PPaperPicks

Di Wang

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

48 papers at tracked venues · 39 at CORE A* · active 2024–2026

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

Venues

ACL ×12NeurIPS ×9ICML ×5AAAI ×4EMNLP ×4ICLR ×4ECML-PKDD ×2VLDB ×2WWW ×2ICCV ×1IJCAI ×1NAACL ×1UAI ×1

Frequent coauthors

Lijie Hu
DBLP profile ↗ORCID search ↗
×5
Meng Ding
DBLP profile ↗ORCID search ↗
×3
Shu Yang
DBLP profile ↗ORCID search ↗
×2
Liangyu Wang
DBLP profile ↗ORCID search ↗
×2
Keyuan Cheng
DBLP profile ↗ORCID search ↗
×2
Lin Zhang
DBLP profile ↗ORCID search ↗
×2
Youming Tao
DBLP profile ↗ORCID search ↗
×2
Shaopeng Fu
DBLP profile ↗ORCID search ↗
×2
Liyang Zhu
DBLP profile ↗ORCID search ↗
×2
Qi Li
DBLP profile ↗ORCID search ↗
×1
Jiaye Lin
DBLP profile ↗ORCID search ↗
×1
Wenrui Zhou
DBLP profile ↗ORCID search ↗
×1

Papers

  1. AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor
    ACL 2026 ·
    Shu Yang
    DBLP profile ↗ORCID search ↗
  2. CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
    ACL 2026 ·
    Qi Li
    DBLP profile ↗ORCID search ↗
  3. Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback
    ACL 2026 ·
    Jiaye Lin
    DBLP profile ↗ORCID search ↗
  4. Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
    ACL 2026 ·
    Wenrui Zhou
    DBLP profile ↗ORCID search ↗
  5. High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing
    ACL 2026 ·
    Liangyu Wang
    DBLP profile ↗ORCID search ↗
  6. PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under a Subspace Calibration
    WWW 2026 ·
    Manjiang Yu
    DBLP profile ↗ORCID search ↗
  7. Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models
    ACL 2026 ·
    Jiayi Zhang
    DBLP profile ↗ORCID search ↗
  8. Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
    ACL 2026 ·
    Qishun Yang
    DBLP profile ↗ORCID search ↗
  9. When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models
    AAAI 2026 ·
    Keyu Wang
    DBLP profile ↗ORCID search ↗
  10. ABNet: Mitigating Sample Imbalance in Anomaly Detection Within Dynamic Graphs
    IJCAI 2025 ·
    Yifan Hong
    DBLP profile ↗ORCID search ↗
  11. CODEMENV: Benchmarking Large Language Models on Code Migration
    ACL 2025 ·
    Keyuan Cheng
    DBLP profile ↗ORCID search ↗
  12. COMPKE: Complex Question Answering under Knowledge Editing
    ACL 2025 ·
    Keyuan Cheng
    DBLP profile ↗ORCID search ↗
  13. Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation
    EMNLP 2025 ·
    Tong Li
    DBLP profile ↗ORCID search ↗
  14. Differentially Private Sparse Linear Regression with Heavy-Tailed Responses
    ECML-PKDD 2025 ·
    Xizhi Tian
    DBLP profile ↗ORCID search ↗
  15. EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
    NeurIPS 2025 ·
    Lin Zhang
    DBLP profile ↗ORCID search ↗
  16. Editable Concept Bottleneck Models
    ICML 2025 ·
    Lijie Hu
    DBLP profile ↗ORCID search ↗
  17. Fair Text-to-Image Diffusion via Fair Mapping
    AAAI 2025 ·
    Jia Li
    DBLP profile ↗ORCID search ↗
  18. Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
    ACL 2025 ·
    Shu Yang
    DBLP profile ↗ORCID search ↗
  19. Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization
    AAAI 2025 ·
    Ruijia Zhang
    DBLP profile ↗ORCID search ↗
  20. LUSTER: Link Prediction Utilizing Shared-Latent Space Representation in Multi-Layer Networks
    WWW 2025 ·
    Ruohan Yang
    DBLP profile ↗ORCID search ↗
  21. Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
    ICML 2025 ·
    Zhuoran Zhang
