Jaehun Jung
8 papers · 2020–2025 · 3 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(25)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(5)
Natural Language Processing
(5)
Core AI
(5)
Application Areas
(4)
Deep Learning
(3)
Generation
(3)
Learning Types · Machine Learning
(3)
Reinforcement Learning
(2)
Core Methods
(2)
Methods
(2)
Models
(2)
Applications
(1)
Learning Types · Deep Learning
(1)
Resources & Methods
(1)
Keywords
text generation
(3)
unsupervised learning
(2)
model compression
(2)
reinforcement learning
(2)
large language model
(2)
language model
(2)
logical reasoning
(1)
explanation generation
(1)
model calibration
(1)
vision-language model
(1)
chain-of-thought reasoning
(1)
policy learning
(1)
visual reasoning
(1)
paraphrase generation
(1)
knowledge graph
(1)
prompt engineering
(1)
monte carlo tree search
(1)
off-policy learning
(1)
knowledge distillation
(1)
style transfer
(1)
Papers
Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions
EMNLP 2025
Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
ICLR 2025
Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model
NAACL 2024
JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
NAACL 2024
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
EMNLP 2023
STEER: Unified Style Transfer with Expert Reinforcement
EMNLP 2023
Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations
EMNLP 2022
AttnIO: Knowledge Graph Exploration with In-and-Out Attention Flow for Knowledge-Grounded Dialogue
EMNLP 2020