Zexu Sun
8 papers · 2023–2026 · 6 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(22)
🏆
Grand Slam
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI
(6)
Machine Learning
(5)
Reinforcement Learning
(3)
Methods
(3)
Optimization & Theory
(3)
Deep Learning
(2)
Knowledge & Reasoning
(1)
Natural Language Processing
(1)
Application Areas
(1)
Applications
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Keywords
large language model
(3)
uplift modeling
(2)
policy optimization
(1)
direct preference optimization
(1)
data augmentation
(1)
intent classification
(1)
knowledge base
(1)
invariant learning
(1)
hierarchical decomposition
(1)
information gain
(1)
variational autoencoder
(1)
reward model
(1)
counterfactual reasoning
(1)
robotics manipulation
(1)
relative accuracy
(1)
out-of-distribution generalization
(1)
evaluation metric
(1)
selection bia
(1)
intent recognition
(1)
mathematical reasoning
(1)
Papers
Beyond Step Pruning: Information Theory Based Step-level Optimization for Self-Refining Large Language Models
AAAI 2026
Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement
ACL 2026
Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency
ICML 2025
KAPA: A Deliberative Agent Framework with Tree-Structured Knowledge Base for Multi-Domain User Intent Understanding
ACL 2025
Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation
ICML 2025
Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback
ICLR 2025
Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment
EMNLP 2024
Offline Imitation Learning with Variational Counterfactual Reasoning
NeurIPS 2023