Xiaomeng Hu
7 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(4)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(23)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
EMNLP (3)
NIPS (2)
AAAI (1)
ACL (1)
Top co-authors
Keywords
large language model
(6)
jailbreak attack
(2)
safety alignment
(2)
knowledge transfer
(1)
text generation
(1)
question generation
(1)
model adaptation
(1)
instruction tuning
(1)
adversarial attack
(1)
autoregressive model
(1)
adversarial defense
(1)
language model
(1)
cycle consistency
(1)
parameter-efficient tuning
(1)
adversarial prompt
(1)
retrieval-augmented generation
(1)
reasoning model
(1)
hallucination detection
(1)
process reward
(1)
gradient information
(1)
Papers
ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models
ACL 2025
Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
AAAI 2025
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization
EMNLP 2025
CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency
EMNLP 2025
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
NIPS 2024
Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection
EMNLP 2024
RADAR: Robust AI-Text Detection via Adversarial Learning
NIPS 2023