Haoyu Xu
4 papers · 2025–2025 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
Venues
Top co-authors
Research topics
Keywords
large language model
(2)
knowledge editing
(1)
semantic parsing
(1)
model unlearning
(1)
orthogonal projection
(1)
lifelong learning
(1)
adversarial attack
(1)
parameter-efficient fine-tuning
(1)
hallucination mitigation
(1)
soft prompt
(1)
gradient projection
(1)
prompt tuning
(1)
semantic gap
(1)
security vulnerability
(1)
knowledge decoupling
(1)
lifelong model editing
(1)
knowledge cache
(1)
reverse engineering
(1)
outer product
(1)
truncated svd
(1)
Papers
Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product
NAACL 2025
Enhancing SQL Table Acquisition with Reverse Engineering for Text-to-SQL
EMNLP 2025
Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models
COLING 2025
Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models
ACL 2025