Seongho Joo
5 papers · 2023–2025 · 2 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
(16)
Venues
Top co-authors
Research topics
Artificial Intelligence
(4)
Machine Learning
(4)
Core AI
(4)
Learning Types · Machine Learning
(3)
Deep Learning
(2)
Natural Language Processing
(1)
Security & Privacy
(1)
Speech & Audio
(1)
Application Areas
(1)
Core Methods
(1)
Differential Privacy
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Resources & Methods
(1)
Synthesis
(1)
Keywords
large language model
(2)
contrastive learning
(1)
adversarial learning
(1)
few-shot learning
(1)
in-context learning
(1)
speech synthesis
(1)
prompt engineering
(1)
harmful content
(1)
reinforcement learning from human feedback
(1)
determinantal point process
(1)
adversarial attack
(1)
generative model
(1)
public data
(1)
jailbreak attack
(1)
adversarial prompt
(1)
symbolic encoding
(1)
abductive reasoning
(1)
prompt injection
(1)
membership inference attack
(1)
user preference
(1)
Papers
Drift: Decoding-time Personalized Alignments with Implicit User Preferences
EMNLP 2025
Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding
EMNLP 2025
MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers
Interspeech 2025
Public Data Assisted Differentially Private In-Context Learning
EMNLP 2025
DPP-TTS: Diversifying prosodic features of speech via determinantal point processes
EMNLP 2023