PPaperPicks

Yang Liu

University of California, Santa Cruz, CA, USA

41 papers at tracked venues · 37 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-8420-6011 ↗Google Scholar ↗Homepage ↗

Venues

ICLR ×12NeurIPS ×9AAAI ×6ICML ×4AISTATS ×2SIGKDD ×2ACL ×1ECCV ×1EMNLP ×1ICCV ×1ICDE ×1WWW ×1

Frequent coauthors

Yaxuan Wang
DBLP profile ↗ORCID search ↗
×3
Zonglin Di
DBLP profile ↗ORCID search ↗
×3
Jinlong Pang
DBLP profile ↗ORCID search ↗
×3
Andrew Estornell
DBLP profile ↗ORCID search ↗
×2
Chentao Cao
DBLP profile ↗ORCID search ↗
×2
Yatong Chen
DBLP profile ↗ORCID search ↗
×2
Xiaoying Zhang
DBLP profile ↗ORCID search ↗
×2
Jayanth Yetukuri
DBLP profile ↗ORCID search ↗
×2
Jiaheng Wei
DBLP profile ↗ORCID search ↗
×1
Yichi Zhang
DBLP profile ↗ORCID search ↗
×1
Minghao Liu
DBLP profile ↗ORCID search ↗
×1
Peng Wu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop
    ACL 2026 ·
    Yaxuan Wang
    DBLP profile ↗ORCID search ↗
  2. Robust Learning from Noisily Labeled Long-Tailed Data via Fairness Regularizer
    AAAI 2026 ·
    Jiaheng Wei
    DBLP profile ↗ORCID search ↗
  3. ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
    ICLR 2025 ·
    Andrew Estornell
    DBLP profile ↗ORCID search ↗
  4. Adversarial Machine Unlearning
    ICLR 2025 ·
    Zonglin Di
    DBLP profile ↗ORCID search ↗
  5. DiffTell: A High-Quality Dataset for Describing Image Manipulation Changes
    ICCV 2025 ·
    Zonglin Di
    DBLP profile ↗ORCID search ↗
  6. Evaluating LLM-contaminated Crowdsourcing Data Without Ground Truth
    NeurIPS 2025 ·
    Yichi Zhang
    DBLP profile ↗ORCID search ↗
  7. Human and AI Perceptual Differences in Image Classification Errors
    AAAI 2025 ·
    Minghao Liu
    DBLP profile ↗ORCID search ↗
  8. Improving Data Efficiency via Curating LLM-Driven Rating Systems
    ICLR 2025 ·
    Jinlong Pang
    DBLP profile ↗ORCID search ↗
  9. LLM Unlearning via Loss Adjustment with Only Forget Data
    ICLR 2025 ·
    Yaxuan Wang
    DBLP profile ↗ORCID search ↗
  10. Learning Counterfactual Outcomes Under Rank Preservation
    NeurIPS 2025 ·
    Peng Wu
    DBLP profile ↗ORCID search ↗
  11. Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels
    SIGKDD 2025 ·
    Yaxuan Wang
    DBLP profile ↗ORCID search ↗
  12. Noisy Test-Time Adaptation in Vision-Language Models
    ICLR 2025 ·
    Chentao Cao
    DBLP profile ↗ORCID search ↗
  13. Nonparametric Factor Analysis and Beyond
    AISTATS 2025 ·
    Yujia Zheng
    DBLP profile ↗ORCID search ↗
  14. Prompting Fairness: Integrating Causality to Debias Large Language Models
    ICLR 2025 ·
    Jingling Li
    DBLP profile ↗ORCID search ↗
  15. Regretful Decisions under Label Noise
    ICLR 2025 ·
    Sujay Nagaraj
    DBLP profile ↗ORCID search ↗
  16. To Give or Not to Give? The Impacts of Strategically Withheld Recourse
    AISTATS 2025 ·
    Yatong Chen
    DBLP profile ↗ORCID search ↗
  17. Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
    ICML 2025 ·
    Jinlong Pang
    DBLP profile ↗ORCID search ↗
  18. Toward Optimal LLM Alignments Using Two-Player Games
    EMNLP 2025 ·
    Rui Zheng
