Xilie Xu
8 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (4) π Academic Marathon (5)
π£
Hot Topic Early Bird
π
Cross-Pollinator
(14)
π
Renaissance Researcher
(5)
π
Grand Slam
Conferences
NIPS (3)
ICLR (2)
ICML (2)
AAAI (1)
Top co-authors
Research topics
Keywords
adversarial training
(2)
adversarial contrastive learning
(2)
representation learning
(1)
reinforcement learning
(1)
adversarial robustness
(1)
image generation
(1)
causal reasoning
(1)
coreset selection
(1)
preference alignment
(1)
privacy preservation
(1)
language model alignment
(1)
reinforcement learning from human feedback
(1)
two-sample test
(1)
projected gradient descent
(1)
submodular maximization
(1)
human feedback
(1)
adversarial attack
(1)
adversarial defense
(1)
low-rank adaptation
(1)
supervised fine-tuning
(1)
Papers
Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models
AAAI 2025
An LLM can Fool Itself: A Prompt-Based Adversarial Attack
ICLR 2024
AutoLoRa: An Automated Robust Fine-Tuning Framework
ICLR 2024
Perplexity-aware Correction for Robust Alignment with Noisy Preferences
NIPS 2024
Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization
NIPS 2023
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
NIPS 2023
Adversarial Attack and Defense for Non-Parametric Two-Sample Tests
ICML 2022
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
ICML 2020