Hang Su
Scholar

Hang Su

Google Scholar ID: dxN1_X0AAAAJ
Associated Professor, Tsinghua University
Adversarial LearningAdversarial Attacks and DefenseInterpretable Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
26,055
 
H-index
61
 
i10-index
155
 
Publications
20
 
Co-authors
11
list available
Contact
No contact links provided.
Publications
13 items
Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses
2026
Cited
0
Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
2026
Cited
0
Mind over Space: Can Multimodal Large Language Models Mentally Navigate?
2026
Cited
0
World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation Models
2026
Cited
0
Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving
2026
Cited
0
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
2026
Cited
0
MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
2026
Cited
0
Geometry-Aware Rotary Position Embedding for Consistent Video World Model
2026
Cited
0
Resume (English only)
Co-authors
11 total
Jun Zhu
Jun Zhu
Professor of Computer Science, Tsinghua University
Yinpeng Dong
Yinpeng Dong
Tsinghua University
Xiao Yang
Xiao Yang
Tsinghua University
Tianyu Pang
Tianyu Pang
Senior Research Scientist, Sea AI Lab
Co-author 5
Co-author 5
Jianguo Li
Jianguo Li
Director, Ant Group
Zhaozheng Yin
Zhaozheng Yin
SUNY Empire Innovation Associate Professor, Stony Brook University
Jun Li（李骏）
Jun Li（李骏）
FIEEE, Professor@Southeast University