Xinwei Wu
12 papers · 2022–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (4) π§ Keyword Pioneer π£ Hot Topic Early Bird π Renaissance Researcher (5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(19)
π₯
Unstoppable
(5)
β
The Questioner
(2)
Conferences
ACL (5)
EMNLP (4)
AAAI (1)
COLING (1)
NIPS (1)
Top co-authors
Research topics
Keywords
large language model
(5)
neuron editing
(3)
sparse autoencoder
(3)
machine translation
(2)
model editing
(2)
parametric knowledge
(2)
value alignment
(2)
privacy protection
(2)
privacy neuron
(2)
language model
(2)
integrated gradient
(2)
model interpretability
(1)
cross-lingual transfer
(1)
adam optimizer
(1)
ai safety
(1)
representation learning
(1)
machine unlearning
(1)
quality estimation
(1)
knowledge editing
(1)
mechanistic interpretability
(1)
Papers
Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation
ACL 2026
Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs
AAAI 2026
From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models
ACL 2026
M2PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation
ACL 2026
DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events?
EMNLP 2025
CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation
COLING 2025
Towards a Unified Paradigm of Concept Editing in Large Language Models
EMNLP 2025
Exploring Multilingual Concepts of Human Values in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?
EMNLP 2024
Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching
ACL 2024
IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
NIPS 2024
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
EMNLP 2023
Adaptive Differential Privacy for Language Model Training
ACL 2022