Qifu (Danny) Wen

2026

1. 

   How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL

   Qifu Wen, Shuaijun Liu, Zihan Zhou, and 2 more authors

   2026

   Preprint

   arXiv BibTeX Website

   @article{wen2026predictor,
     title = {How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL},
     author = {Wen, Qifu and Liu, Shuaijun and Zhou, Zihan and Zeng, Xi and Su, Ningxin},
     year = {2026},
     note = {Preprint},
   }

2. 

   SR-JEPA: Learning Predictive Latent State in 3D Scenes

   Zihan Zhou, Qifu Wen, and Xi Zeng

   2026

   Preprint

   arXiv BibTeX

   @article{zhou2026srjepa,
     title = {SR-JEPA: Learning Predictive Latent State in 3D Scenes},
     author = {Zhou, Zihan and Wen, Qifu and Zeng, Xi},
     year = {2026},
     note = {Preprint},
   }

3. 

   CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs

   Shuaijun Liu, Qifu Wen, Shuyang Hao, and 5 more authors

   2026

   Preprint; under review at AAAI 2027

   arXiv BibTeX

   @article{liu2026cowam,
     title = {CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs},
     author = {Liu, Shuaijun and Wen, Qifu and Hao, Shuyang and Luo, Qi and Zhang, Chenglong and You, Feiyang and Wu, Chengyu and Su, Ningxin},
     year = {2026},
     note = {Preprint; under review at AAAI 2027},
   }

4. 

   One Ocean, All Tasks: A Holistic Simulation Environment for Marine Robotics

   Shuaijun Liu, Qifu Wen, Xiang Chen, and 2 more authors

   2026

   Under review at AAAI 2027

   Abstract BibTeX

   OceanEnv is a modular framework unifying large-scale ocean data with simulation tools for 3-DOF and 6-DOF marine robotics training.

   @article{liu2026ocean,
     title = {One Ocean, All Tasks: A Holistic Simulation Environment for Marine Robotics},
     author = {Liu, Shuaijun and Wen, Qifu and Chen, Xiang and Hu, Xinyu and Su, Ningxin},
     year = {2026},
     note = {Under review at AAAI 2027},
   }

5. 

   Estimation of Distribution Parameters by Mean Absolute Deviations of a Truncated Distribution Using Quantile Functions

   Eugene Pinsky and Qifu Wen

   Statistical Papers, Feb 2026

   Co-first authors

   Abstract DOI BibTeX HTML Website

   Novel parameter estimation method using mean absolute deviations around quartiles for truncated distributions without moments or variance, providing closed-form solutions comparable to MLE for Lévy, Cauchy, and Pareto distributions.

   @article{pinsky2026estimation,
     title = {Estimation of Distribution Parameters by Mean Absolute Deviations of a Truncated Distribution Using Quantile Functions},
     author = {Pinsky, Eugene and Wen, Qifu},
     journal = {Statistical Papers},
     publisher = {Springer},
     year = {2026},
     month = feb,
     volume = {67},
     number = {31},
     doi = {10.1007/s00362-026-01811-4},
     note = {Co-first authors},
   }

2025

1. 

   GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping

   Qifu Wen, Xi Zeng, Zihan Zhou, and 4 more authors

   2025

   Preprint; under review at AAAI 2027

   Abstract arXiv BibTeX

   GradES is a gradient-based early stopping algorithm that individually freezes transformer components when their gradients fall below a convergence threshold. Achieves 1.70–1.77× faster full-parameter fine-tuning at neutral accuracy on Qwen3-0.6B, Llama-3.1-8B, and Qwen3-14B.

   @article{wen2025grades,
     title = {GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping},
     author = {Wen, Qifu and Zeng, Xi and Zhou, Zihan and Liu, Shuaijun and Hosseinzadeh, Mehdi and Su, Ningxin and Rawassizadeh, Reza},
     year = {2025},
     note = {Preprint; under review at AAAI 2027},
   }

2. 

   Pruning and Quantization Impact on Graph Neural Networks

   Khatoon Khedri, Reza Rawassizadeh, Qifu Wen, and 1 more author

   2025

   Preprint; under review at JAIR

   arXiv BibTeX

   @article{khedri2025pruning,
     title = {Pruning and Quantization Impact on Graph Neural Networks},
     author = {Khedri, Khatoon and Rawassizadeh, Reza and Wen, Qifu and Hosseinzadeh, Mehdi},
     year = {2025},
     note = {Preprint; under review at JAIR},
   }

3. 

   From Clicks to Conversations: Evaluating the Effectiveness of Conversational Agents in Statistical Analysis

   Qifu Wen, Prishita Kochhar, Sherif Zeyada, and 2 more authors

   International Journal of Human-Computer Interaction, 2025

   Abstract DOI BibTeX HTML

   We compared conversational agents to traditional GUIs for statistical analysis through a user study with 51 participants. Conversational agents significantly outperformed GUI-based software on accuracy, completion time, and user satisfaction.

   @article{wen2025clicks,
     title = {From Clicks to Conversations: Evaluating the Effectiveness of Conversational Agents in Statistical Analysis},
     author = {Wen, Qifu and Kochhar, Prishita and Zeyada, Sherif and Javaheri, Tahereh and Rawassizadeh, Reza},
     journal = {International Journal of Human-Computer Interaction},
     publisher = {Taylor \& Francis},
     year = {2025},
     doi = {10.1080/10447318.2025.2561760},
   }

4. 

   Simple Approximations and Interpretation of Pareto Index and Gini Coefficient Using Mean Absolute Deviations and Quantile Functions

   Eugene Pinsky and Qifu Wen

   Econometrics, 2025

   DOI BibTeX HTML

   @article{pinsky2025pareto,
     title = {Simple Approximations and Interpretation of Pareto Index and Gini Coefficient Using Mean Absolute Deviations and Quantile Functions},
     author = {Pinsky, Eugene and Wen, Qifu},
     year = {2025},
     journal = {Econometrics},
     volume = {13},
     number = {3},
     pages = {30},
     doi = {10.3390/econometrics13030030},
   }