Gaojie Jin
14 papers · 2020–2026 · 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (28) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Grand Slam
β
The Questioner
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(66)
Top co-authors
Research topics
Machine Learning
(11)
Artificial Intelligence
(8)
Core AI
(8)
Learning Types Β· Machine Learning
(7)
Optimization & Theory Β· Machine Learning
(6)
Deep Learning
(3)
Learning Types Β· Deep Learning
(3)
Application Areas
(2)
Techniques
(2)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Methods
(1)
Optimization & Theory Β· Deep Learning
(1)
Resources & Methods
(1)
Keywords
adversarial robustness
(4)
confusion matrix
(2)
large language model
(2)
spectral norm
(2)
adversarial training
(2)
adversarial attack
(2)
pac learning
(1)
language model training
(1)
false discovery rate
(1)
loss landscape
(1)
class imbalance
(1)
spectral regularization
(1)
second-order statistics
(1)
generalization bound
(1)
preference optimization
(1)
backdoor attack
(1)
explainable ai
(1)
second-order optimization
(1)
trajectory prediction
(1)
chain-of-thought reasoning
(1)
Papers
BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
AAAI 2026
CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
AAAI 2026
Confusion-Aware Spectral Regularizer for Long-Tailed Recognition
CVPR 2026
Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Model
ACML 2025
Enhancing Robust Fairness via Confusional Spectral Regularization
ICLR 2025
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
ICLR 2025
Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors
ECCV 2024
Position: Building Guardrails for Large Language Models Requires Systematic Design
ICML 2024
Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning
AAAI 2023
Randomized Adversarial Training via Taylor Expansion
CVPR 2023
SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability
ICCV 2023
TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models
ICCV 2023
Enhancing Adversarial Training With Second-Order Statistics of Weights
CVPR 2022
How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?
NeurIPS 2020