Weijie J. Su - RankMe

111 papers A* 24A 1Journal 85Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models. CoRR Weiqing He, Xiang Li, Li Shen, Weijie J. Su, Qi Long
2026	J	`jnl`	Recommending Best Paper Awards for ML/AI Conferences via the Isotonic Mechanism. CoRR Garrett G. Wen, Buxin Su, Natalie Collina, Zhun Deng, Weijie J. Su
2026	J	`jnl`	Statistical Early Stopping for Reasoning Models. CoRR Yangxinyu Xie, Tao Wang, Soham Mallick, Yan Sun, Georgy Noarov, Mengxin Yu, Tanwi Mallick, Weijie J. Su, Edgar Dobriban
2026	J	`jnl`	You Are the Best Reviewer of Your Own Papers: The Isotonic Mechanism. Oper. Res. Weijie J. Su
2025	J	`jnl`	An Overview of Large Language Models for Statisticians. CoRR Wenlong Ji, Weizhe Yuan, Emily J. Getzen, Kyunghyun Cho, Michael I. Jordan, Song Mei, Jason Aaron Edward Weston, Weijie J. Su, Jing Xu, Linjun Zhang
2025	J	`jnl`	Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know? CoRR Xiang Li, Jiayi Xin, Qi Long, Weijie J. Su
2025	A*	`conf`	Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic. ICLR Ruochen Jin, Bojian Hou, Jiancong Xiao, Weijie J. Su, Li Shen
2025	J	`jnl`	Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching. CoRR Zhekun Shi, Kaizhao Liu, Qi Long, Weijie J. Su, Jiancong Xiao
2025	A*	`conf`	Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment. ICLR Mingzhi Wang, Chengdong Ma, Qizhi Chen, Linjian Meng, Yang Han, Jiancong Xiao, Zhaowei Zhang, Jing Huo, Weijie J. Su, Yaodong Yang
2025	J	`jnl`	Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy. CoRR Xiang Li, Buxin Su, Chendi Wang, Qi Long, Weijie J. Su
2025	J	`jnl`	On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection. CoRR Weiqing He, Xiang Li, Tianqi Shang, Li Shen, Weijie J. Su, Qi Long
2025	J	`jnl`	Optimal Detection for Language Watermarks with Pseudorandom Collision. CoRR T. Tony Cai, Xiang Li, Qi Long, Weijie J. Su, Garrett Wen
2025	J	`jnl`	Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts. CoRR Xiang Li, Garrett Wen, Weiqing He, Jiayuan Wu, Qi Long, Weijie J. Su
2025	J	`jnl`	Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers. J. Mach. Learn. Res. Fan Yang, Hongyang R. Zhang, Sen Wu, Christopher Ré, Weijie J. Su
2025	A*	`conf`	Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach. ICML Jiancong Xiao, Bojian Hou, Zhanliang Wang, Ruochen Jin, Qi Long, Weijie J. Su, Li Shen
2025	J	`jnl`	Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach. CoRR Jiancong Xiao, Bojian Hou, Zhanliang Wang, Ruochen Jin, Qi Long, Weijie J. Su, Li Shen
2025	J	`jnl`	Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium. CoRR Kaizhao Liu, Qi Long, Zhekun Shi, Weijie J. Su, Jiancong Xiao
2025	J	`jnl`	Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory. CoRR Jiancong Xiao, Zhekun Shi, Kaizhao Liu, Qi Long, Weijie J. Su
2025	—	`conf`	Towards Rationality in Language and Multimodal Agents: A Survey. NAACL (Long Papers) Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Yuan Yuan, Zhuoqun Hao, Xinyi Bai, Weijie J. Su, Camillo Jose Taylor, Tanwi Mallick
2024	J	`jnl`	A Law of Next-Token Prediction in Large Language Models. CoRR Hangfeng He, Weijie J. Su
