Yuzhong Hong
3 papers · 2019–2025 · 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 · Bronze
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Artificial Intelligence
(2)
Machine Learning
(2)
Core AI
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Deep Learning
(1)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Methods
(1)
Processing
(1)
Resources & Methods
(1)
Keywords
direct preference optimization
(1)
masked language model
(1)
language model alignment
(1)
instruction tuning
(1)
error detection
(1)
model alignment
(1)
denoising autoencoder
(1)
supervised fine-tuning
(1)
error correction
(1)
chinese language
(1)
spell checking
(1)
text correction
(1)
large language model
(1)
offline alignment
(1)
bradley-terry preference model
(1)
energy preference alignment
(1)
energy-based preference model
(1)
kl-constrained rlhf loss
(1)
unique mle
(1)
Papers
Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
ICML 2025
Preference-Oriented Supervised Fine-Tuning: Favoring Target Model over Aligned Large Language Models
AAAI 2025
FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm
EMNLP 2019