PPaperPicks

Kaidi Xu

29 papers at tracked venues · 20 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×4CVPR ×4AAAI ×3EMNLP ×3ICML ×3NAACL ×3ACM MM ×2NeurIPS ×2EACL ×1ECCV ×1ICCV ×1ICLR ×1RSS ×1

Frequent coauthors

Jinhao Duan
DBLP profile ↗ORCID search ↗
×5
Zhiyuan Wang
DBLP profile ↗ORCID search ↗
×3
Hao Cheng
DBLP profile ↗ORCID search ↗
×3
Fei Kong
DBLP profile ↗ORCID search ↗
×2
Zijie Liu
DBLP profile ↗ORCID search ↗
×1
Haozhi Fan
DBLP profile ↗ORCID search ↗
×1
Xiaoyun Zhang
DBLP profile ↗ORCID search ↗
×1
Pucheng Dang
DBLP profile ↗ORCID search ↗
×1
Wenhao Hu
DBLP profile ↗ORCID search ↗
×1
Shrey Pandit
DBLP profile ↗ORCID search ↗
×1
Xu Zhang
DBLP profile ↗ORCID search ↗
×1
Zhuoxuan Zhang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees
    AAAI 2026 ·
    Zhiyuan Wang
    DBLP profile ↗ORCID search ↗
  2. Dialogue is Better Than Monologue: Instructing Meidcal LLMs via Strategic Conversations
    EACL 2026 ·
    Zijie Liu
    DBLP profile ↗ORCID search ↗
  3. IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation
    ACL 2026 ·
    Haozhi Fan
    DBLP profile ↗ORCID search ↗
  4. Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
    AAAI 2026 ·
    Xiaoyun Zhang
    DBLP profile ↗ORCID search ↗
  5. DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization
    NAACL 2025 ·
    Pucheng Dang
    DBLP profile ↗ORCID search ↗
  6. DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation
    ACL 2025 ·
    Wenhao Hu
    DBLP profile ↗ORCID search ↗
  7. GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing
    NAACL 2025 ·
    Jinhao Duan
    DBLP profile ↗ORCID search ↗
  8. MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models
    EMNLP 2025 ·
    Shrey Pandit
    DBLP profile ↗ORCID search ↗
  9. Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models
    CVPR 2025 ·
    Hao Cheng
    DBLP profile ↗ORCID search ↗
  10. Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
    ICML 2025 ·
    Xu Zhang
    DBLP profile ↗ORCID search ↗
  11. SConU: Selective Conformal Uncertainty in Large Language Models
    ACL 2025 ·
    Zhiyuan Wang
    DBLP profile ↗ORCID search ↗
  12. Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
    EMNLP 2025 ·
    Zhuoxuan Zhang
    DBLP profile ↗ORCID search ↗
  13. Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models
    ACM MM 2025 ·
    Hao Cheng
    DBLP profile ↗ORCID search ↗
  14. TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination via Latent Truthful-Guided Pre-Intervention
    ICCV 2025 ·
    Jinhao Duan
    DBLP profile ↗ORCID search ↗
  15. ACT-Diffusion: Efficient Adversarial Consistency Training for One-Step Diffusion Models
    CVPR 2024 ·
    Fei Kong
    DBLP profile ↗ORCID search ↗
  16. An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
    ICLR 2024 ·
    Fei Kong
    DBLP profile ↗ORCID search ↗
  17. Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
    CVPR 2024 ·
    Zhengyue Zhao
    DBLP profile ↗ORCID search ↗
  18. Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation
    ACM MM 2024 ·
    Jin Sun
    DBLP profile ↗ORCID search ↗
  19. ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees
    EMNLP 2024 ·
    Zhiyuan Wang
    DBLP profile ↗ORCID search ↗
  20. Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
    ICML 2024 ·
    Junyuan Hong
    DBLP profile ↗ORCID search ↗
  21. Dynamic Adversarial Attacks on Autonomous Driving Systems
    RSS 2024 ·
    Amirhosein Chahe
    DBLP profile ↗ORCID search ↗
  22. E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data
    CVPR 2024 ·
    Aref Azizpour
    DBLP profile ↗ORCID search ↗
  23. GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations
    NeurIPS 2024 ·
    Jinhao Duan
    DBLP profile ↗ORCID search ↗
  24. NN4SysBench: Characterizing Neural Network Verification for Computer Systems
    NeurIPS 2024 ·
    Shuyi Lin
    DBLP profile ↗ORCID search ↗
  25. Position: TrustLLM: Trustworthiness in Large Language Models
    ICML 2024 ·
    Yue Huang
    DBLP profile ↗ORCID search ↗
  26. ReTA: Recursively Thinking Ahead to Improve the Strategic Reasoning of Large Language Models
    NAACL 2024 ·
    Jinhao Duan
    DBLP profile ↗ORCID search ↗
  27. Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
    ACL 2024 ·
    Jinhao Duan
    DBLP profile ↗ORCID search ↗
  28. Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise
    AAAI 2024 ·
    Yixin Liu
    DBLP profile ↗ORCID search ↗
  29. Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Models
    ECCV 2024 ·
    Hao Cheng
    DBLP profile ↗ORCID search ↗