2024	J	`jnl`	A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners. CoRR Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao, Xiaomeng Wang, Tanwi Mallick, Weijie J. Su, Camillo J. Taylor, Dan Roth
2024	J	`jnl`	A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules. CoRR Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, Weijie J. Su
2024	J	`jnl`	A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem. CoRR Weijie J. Su
2024	J	`jnl`	AI Risk Management Should Incorporate Both Safety and Security. CoRR Xiangyu Qi, Yangsibo Huang, Yi Zeng, Edoardo Debenedetti, Jonas Geiping, Luxi He, Kaixuan Huang, Udari Madhushani, Vikash Sehwag, Weijia Shi, Boyi Wei, Tinghao Xie, Danqi Chen, Pin-Yu Chen, Jeffrey Ding, Ruoxi Jia, Jiaqi Ma, Arvind Narayanan, Weijie J. Su, Mengdi Wang, Chaowei Xiao, Bo Li, Dawn Song, Peter Henderson, Prateek Mittal
2024	J	`jnl`	An Economic Solution to Copyright Challenges of Generative AI. CoRR Jiachen T. Wang, Zhun Deng, Hiroaki Chiba-Okabe, Boaz Barak, Weijie J. Su
2024	J	`jnl`	Analysis of the ICML 2023 Ranking Data: Can Authors' Opinions of Their Own Papers Assist Peer Review in Machine Learning? CoRR Buxin Su, Jiayao Zhang, Natalie Collina, Yuling Yan, Didong Li, Kyunghyun Cho, Jianqing Fan, Aaron Roth, Weijie J. Su
2024	J	`jnl`	Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization. CoRR Jiancong Xiao, Ruoyu Sun, Qi Long, Weijie J. Su
2024	J	`jnl`	Can AI Be as Creative as Humans? CoRR Haonan Wang, James Zou, Michael Mozer, Anirudh Goyal, Alex Lamb, Linjun Zhang, Weijie J. Su, Zhun Deng, Michael Qizhe Xie, Hannah Brown, Kenji Kawaguchi
2024	J	`jnl`	Debiasing Watermarks for Large Language Models via Maximal Coupling. CoRR Yangxinyu Xie, Xiang Li, Tanwi Mallick, Weijie J. Su, Ruixun Zhang
2024	J	`jnl`	Envisioning future deep learning theories: some basic concepts and characteristics. Sci. China Inf. Sci. Weijie J. Su
2024	J	`jnl`	Fine-Tuning Linear Layers Only Is a Simple yet Effective Way for Task Arithmetic. CoRR Ruochen Jin, Bojian Hou, Jiancong Xiao, Weijie J. Su, Li Shen
2024	J	`jnl`	Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Models Alignment. CoRR Mingzhi Wang, Chengdong Ma, Qizhi Chen, Linjian Meng, Yang Han, Jiancong Xiao, Zhaowei Zhang, Jing Huo, Weijie J. Su, Yaodong Yang
2024	J	`jnl`	Multi-Modal and Multi-Agent Systems Meet Rationality: A Survey. CoRR Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Weijie J. Su, Camillo J. Taylor, Tanwi Mallick
2024	J	`jnl`	Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning. CoRR Chendi Wang, Yuqing Zhu, Weijie J. Su, Yu-Xiang Wang
2024	A*	`conf`	Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning. ICML Chendi Wang, Yuqing Zhu, Weijie J. Su, Yu-Xiang Wang
2024	J	`jnl`	On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization. CoRR Jiancong Xiao, Ziniu Li, Xingyu Xie, Emily J. Getzen, Cong Fang, Qi Long, Weijie J. Su
2024	J	`jnl`	Provable Multi-Party Reinforcement Learning with Diverse Human Feedback. CoRR Huiying Zhong, Zhun Deng, Weijie J. Su, Zhiwei Steven Wu, Linjun Zhang
2024	J	`jnl`	Robust Detection of Watermarks for Large Language Models Under Human Edits. CoRR Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, Weijie J. Su
