PPaperPicks

Di Wang

King Abdullah University of Science and Technology (KAUST), Saudi Arabia

53 papers at tracked venues · 44 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-4908-0243 ↗Homepage ↗

Venues

ACL ×12NeurIPS ×9ICML ×5AAAI ×4EMNLP ×4ICLR ×4USENIX Security ×3ECML-PKDD ×2VLDB ×2WWW ×2ICCV ×1IJCAI ×1NAACL ×1NDSS ×1S&P ×1UAI ×1

Frequent coauthors

Lijie Hu
×21
Shu Yang
×11
Jingfeng Zhang
×8
Zihang Xiang
×7
Meng Ding
×7
Jinhui Xu
×6
Cheng-Long Wang
×5
Mengdi Li
×4
Zhuoran Zhang
×4
Muhammad Asif Ali
×4
Shaowei Wang
×4
Tianhao Wang
×3

Papers

  1. AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor
    ACL 2026 ·
    Shu Yang
    ,
    Jingyu Hu
    ,
    Tong Li
    ,
    Hanqi Yan
    ,
    Wenxuan Wang
    , Di Wang
  2. CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
    ACL 2026 ·
    Qi Li
    ,
    Cheng-Long Wang
    ,
    Yinzhi Cao
    , Di Wang
  3. Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback
    ACL 2026 ·
    Jiaye Lin
    ,
    Mengdi Li
    ,
    Xufeng Zhao
    ,
    Wenhao Lu
    ,
    Peilin Zhao
    ,
    Stefan Wermter
    , Di Wang
  4. Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
    ACL 2026 ·
    Wenrui Zhou
    ,
    Mohamed Hendy
    ,
    Shu Yang
    ,
    Qingsong Yang
    ,
    Zikun Guo
    ,
    Yuyu Luo
    ,
    Lijie Hu
    , Di Wang
  5. High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing
    ACL 2026 ·
    Liangyu Wang
    ,
    Huanyi Xie
    , Di Wang
  6. PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under a Subspace Calibration
    WWW 2026 ·
    Manjiang Yu
    ,
    Hongji Li
    ,
    Priyanka Singh
    ,
    Xue Li
    , Di Wang,
    Lijie Hu
  7. Revisiting Differentially Private Hyper-parameter Tuning
    NDSS 2026 ·
    Zihang Xiang
    ,
    Tianhao Wang
    ,
    Cheng-Long Wang
    , Di Wang
  8. Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models
    ACL 2026 ·
    Jiayi Zhang
    ,
    Shu Yang
    ,
    Junchao Wu
    ,
    Derek F. Wong
    , Di Wang
  9. Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
    ACL 2026 ·
    Qishun Yang
    ,
    Shu Yang
    ,
    Lijie Hu
    , Di Wang
  10. When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models
    AAAI 2026 ·
    Keyu Wang
    ,
    Jin Li
    ,
    Shu Yang
    ,
    Zhuoran Zhang
    , Di Wang
  11. ABNet: Mitigating Sample Imbalance in Anomaly Detection Within Dynamic Graphs
    IJCAI 2025 ·
    Yifan Hong
    ,
    Muhammad Asif Ali
    ,
    Huan Wang
    ,
    Junyang Chen
    , Di Wang
  12. Beyond Statistical Estimation: Differentially Private Individual Computation via Shuffling
    USENIX Security 2025 ·
    Shaowei Wang
    ,
    Changyu Dong
    ,
    Xiangfu Song
    ,
    Jin Li
    ,
    Zhili Zhou
    , Di Wang,
    Han Wu
  13. CODEMENV: Benchmarking Large Language Models on Code Migration
    ACL 2025 ·
    Keyuan Cheng
    ,
    Xudong Shen
    ,
    Yihao Yang
    ,
    TengyueWang TengyueWang
    ,
    Yang Cao
    ,
    Muhammad Asif Ali
    ,
    Hanbin Wang
    ,
    Lijie Hu
    , Di Wang
  14. COMPKE: Complex Question Answering under Knowledge Editing
    ACL 2025 ·
    Keyuan Cheng
    ,
    Zijian Kan
    ,
    Zhuoran Zhang
    ,
    Muhammad Asif Ali
    ,
    Lijie Hu
    , Di Wang
  15. Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation
    EMNLP 2025 ·
    Tong Li
    ,
    Shu Yang
    ,
    Junchao Wu
    ,
    Jiyao Wei
    ,
    Lijie Hu
    ,
    Mengdi Li
    ,
    Derek F. Wong
    ,
    Joshua R. Oltmanns
    , Di Wang
  16. Differentially Private Sparse Linear Regression with Heavy-Tailed Responses
    ECML-PKDD 2025 ·
    Xizhi Tian
    ,
    Meng Ding
    ,
    Touming Tao
