Tai-Wei Chang
4 papers · 2014–2025 · 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 · Half
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(15)
Venues
Top co-authors
Research topics
Artificial Intelligence
(3)
Machine Learning
(3)
Core AI
(3)
Learning Types · Machine Learning
(3)
Optimization & Theory
(3)
Deep Learning
(2)
Natural Language Processing
(2)
Learning Types · Deep Learning
(2)
Reinforcement Learning
(1)
Bayesian & Probabilistic
(1)
Core Methods
(1)
Generation
(1)
Learning Paradigms
(1)
Methods
(1)
Resources & Methods
(1)
Keywords
reinforcement learning from human feedback
(2)
reinforcement learning
(1)
probabilistic modeling
(1)
policy optimization
(1)
language model alignment
(1)
label noise
(1)
mirror descent
(1)
language model
(1)
reward model
(1)
credit assignment
(1)
causal graph
(1)
llm alignment
(1)
transition matrix
(1)
instance-dependent noise
(1)
large language model
(1)
reward redistribution
(1)
token-level reward
(1)
ai-generated feedback
(1)
reward composition
(1)
fairness theory
(1)
Papers
Learning Causal Transition Matrix for Instance-dependent Label Noise
AAAI 2025
RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution
EMNLP 2025
Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning
EMNLP 2024
Interpretation of Chinese Discourse Connectives for Explicit Discourse Relation Recognition
COLING 2014