026
Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
ICLR 2025
A Reinforcement Learning Framework for Cross-Lingual Stance Detection Using Chain-of-Thought Alignment
ACL 2025
Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
ICLR 2025
On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
ICML 2025
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
NeurIPS 2022