2024	J	`jnl`	Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic. Trans. Mach. Learn. Res. Matteo Sordello, Niccolò Dalmasso, Hangfeng He, Weijie J. Su
2024	A*	`conf`	Shifted Interpolation for Differential Privacy. ICML Jinho Bok, Weijie J. Su, Jason M. Altschuler
2024	J	`jnl`	Tackling GenAI Copyright Issues: Originality Estimation and Genericization. CoRR Hiroaki Chiba-Okabe, Weijie J. Su
2024	J	`jnl`	The 2020 United States Decennial Census Is More Private Than You (Might) Think. CoRR Buxin Su, Weijie J. Su, Chendi Wang
2024	J	`jnl`	WildfireGPT: Tailored Large Language Model for Wildfire Analysis. CoRR Yangxinyu Xie, Tanwi Mallick, Joshua David Bergerson, John K. Hutchison, Duane R. Verner, Jordan Branham, M. Ross Alexander, Robert B. Ross, Yan Feng, Leslie-Anne Levy, Weijie J. Su
2023	J	`jnl`	Challenges towards the Next Frontier in Privacy. CoRR Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Matthew Jagielski, Yangsibo Huang, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie J. Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, Wanrong Zhang
2023	A*	`conf`	DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization. NeurIPS Hua Wang, Sheng Gao, Huanyu Zhang, Weijie J. Su, Milan Shen
2023	J	`jnl`	DP-HyPO: An Adaptive Private Hyperparameter Optimization Framework. CoRR Hua Wang, Sheng Gao, Huanyu Zhang, Weijie J. Su, Milan Shen
2023	A*	`conf`	FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data. ICLR Zhun Deng, Jiayao Zhang, Linjun Zhang, Ting Ye, Yates Coley, Weijie J. Su, James Zou
2023	J	`jnl`	HiGrad: Uncertainty Quantification for Online Learning and Stochastic Approximation. J. Mach. Learn. Res. Weijie J. Su, Yuancheng Zhu
2023	J	`jnl`	Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training? J. Mach. Learn. Res. Shuxiao Chen, Qinqing Zheng, Qi Long, Weijie J. Su
2023	J	`jnl`	On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks. Quantum Yizhou Liu, Weijie J. Su, Tongyang Li
2023	J	`jnl`	Reward Collapse in Aligning Large Language Models. CoRR Ziang Song, Tianle Cai, Jason D. Lee, Weijie J. Su
2023	A*	`conf`	The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent. ICML Lei Wu, Weijie J. Su
2023	J	`jnl`	The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent. CoRR Lei Wu, Weijie J. Su
2023	J	`jnl`	The Isotonic Mechanism for Exponential Family Estimation. CoRR Yuling Yan, Weijie J. Su, Jianqing Fan
2023	A*	`conf`	Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacy. NeurIPS Chendi Wang, Buxin Su, Jiayuan Ye, Reza Shokri, Weijie J. Su
2023	J	`jnl`	Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacy. CoRR Chendi Wang, Buxin Su, Jiayuan Ye, Reza Shokri, Weijie J. Su
2023	J	`jnl`	What Should Data Science Education Do with Large Language Models? CoRR Xinming Tu, James Zou, Weijie J. Su, Linjun Zhang
2022	J	`jnl`	A Law of Data Separation in Deep Learning. CoRR Hangfeng He, Weijie J. Su
2022	J	`jnl`	A Truthful Owner-Assisted Scoring Mechanism. CoRR Weijie J. Su
2022	A*	`conf`	An Unconstrained Layer-Peeled Perspective on Neural Collapse. ICLR Wenlong Ji, Yiping Lu, Yiliang Zhang, Zhun Deng, Weijie J. Su
2022	J	`jnl`	Analytical Composition of Differential Privacy via the Edgeworth Accountant. CoRR Hua Wang, Sheng Gao, Huanyu Zhang, Milan Shen, Weijie J. Su
