Ching-Yun Ko
12 papers · 2019–2026 · 8 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 ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (22) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver 𧬠Topic Evolution
π
Grand Slam
ποΈ
Keyword Collector
(50)
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(8)
Core AI
(8)
Core Methods
(5)
Deep Learning
(4)
Learning Types Β· Machine Learning
(4)
Optimization & Theory Β· Machine Learning
(4)
Learning Types Β· Deep Learning
(2)
Natural Language Processing
(1)
Application Areas
(1)
Architectures
(1)
Optimization & Theory Β· Deep Learning
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
large language model
(3)
adversarial robustness
(3)
representation learning
(2)
adversarial attack
(2)
randomized smoothing
(2)
contrastive learning
(2)
neural network
(2)
model safety
(1)
recurrent neural network
(1)
model merging
(1)
nuclear norm
(1)
linear probing
(1)
inductive bia
(1)
neighborhood component analysis
(1)
pre-trained model
(1)
linear programming
(1)
spectral truncation
(1)
neural network verification
(1)
decision boundary
(1)
convex relaxation
(1)
Papers
AI Steerability 360: A Toolkit for Steering Large Language Models
ACL 2026
ImReasoner: Improving Memory-based Language Models for Reasoning-in-a-Haystack Tasks
ACL 2026
Attention Tracker: Detecting Prompt Injection Attacks in LLMs
NAACL 2025
Large Language Models can Become Strong Self-Detoxifiers
ICLR 2025
STAR: Spectral Truncation and Rescale for Model Merging
NAACL 2025
What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks
ICML 2024
Sample-Specific Debiasing for Better Image-Text Models
MLHC 2023
Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
ICML 2022
Hidden Cost of Randomized Smoothing
AISTATS 2021
Fastened CROWN: Tightened Neural Network Robustness Certificates
AAAI 2020
Higher-Order Certification For Randomized Smoothing
NeurIPS 2020
POPQORN: Quantifying Robustness of Recurrent Neural Networks
ICML 2019