    ,
    Zihang Xiang
    , Di Wang
  17. EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
    NeurIPS 2025 ·
    Lin Zhang
    ,
    Wenshuo Dong
    ,
    Zhuoran Zhang
    ,
    Shu Yang
    ,
    Lijie Hu
    ,
    Ninghao Liu
    ,
    Pan Zhou
    , Di Wang
  18. Editable Concept Bottleneck Models
    ICML 2025 ·
    Lijie Hu
    ,
    Chenyang Ren
    ,
    Zhengyu Hu
    ,
    Hongbin Lin
    ,
    Cheng-Long Wang
    ,
    Zhen Tan
    ,
    Weimin Lyu
    ,
    Jingfeng Zhang
    ,
    Hui Xiong
    , Di Wang
  19. Fair Text-to-Image Diffusion via Fair Mapping
    AAAI 2025 ·
    Jia Li
    ,
    Lijie Hu
    ,
    Jingfeng Zhang
    ,
    Tianhang Zheng
    ,
    Hua Zhang
    , Di Wang
  20. Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
    ACL 2025 ·
    Shu Yang
    ,
    Shenzhe Zhu
    ,
    Zeyu Wu
    ,
    Keyu Wang
    ,
    Junchi Yao
    ,
    Junchao Wu
    ,
    Lijie Hu
    ,
    Mengdi Li
    ,
    Derek F. Wong
    , Di Wang
  21. Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization
    AAAI 2025 ·
    Ruijia Zhang
    ,
    Mingxi Lei
    ,
    Meng Ding
    ,
    Zihang Xiang
    ,
    Jinhui Xu
    , Di Wang
  22. LUSTER: Link Prediction Utilizing Shared-Latent Space Representation in Multi-Layer Networks
    WWW 2025 ·
    Ruohan Yang
    ,
    Muhammad Asif Ali
    ,
    Huan Wang
    ,
    Junyang Chen
    , Di Wang
  23. Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
    ICML 2025 ·
    Zhuoran Zhang
    ,
    Yongxiang Li
    ,
    Zijian Kan
    ,
    Keyuan Cheng
    ,
    Lijie Hu
    , Di Wang
  24. Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning
    NAACL 2025 ·
    Lin Zhang
    ,
    Lijie Hu
    , Di Wang
  25. Nearly Optimal Differentially Private ReLU Regression
    UAI 2025 ·
    Meng Ding
    ,
    Mingxi Lei
    ,
    Shaowei Wang
    ,
    Tianhang Zheng
    , Di Wang,
    Jinhui Xu
  26. Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run
    USENIX Security 2025 ·
    Zihang Xiang
    ,
    Tianhao Wang
    , Di Wang
  27. Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models
    AAAI 2025 ·
    Zihao Luo
    ,
    Xilie Xu
    ,
    Feng Liu
    ,
    Yun Sing Koh
    , Di Wang,
    Jingfeng Zhang
  28. Private Training Large-scale Models with Efficient DP-SGD
    NeurIPS 2025 ·
    Liangyu Wang
    ,
    Junxiao Wang
    ,
    Jie Ren
    ,
    Zihang Xiang
    ,
    David E. Keyes
    , Di Wang
  29. Second-Order Convergence in Private Stochastic Non-Convex Optimization
    NeurIPS 2025 ·
    Youming Tao
    ,
    Zuyuan Zhang
    ,
    Dongxiao Yu
    ,
    Xiuzhen Cheng
    ,
    Falko Dressler
    , Di Wang
  30. Semi-Supervised Concept Bottleneck Models
    ICCV 2025 ·
    Lijie Hu
    ,
    Tianhao Huang
    ,
    Huanyi Xie
    ,
    Xilin Gong
    ,
    Chenyang Ren
    ,
    Zhengyu Hu
    ,
    Lu Yu
    ,
    Ping Ma
    , Di Wang
  31. Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
    NeurIPS 2025 ·
    Shaopeng Fu
    ,
    Liang Ding
    ,
    Jingfeng Zhang
    , Di Wang
  32. Stable Vision Concept Transformers for Medical Diagnosis
    ECML-PKDD 2025 ·
    Lijie Hu
    ,
    Songning Lai
    ,
    Yuan Hua
    ,
    Shu Yang
    ,
    Jingfeng Zhang
    , Di Wang
  33. Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
    USENIX Security 2025 ·
    Cheng-Long Wang
    ,
    Qi Li
    ,
    Zihang Xiang
    ,
    Yinzhi Cao
    , Di Wang
  34. TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents
    NeurIPS 2025 ·
    Xiaochuan Gou
    ,
    Ziyue Li
    ,
    Tian Lan
    ,
    Junpeng Lin
    ,
    Zhishuai Li
    ,
    Bingyu Zhao
    ,
    Chen Zhang
    , Di Wang,