2022	J	`jnl`	Causal Inference Principles for Reasoning about Commonsense Causality. CoRR Jiayao Zhang, Hongming Zhang, Dan Roth, Weijie J. Su
2022	J	`jnl`	FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data. CoRR Zhun Deng, Jiayao Zhang, Linjun Zhang, Ting Ye, Yates Coley, Weijie J. Su, James Zou
2022	J	`jnl`	On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks. CoRR Yizhou Liu, Weijie J. Su, Tongyang Li
2022	A*	`conf`	ROCK: Causal Inference Principles for Reasoning about Commonsense Causality. ICML Jiayao Zhang, Hongming Zhang, Weijie J. Su, Dan Roth
2022	J	`jnl`	The Price of Competition: Effect Size Heterogeneity Matters in High Dimensions. IEEE Trans. Inf. Theory Hua Wang, Yachong Yang, Weijie J. Su
2022	J	`jnl`	Understanding the acceleration phenomenon via high-resolution differential equations. Math. Program. Bin Shi, Simon S. Du, Michael I. Jordan, Weijie J. Su
2022	A*	`conf`	Weighted Training for Cross-Task Learning. ICLR Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie J. Su
2021	A*	`conf`	A Central Limit Theorem for Differentially Private Query Answering. NeurIPS Jinshuo Dong, Weijie J. Su, Linjun Zhang
2021	J	`jnl`	A Central Limit Theorem for Differentially Private Query Answering. CoRR Jinshuo Dong, Weijie J. Su, Linjun Zhang
2021	J	`jnl`	A Theorem of the Alternative for Personalized Federated Learning. CoRR Shuxiao Chen, Qinqing Zheng, Qi Long, Weijie J. Su
2021	J	`jnl`	Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing. IEEE Trans. Inf. Theory Zhiqi Bu, Jason M. Klusowski, Cynthia Rush, Weijie J. Su
2021	J	`jnl`	An Unconstrained Layer-Peeled Perspective on Neural Collapse. CoRR Wenlong Ji, Yiping Lu, Yiliang Zhang, Zhun Deng, Weijie J. Su
2021	J	`jnl`	Characterizing the SLOPE Trade-off: A Variational Perspective and the Donoho-Tanner Limit. CoRR Zhiqi Bu, Jason M. Klusowski, Cynthia Rush, Weijie J. Su
2021	J	`jnl`	Differentially private false discovery rate control. J. Priv. Confidentiality Cynthia Dwork, Weijie J. Su, Li Zhang
2021	J	`jnl`	Federated $f$-Differential Privacy. CoRR Qinqing Zheng, Shuxiao Chen, Qi Long, Weijie J. Su
2021	A	`conf`	Federated f-Differential Privacy. AISTATS Qinqing Zheng, Shuxiao Chen, Qi Long, Weijie J. Su
2021	A*	`conf`	Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations. NeurIPS Jiayao Zhang, Hua Wang, Weijie J. Su
2021	J	`jnl`	Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations. CoRR Jiayao Zhang, Hua Wang, Weijie J. Su
2021	J	`jnl`	Layer-Peeled Model: Toward Understanding Well-Trained Deep Neural Networks. CoRR Cong Fang, Hangfeng He, Qi Long, Weijie J. Su
2021	J	`jnl`	Neurashed: A Phenomenological Model for Imitating Deep Learning Training. CoRR Weijie J. Su
2021	J	`jnl`	On the Convergence of Deep Learning with Differential Privacy. CoRR Zhiqi Bu, Hua Wang, Qi Long, Weijie J. Su
2021	A*	`conf`	Oneshot Differentially Private Top-k Selection. ICML Gang Qiao, Weijie J. Su, Li Zhang
2021	J	`jnl`	Oneshot Differentially Private Top-k Selection. CoRR Gang Qiao, Weijie J. Su, Li Zhang
2021	J	`jnl`	Rejoinder: Gaussian Differential Privacy. CoRR Jinshuo Dong, Aaron Roth, Weijie J. Su
