Songlei Jian
10 papers · 2017–2026 · 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (27)
ποΈ
Keyword Collector
(60)
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Conference Pioneer
Top co-authors
Research topics
Machine Learning
(8)
Learning Types Β· Machine Learning
(6)
Artificial Intelligence
(5)
Deep Learning
(4)
Core Methods
(4)
Core AI
(3)
Learning Types Β· Deep Learning
(3)
Data Science & Analytics
(2)
Applications
(2)
Learning Paradigms
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Analysis
(1)
Application Areas
(1)
Architectures
(1)
Keywords
jailbreak attack
(2)
representation learning
(2)
image classification
(1)
adversarial learning
(1)
semi-supervised learning
(1)
few-shot learning
(1)
domain adaptation
(1)
hierarchical clustering
(1)
anomaly detection
(1)
matrix factorization
(1)
similarity learning
(1)
collaborative filtering
(1)
backdoor defense
(1)
self-supervised learning
(1)
cross-domain learning
(1)
transfer learning
(1)
machine unlearning
(1)
safety alignment
(1)
content-based filtering
(1)
link prediction
(1)
Papers
JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
ACL 2026
BadWindtunnel: Defending Backdoor in High-noise Simulated Training with Confidence Variance
ACL 2025
Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience
EMNLP 2025
Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning
ICML 2023
Rethinking Class Relations: Absolute-Relative Supervised and Unsupervised Few-Shot Learning
CVPR 2021
Representation Learning with Multiple Lipschitz-Constrained Alignments on Partially-Labeled Cross-Domain Data
AAAI 2020
Evolutionarily Learning Multi-Aspect Interactions and Influences from Network Structure and Node Content
AAAI 2019
HERS: Modeling Influential Contexts with Heterogeneous Relations for Sparse and Cold-Start Recommendation
AAAI 2019
Interpretable Recommendation via Attraction Modeling: Learning Multilevel Attractiveness over Multimodal Movie Contents
IJCAI 2018
Embedding-based Representation of Categorical Data by Hierarchical Value Coupling Learning
IJCAI 2017