Depeng Xu
6 papers · 2019–2025 · 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 ↓
π
Conference Polyglot Β· Silver
π
Academic Marathon Β· Sprint
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(11)
π£
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
bias mitigation
(2)
model interpretability
(1)
backdoor attack
(1)
adversarial attack
(1)
weight decay
(1)
generative adversarial network
(1)
pre-trained language model
(1)
cross-attention mechanism
(1)
semantic preservation
(1)
sensitive attribute
(1)
fairness criterion
(1)
poisoned sample
(1)
causal modeling
(1)
fine tuning
(1)
personally identifiable information
(1)
word substitution
(1)
text perturbation
(1)
data generation
(1)
causal fairness
(1)
motion retargeting
(1)
Papers
Fine-tuning LLMs with Cross-Attention-based Weight Decay for Bias Mitigation
EMNLP 2025
Privacy-centric Deep Motion Retargeting for Anonymization of Skeleton-Based Motion Visualization
ICCV 2025
Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization
ICML 2024
Discovering and Mitigating Indirect Bias in Attention-Based Model Explanations
NAACL 2024
Generating Textual Adversaries with Minimal Perturbation
EMNLP 2022
Achieving Causal Fairness through Generative Adversarial Networks
IJCAI 2019