2021	A*	`conf`	Toward Better Generalization Bounds with Locally Elastic Stability. ICML Zhun Deng, Hangfeng He, Weijie J. Su
2021	J	`jnl`	Weighted Training for Cross-Task Learning. CoRR Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie J. Su
2021	A*	`conf`	You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism. NeurIPS Weijie J. Su
2021	J	`jnl`	You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism. CoRR Weijie J. Su
2020	J	`jnl`	Benign Overfitting and Noisy Features. CoRR Zhu Li, Weijie J. Su, Dino Sejdinovic
2020	A*	`conf`	Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity. NeurIPS Shuxiao Chen, Hangfeng He, Weijie J. Su
2020	J	`jnl`	Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity. CoRR Shuxiao Chen, Hangfeng He, Weijie J. Su
2020	J	`jnl`	On Learning Rates and Schrödinger Operators. CoRR Bin Shi, Weijie J. Su, Michael I. Jordan
2020	J	`jnl`	Sharp Bias-variance Tradeoffs of Hard Parameter Sharing in High-dimensional Linear Regression. CoRR Hongyang R. Zhang, Fan Yang, Sen Wu, Weijie J. Su, Christopher Ré
2020	A*	`conf`	Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion. ICML Qinqing Zheng, Jinshuo Dong, Qi Long, Weijie J. Su
2020	J	`jnl`	Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion. CoRR Qinqing Zheng, Jinshuo Dong, Qi Long, Weijie J. Su
2020	A*	`conf`	The Complete Lasso Tradeoff Diagram. NeurIPS Hua Wang, Yachong Yang, Zhiqi Bu, Weijie J. Su
2020	J	`jnl`	The Complete Lasso Tradeoff Diagram. CoRR Hua Wang, Yachong Yang, Zhiqi Bu, Weijie J. Su
2020	A*	`conf`	The Local Elasticity of Neural Networks. ICLR Hangfeng He, Weijie J. Su
2020	J	`jnl`	The Price of Competition: Effect Size Heterogeneity Matters in High Dimensions. CoRR Hua Wang, Yachong Yang, Weijie J. Su
2020	J	`jnl`	Toward Better Generalization Bounds with Locally Elastic Stability. CoRR Zhun Deng, Hangfeng He, Weijie J. Su
2020	A*	`conf`	Towards Understanding the Dynamics of the First-Order Adversaries. ICML Zhun Deng, Hangfeng He, Jiaoyang Huang, Weijie J. Su
2020	J	`jnl`	Towards Understanding the Dynamics of the First-Order Adversaries. CoRR Zhun Deng, Hangfeng He, Jiaoyang Huang, Weijie J. Su
2019	A*	`conf`	Acceleration via Symplectic Discretization of High-Resolution Differential Equations. NeurIPS Bin Shi, Simon S. Du, Weijie J. Su, Michael I. Jordan
2019	J	`jnl`	Acceleration via Symplectic Discretization of High-Resolution Differential Equations. CoRR Bin Shi, Simon S. Du, Weijie J. Su, Michael I. Jordan
2019	A*	`conf`	Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing. NeurIPS Zhiqi Bu, Jason M. Klusowski, Cynthia Rush, Weijie J. Su
2019	J	`jnl`	Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing. CoRR Zhiqi Bu, Jason M. Klusowski, Cynthia Rush, Weijie J. Su
2019	J	`jnl`	Deep Learning with Gaussian Differential Privacy. CoRR Zhiqi Bu, Jinshuo Dong, Qi Long, Weijie J. Su
2019	J	`jnl`	Gaussian Differential Privacy. CoRR Jinshuo Dong, Aaron Roth, Weijie J. Su
2019	J	`jnl`	The Local Elasticity of Neural Networks. CoRR Hangfeng He, Weijie J. Su
2018	J	`jnl`	Understanding the Acceleration Phenomenon via High-Resolution Differential Equations. CoRR Bin Shi, Simon S. Du, Michael I. Jordan, Weijie J. Su