Zexu Sun

Orcid: 0000-0002-6727-6242

According to our database1, Zexu Sun authored at least 22 papers between 2023 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning.
CoRR, June, 2025

Counterfactual Multi-player Bandits for Explainable Recommendation Diversification.
CoRR, May, 2025

What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models.
CoRR, March, 2025

Sequential Causal Effect Estimation by Jointly Modeling the Unmeasured Confounders and Instrumental Variables.
IEEE Trans. Knowl. Data Eng., February, 2025

ARIES: Stimulating Self-Refinement of Large Language Models by Iterative Preference Optimization.
CoRR, February, 2025

Robust Uplift Modeling with Large-Scale Contexts for Real-time Marketing.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.1, 2025

Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

KAPA: A Deliberative Agent Framework with Tree-Structured Knowledge Base for Multi-Domain User Intent Understanding.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
End-to-End Cost-Effective Incentive Recommendation under Budget Constraint with Uplift Modeling.
CoRR, 2024

Generalized Encouragement-Based Instrumental Variables for Counterfactual Regression.
CoRR, 2024

Benchmarking for Deep Uplift Modeling in Online Marketing.
CoRR, 2024

Revisiting Counterfactual Regression through the Lens of Gromov-Wasserstein Information Bottleneck.
CoRR, 2024

End-to-End Cost-Effective Incentive Recommendation under Budget Constraint with Uplift Modeling.
Proceedings of the 18th ACM Conference on Recommender Systems, 2024

Towards Robust Recommendation via Decision Boundary-aware Graph Contrastive Learning.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

Rankability-enhanced Revenue Uplift Modeling Framework for Online Marketing.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

Policy-Based Bayesian Active Causal Discovery with Deep Reinforcement Learning.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

M<sup>3</sup>TN: Multi-Gate Mixture-of-Experts Based Multi-Valued Treatment Network for Uplift Modeling.
Proceedings of the IEEE International Conference on Acoustics, 2024

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Towards Effective and Efficient Multi-valued Treatment Uplift Modeling in Online Marketing.
Proceedings of the Database Systems for Advanced Applications, 2024

OptDist: Learning Optimal Distribution for Customer Lifetime Value Prediction.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

2023
Offline Imitation Learning with Variational Counterfactual Reasoning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Robustness-enhanced Uplift Modeling with Adversarial Feature Desensitization.
Proceedings of the IEEE International Conference on Data Mining, 2023


  Loading...