    DBLP profile ↗ORCID search ↗
  19. Understanding Chain-of-Thought in LLMs through Information Theory
    ICML 2025 ·
    Jean-Francois Ton
    DBLP profile ↗ORCID search ↗
  20. Achievable Fairness on Your Data With Utility Guarantees
    NeurIPS 2024 ·
    Muhammad Faaiz Taufiq
    DBLP profile ↗ORCID search ↗
  21. Conformal Counterfactual Inference under Hidden Confounding
    SIGKDD 2024 ·
    Zonghao Chen
    DBLP profile ↗ORCID search ↗
  22. Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
    ICML 2024 ·
    Chentao Cao
    DBLP profile ↗ORCID search ↗
  23. Fair Classifiers that Abstain without Harm
    ICLR 2024 ·
    Tongxin Yin
    DBLP profile ↗ORCID search ↗
  24. Fair Participation via Sequential Policies
    AAAI 2024 ·
    Reilly Raab
    DBLP profile ↗ORCID search ↗
  25. Fairness without Harm: An Influence-Guided Active Sampling Approach
    NeurIPS 2024 ·
    Jinlong Pang
    DBLP profile ↗ORCID search ↗
  26. FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning
    AAAI 2024 ·
    Xinyuan Ji
    DBLP profile ↗ORCID search ↗
  27. Federated Learning with Local Openset Noisy Labels
    ECCV 2024 ·
    Zonglin Di
    DBLP profile ↗ORCID search ↗
  28. Large Language Model Unlearning via Embedding-Corrupted Prompts
    NeurIPS 2024 ·
    Chris Yuhao Liu
    DBLP profile ↗ORCID search ↗
  29. Learning the Optimal Policy for Balancing Short-Term and Long-Term Rewards
    NeurIPS 2024 ·
    Qinwei Yang
    DBLP profile ↗ORCID search ↗
  30. Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
    NeurIPS 2024 ·
    Xiaoying Zhang
    DBLP profile ↗ORCID search ↗
  31. Multi-LLM Debate: Framework, Principals, and Interventions
    NeurIPS 2024 ·
    Andrew Estornell
    DBLP profile ↗ORCID search ↗
  32. Multifaceted Reformulations for Null & Low queries and its parallelism with Counterfactuals
    ICDE 2024 ·
    Jayanth Yetukuri
    DBLP profile ↗ORCID search ↗
  33. Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts
    AAAI 2024 ·
    Kun Jin
    DBLP profile ↗ORCID search ↗
  34. Performative Prediction with Bandit Feedback: Learning through Reparameterization
    ICML 2024 ·
    Yatong Chen
    DBLP profile ↗ORCID search ↗
  35. Post-hoc bias scoring is optimal for fair classification
    ICLR 2024 ·
    Wenlong Chen
    DBLP profile ↗ORCID search ↗
  36. Procedural Fairness Through Decoupling Objectionable Data Generating Components
    ICLR 2024 ·
    Zeyu Tang
    DBLP profile ↗ORCID search ↗
  37. Providing Fair Recourse over Plausible Groups
    AAAI 2024 ·
    Jayanth Yetukuri
    DBLP profile ↗ORCID search ↗
  38. Retention Depolarization in Recommender System
    WWW 2024 ·
    Xiaoying Zhang
    DBLP profile ↗ORCID search ↗
  39. RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies
    ICLR 2024 ·
    Hao Cheng
    DBLP profile ↗ORCID search ↗
  40. Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
    ICLR 2024 ·
    Zhaowei Zhu
    DBLP profile ↗ORCID search ↗
  41. User-Creator Feature Polarization in Recommender Systems with Dual Influence
    NeurIPS 2024 ·
    Tao Lin
    DBLP profile ↗ORCID search ↗