    Xiangliang Zhang
  35. Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
    EMNLP 2025 ·
    Yi Su
    ,
    Jiayi Zhang
    ,
    Shu Yang
    ,
    Xinhai Wang
    ,
    Lijie Hu
    , Di Wang
  36. Understanding the Repeat Curse in Large Language Models from a Feature Perspective
    ACL 2025 ·
    Junchi Yao
    ,
    Shu Yang
    ,
    Jianhua Xu
    ,
    Lijie Hu
    ,
    Mengdi Li
    , Di Wang
  37. An LLM can Fool Itself: A Prompt-Based Adversarial Attack
    ICLR 2024 ·
    Xilie Xu
    ,
    Keyi Kong
    ,
    Ning Liu
    ,
    Lizhen Cui
    , Di Wang,
    Jingfeng Zhang
    ,
    Mohan S. Kankanhalli
  38. Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality
    ACL 2024 ·
    Jiahuan Pei
    ,
    Irene Viola
    ,
    Haochen Huang
    ,
    Junxiao Wang
    ,
    Moonisa Ahsan
    ,
    Fanghua Ye
    ,
    Yiming Jiang
    ,
    Yao Sai
    , Di Wang,
    Zhumin Chen
    ,
    Pengjie Ren
    ,
    Pablo César
  39. Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
    ICML 2024 ·
    Mudit Gaur
    ,
    Amrit S. Bedi
    , Di Wang,
    Vaneet Aggarwal
  40. Communication Efficient and Provable Federated Unlearning
    VLDB 2024 ·
    Youming Tao
    ,
    Cheng-Long Wang
    ,
    Miao Pan
    ,
    Dongxiao Yu
    ,
    Xiuzhen Cheng
    , Di Wang
  41. Dissecting Fine-Tuning Unlearning in Large Language Models
    EMNLP 2024 ·
    Yihuai Hong
    ,
    Yuelin Zou
    ,
    Lijie Hu
    ,
    Ziqian Zeng
    , Di Wang,
    Haiqin Yang
  42. Faithful Vision-Language Interpretation via Concept Bottleneck Models
    ICLR 2024 ·
    Songning Lai
    ,
    Lijie Hu
    ,
    Junxiao Wang
    ,
    Laure Berti-Équille
    , Di Wang
  43. Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
    ICLR 2024 ·
    Liyang Zhu
    ,
    Meng Ding
    ,
    Vaneet Aggarwal
    ,
    Jinhui Xu
    , Di Wang
  44. Improving Interpretation Faithfulness for Vision Transformers
    ICML 2024 ·
    Lijie Hu
    ,
    Yixin Liu
    ,
    Ninghao Liu
    ,
    Mengdi Huai
    ,
    Lichao Sun
    , Di Wang
  45. Perplexity-aware Correction for Robust Alignment with Noisy Preferences
    NeurIPS 2024 ·
    Keyi Kong
    ,
    Xilie Xu
    , Di Wang,
    Jingfeng Zhang
    ,
    Mohan S. Kankanhalli
  46. Preserving Node-level Privacy in Graph Neural Networks
    S&P 2024 ·
    Zihang Xiang
    ,
    Tianhao Wang
    , Di Wang
  47. Privacy Amplification via Shuffling: Unified, Simplified, and Tightened
    VLDB 2024 ·
    Shaowei Wang
    ,
    Yun Peng
    ,
    Jin Li
    ,
    Zikai Wen
    ,
    Zhipeng Li
    ,
    Shiyu Yu
    , Di Wang,
    Wei Yang
  48. Private Language Models via Truncated Laplacian Mechanism
    EMNLP 2024 ·
    Tianhao Huang
    ,
    Tao Yang
    ,
    Ivan Habernal
    ,
    Lijie Hu
    , Di Wang
  49. Revisiting Differentially Private ReLU Regression
    NeurIPS 2024 ·
    Meng Ding
    ,
    Mingxi Lei
    ,
    Liyang Zhu
    ,
    Shaowei Wang
    , Di Wang,
    Jinhui Xu
  50. Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
    ICLR 2024 ·
    Shaopeng Fu
    , Di Wang
  51. Towards Multi-dimensional Explanation Alignment for Medical Classification
    NeurIPS 2024 ·
    Lijie Hu
    ,
    Songning Lai
    ,
    Wenshuo Chen
    ,
    Hongru Xiao
    ,
    Hongbin Lin
    ,
    Lu Yu
    ,
    Jingfeng Zhang
    , Di Wang
  52. Truthful High Dimensional Sparse Linear Regression
    NeurIPS 2024 ·
    Liyang Zhu
    ,
    Amina Manseur
    ,
    Meng Ding
    ,
    Jinyan Liu
    ,
    Jinhui Xu
    , Di Wang
  53. Understanding Forgetting in Continual Learning with Linear Regression
    ICML 2024 ·
    Meng Ding
    ,
    Kaiyi Ji
    , Di Wang,
    Jinhui Xu