XiaoHua Feng
4 papers · 2024–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (2) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
AAAI (2)
EMNLP (1)
ICLR (1)
Top co-authors
Keywords
federated learning
(1)
constrained reinforcement learning
(1)
knowledge editing
(1)
machine unlearning
(1)
knowledge unlearning
(1)
adversarial attack
(1)
hierarchical bayesian model
(1)
data heterogeneity
(1)
language model
(1)
sequential recommendation
(1)
vision-language model
(1)
bi-level optimization
(1)
sensitive information
(1)
gradient ascent
(1)
fine-grained control
(1)
distribution consistency
(1)
one-shot federated adaptation
(1)
profile pollution attack
(1)
Papers
Potent but Stealthy: Rethink Profile Pollution Against Sequential Recommendation via Bi-Level Constrained Reinforcement Paradigm
AAAI 2026
TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models
AAAI 2026
Controllable Unlearning for Image-to-Image Generative Models via $\epsilon$-Constrained Optimization
ICLR 2025
Fine-grained Pluggable Gradient Ascent for Knowledge Unlearning in Language Models
EMNLP 2024