Jiwoo Hong
11 papers · 2021–2026 · 8 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (35)
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🗃️
Keyword Collector
(64)
Top co-authors
Research topics
Machine Learning
(10)
Artificial Intelligence
(8)
Core AI
(7)
Optimization & Theory · Machine Learning
(7)
Deep Learning
(6)
Natural Language Processing
(3)
Reinforcement Learning
(3)
Application Areas
(3)
Learning Types · Machine Learning
(3)
Methods
(3)
Models
(3)
Techniques
(3)
Architectures
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory · Deep Learning
(2)
Keywords
reward modeling
(2)
model alignment
(2)
mathematical reasoning
(2)
preference optimization
(2)
text-to-image generation
(1)
language model alignment
(1)
direct preference optimization
(1)
chain-of-thought reasoning
(1)
text classification
(1)
cross-lingual transfer
(1)
attention mechanism
(1)
news analysis
(1)
domain generalization
(1)
neural network optimization
(1)
sample efficiency
(1)
document classification
(1)
policy improvement
(1)
bradley-terry model
(1)
diffusion model
(1)
reinforcement learning
(1)
Papers
Margin-Aware Preference Optimization for Aligning Diffusion Models Without Reference
AAAI 2026
Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning
EACL 2026
AlphaPO: Reward Shape Matters for LLM Alignment
ICML 2025
Cross-lingual Transfer of Reward Models in Multilingual Alignment
NAACL 2025
Evaluating the Consistency of LLM Evaluators
COLING 2025
Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning
ACL 2025
On the Robustness of Reward Models for Language Model Alignment
ICML 2025
ORPO: Monolithic Preference Optimization without Reference Model
EMNLP 2024
Stable Language Model Pre-training by Reducing Embedding Variability
EMNLP 2024
Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy
EMNLP 2023
Activation Sharing with Asymmetric Paths Solves Weight Transport Problem without Bidirectional Connection
NeurIPS 2021