PPaperPicks

Tianyu Du

28 papers at tracked venues · 23 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×7AAAI ×6EMNLP ×4ICLR ×4ACM MM ×3ICCV ×1IJCAI ×1SIGKDD ×1WWW ×1

Frequent coauthors

Yanming Liu
DBLP profile ↗ORCID search ↗
×5
Naen Xu
DBLP profile ↗ORCID search ↗
×4
Hengyu An
DBLP profile ↗ORCID search ↗
×3
Zhou Feng
DBLP profile ↗ORCID search ↗
×2
Boyu Zhang
DBLP profile ↗ORCID search ↗
×2
Yuntai Bao
DBLP profile ↗ORCID search ↗
×2
Rui Yin
DBLP profile ↗ORCID search ↗
×1
Shuo Shi
DBLP profile ↗ORCID search ↗
×1
Yuyuan Li
DBLP profile ↗ORCID search ↗
×1
Jingxiao Yang
DBLP profile ↗ORCID search ↗
×1
Guanjie Cheng
DBLP profile ↗ORCID search ↗
×1
Zhe Ma
DBLP profile ↗ORCID search ↗
×1

Papers

  1. "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?
    ACL 2026 ·
    Naen Xu
    DBLP profile ↗ORCID search ↗
  2. ACIArena: Toward Unified Evaluation for Agent Cascading Injection
    ACL 2026 ·
    Hengyu An
    DBLP profile ↗ORCID search ↗
  3. Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?
    AAAI 2026 ·
    Naen Xu
    DBLP profile ↗ORCID search ↗
  4. Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
    ACL 2026 ·
    Rui Yin
    DBLP profile ↗ORCID search ↗
  5. DP-GenG: Differentially Private Dataset Distillation Guided by DP-Generated Data
    AAAI 2026 ·
    Shuo Shi
    DBLP profile ↗ORCID search ↗
  6. FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training
    AAAI 2026 ·
    Yuyuan Li
    DBLP profile ↗ORCID search ↗
  7. FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
    WWW 2026 ·
    Naen Xu
    DBLP profile ↗ORCID search ↗
  8. HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors
    AAAI 2026 ·
    Jingxiao Yang
    DBLP profile ↗ORCID search ↗
  9. LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping
    AAAI 2026 ·
    Guanjie Cheng
    DBLP profile ↗ORCID search ↗
  10. PerMemSafe: Benchmarking Implicit Personalized Safety of Long Horizon Self-Evolving Agents
    ACL 2026 ·
    Hengyu An
    DBLP profile ↗ORCID search ↗
  11. The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks
    SIGKDD 2026 ·
    Zhou Feng
    DBLP profile ↗ORCID search ↗
  12. An Inversion-Based Measure of Memorization for Diffusion Models
    ICCV 2025 ·
    Zhe Ma
    DBLP profile ↗ORCID search ↗
  13. Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
    ICLR 2025 ·
    Yanming Liu
    DBLP profile ↗ORCID search ↗
  14. CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
    EMNLP 2025 ·
    Boyu Zhang
    DBLP profile ↗ORCID search ↗
  15. CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
    ICLR 2025 ·
    Jiamu Zheng
    DBLP profile ↗ORCID search ↗
  16. DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
    AAAI 2025 ·
    Yanming Liu
    DBLP profile ↗ORCID search ↗
  17. Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes
    ACM MM 2025 ·
    Zhou Feng
    DBLP profile ↗ORCID search ↗
  18. IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
    EMNLP 2025 ·
    Hengyu An
    DBLP profile ↗ORCID search ↗
  19. Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
    ACL 2025 ·
    Yuntai Bao
    DBLP profile ↗ORCID search ↗
  20. Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization
    IJCAI 2025 ·
    Yuntai Bao
    DBLP profile ↗ORCID search ↗
  21. Tool-Planner: Task Planning with Clusters across Multiple Tools
    ICLR 2025 ·
    Yanming Liu
    DBLP profile ↗ORCID search ↗
  22. VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
    EMNLP 2025 ·
    Naen Xu
    DBLP profile ↗ORCID search ↗
  23. Cons2Plan: Vector Floorplan Generation from Various Conditions via a Learning Framework based on Conditional Diffusion Models
    ACM MM 2024 ·
    Shibo Hong
    DBLP profile ↗ORCID search ↗
  24. ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis
    ACL 2024 ·
    Yanming Liu
    DBLP profile ↗ORCID search ↗
  25. RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
    ACL 2024 ·
    Yanming Liu
    DBLP profile ↗ORCID search ↗
  26. ReMasker: Imputing Tabular Data with Masked Autoencoding
    ICLR 2024 · Tianyu Du
  27. SecCoder: Towards Generalizable and Robust Secure Code Generation
    EMNLP 2024 ·
    Boyu Zhang
    DBLP profile ↗ORCID search ↗
  28. TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment
    ACM MM 2024 ·
    Qinfeng Li
    DBLP profile ↗ORCID search ↗