Huijia Wu
8 papers · 2016–2026 · 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 ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Academic Marathon Β· Half π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (16) π£ Hot Topic Early Bird
π§
Keyword Pioneer
Venues
Top co-authors
Research topics
Keywords
large language model
(3)
prompt engineering
(1)
text generation
(1)
toxicity detection
(1)
task-oriented dialogue
(1)
safety alignment
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
mixture of expert
(1)
sparse autoencoder
(1)
risk assessment
(1)
task decomposition
(1)
decoding strategy
(1)
bias amplification
(1)
harmful content detection
(1)
skip connection
(1)
expert routing
(1)
jailbreak defense
(1)
sparse expert selection
(1)
cost optimization
(1)
Papers
From Chaos to Cure: A Prefix Heuristics Guided Model-Agnostic Adaptive Detoxification Framework
AAAI 2026
HEV Generative Sandbox: A Framework for Assessing Domain-Specific Social Risks Through Human-LLM Simulation
AAAI 2026
Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
ACL 2026
SecDecoding: Steerable Decoding for Safer LLM Generation
EMNLP 2025
Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
EMNLP 2025
HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts
ACL 2024
An Adaptive Prompt Generation Framework for Task-oriented Dialogue System
EMNLP 2023
An Empirical Exploration of Skip Connections for Sequential Tagging
COLING 2016