Shentao Yang
5 papers · 2022–2024 · 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(15)
📈
Trend Setter
Venues
Top co-authors
Research topics
Deep Learning
(3)
Machine Learning
(2)
Natural Language Processing
(2)
Reinforcement Learning
(2)
Generation · Natural Language Processing
(2)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Methods
(2)
Artificial Intelligence
(1)
Computer Vision
(1)
Core AI
(1)
Generation · Computer Vision
(1)
Models
(1)
Resources & Methods
(1)
Keywords
model-based reinforcement learning
(2)
offline reinforcement learning
(2)
preference learning
(1)
preference alignment
(1)
response generation
(1)
text generation
(1)
policy learning
(1)
text-to-image generation
(1)
task-oriented dialogue
(1)
continuous control
(1)
learning to rank
(1)
stationary distribution
(1)
reward learning
(1)
diffusion model
(1)
lower bound
(1)
language model
(1)
dynamics model
(1)
end-to-end training
(1)
language model fine-tuning
(1)
dynamic model
(1)
Papers
A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
ICML 2024
Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems
ICLR 2023
Preference-grounded Token-level Guidance for Language Model Fine-tuning
NeurIPS 2023
A Unified Framework for Alternating Offline Model Training and Policy Learning
NeurIPS 2022
Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning
ICML 2022