Zhengyi Yang
6 papers · 2023–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Optimization & Theory
(4)
Learning Types · Machine Learning
(3)
Data Science & Analytics
(2)
Deep Learning
(2)
Natural Language Processing
(2)
Applications
(2)
Core Methods
(2)
Models
(2)
Resources & Methods
(2)
Reinforcement Learning
(1)
Architectures
(1)
Learning Types · Deep Learning
(1)
Keywords
direct preference optimization
(3)
negative sampling
(2)
user preference
(2)
chain-of-thought reasoning
(1)
language model training
(1)
multimodal learning
(1)
parameter optimization
(1)
item recommendation
(1)
distributionally robust optimization
(1)
preference modeling
(1)
diffusion model
(1)
language model
(1)
sequential recommendation
(1)
human preference
(1)
recommender system
(1)
transformer encoder
(1)
noisy data
(1)
molecular relational learning
(1)
chain of thought
(1)
reward margin
(1)
Papers
AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
ICML 2025
Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
ICLR 2025
β-DPO: Direct Preference Optimization with Dynamic β
NeurIPS 2024
MolTC: Towards Molecular Relational Modeling In Language Models
ACL 2024
On Softmax Direct Preference Optimization for Recommendation
NeurIPS 2024
Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion
NeurIPS 2023