    DBLP profile ↗ORCID search ↗
  22. Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning
    NAACL 2025 ·
    Lin Zhang
    DBLP profile ↗ORCID search ↗
  23. Nearly Optimal Differentially Private ReLU Regression
    UAI 2025 ·
    Meng Ding
    DBLP profile ↗ORCID search ↗
  24. Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models
    AAAI 2025 ·
    Zihao Luo
    DBLP profile ↗ORCID search ↗
  25. Private Training Large-scale Models with Efficient DP-SGD
    NeurIPS 2025 ·
    Liangyu Wang
    DBLP profile ↗ORCID search ↗
  26. Second-Order Convergence in Private Stochastic Non-Convex Optimization
    NeurIPS 2025 ·
    Youming Tao
    DBLP profile ↗ORCID search ↗
  27. Semi-Supervised Concept Bottleneck Models
    ICCV 2025 ·
    Lijie Hu
    DBLP profile ↗ORCID search ↗
  28. Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
    NeurIPS 2025 ·
    Shaopeng Fu
    DBLP profile ↗ORCID search ↗
  29. Stable Vision Concept Transformers for Medical Diagnosis
    ECML-PKDD 2025 ·
    Lijie Hu
    DBLP profile ↗ORCID search ↗
  30. TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents
    NeurIPS 2025 ·
    Xiaochuan Gou
    DBLP profile ↗ORCID search ↗
  31. Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
    EMNLP 2025 ·
    Yi Su
    DBLP profile ↗ORCID search ↗
  32. Understanding the Repeat Curse in Large Language Models from a Feature Perspective
    ACL 2025 ·
    Junchi Yao
    DBLP profile ↗ORCID search ↗
  33. An LLM can Fool Itself: A Prompt-Based Adversarial Attack
    ICLR 2024 ·
    Xilie Xu
    DBLP profile ↗ORCID search ↗
  34. Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality
    ACL 2024 ·
    Jiahuan Pei
    DBLP profile ↗ORCID search ↗
  35. Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
    ICML 2024 ·
    Mudit Gaur
    DBLP profile ↗ORCID search ↗
  36. Communication Efficient and Provable Federated Unlearning
    VLDB 2024 ·
    Youming Tao
    DBLP profile ↗ORCID search ↗
  37. Dissecting Fine-Tuning Unlearning in Large Language Models
    EMNLP 2024 ·
    Yihuai Hong
    DBLP profile ↗ORCID search ↗
  38. Faithful Vision-Language Interpretation via Concept Bottleneck Models
    ICLR 2024 ·
    Songning Lai
    DBLP profile ↗ORCID search ↗
  39. Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
    ICLR 2024 ·
    Liyang Zhu
    DBLP profile ↗ORCID search ↗
  40. Improving Interpretation Faithfulness for Vision Transformers
    ICML 2024 ·
    Lijie Hu
    DBLP profile ↗ORCID search ↗
  41. Perplexity-aware Correction for Robust Alignment with Noisy Preferences
    NeurIPS 2024 ·
    Keyi Kong
    DBLP profile ↗ORCID search ↗
  42. Privacy Amplification via Shuffling: Unified, Simplified, and Tightened
    VLDB 2024 ·
    Shaowei Wang
    DBLP profile ↗ORCID search ↗
  43. Private Language Models via Truncated Laplacian Mechanism
    EMNLP 2024 ·
    Tianhao Huang
    DBLP profile ↗ORCID search ↗
  44. Revisiting Differentially Private ReLU Regression
    NeurIPS 2024 ·
    Meng Ding
    DBLP profile ↗ORCID search ↗
  45. Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
    ICLR 2024 ·
    Shaopeng Fu
    DBLP profile ↗ORCID search ↗
  46. Towards Multi-dimensional Explanation Alignment for Medical Classification
    NeurIPS 2024 ·
    Lijie Hu
    DBLP profile ↗ORCID search ↗
  47. Truthful High Dimensional Sparse Linear Regression
    NeurIPS 2024 ·
    Liyang Zhu
    DBLP profile ↗ORCID search ↗
  48. Understanding Forgetting in Continual Learning with Linear Regression
    ICML 2024 ·
    Meng Ding
    DBLP profile ↗ORCID search ↗