Ziqian Zeng

Venues

Frequent coauthors

Papers

1. Activation-Guided Local Editing for Jailbreaking Attacks
   ACL 2026 ·

   Jiecong Wang

   DBLP profile ↗ORCID search ↗
2. MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning
   ACL 2026 ·

   Tao Zhang

   DBLP profile ↗ORCID search ↗
3. Neural Architecture for Fast and Reliable Coagulation Assessment in Clinical Settings: Leveraging Thromboelastography
   AAAI 2026 ·

   Yulu Wang

   DBLP profile ↗ORCID search ↗
4. Preserving Language Capabilities in Vision-Language Models via Representation Regulation
   ACL 2026 ·

   Zixuan Chen

   DBLP profile ↗ORCID search ↗
5. RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior
   AAAI 2026 ·

   Junyao Yang

   DBLP profile ↗ORCID search ↗
6. AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models
   CVPR 2025 ·

   Run He

   DBLP profile ↗ORCID search ↗
7. Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
   EMNLP 2025 ·

   Wenbin Hu

   DBLP profile ↗ORCID search ↗
8. DrFrattn: Directly Learn Adaptive Policy from Attention for Simultaneous Machine Translation
   EMNLP 2025 ·

   Libo Zhao

   DBLP profile ↗ORCID search ↗
9. GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
   ACL 2025 ·

   Tao Zhang

   DBLP profile ↗ORCID search ↗
10. L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
    ICML 2025 ·

    Xiang Zhang

    DBLP profile ↗ORCID search ↗
11. PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration
    ACL 2025 · Ziqian Zeng
12. RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis
    EMNLP 2025 ·

    Jianwei Wang

    DBLP profile ↗ORCID search ↗
13. SDD: Self-Degraded Defense against Malicious Fine-tuning
    ACL 2025 ·

    Zixuan Chen

    DBLP profile ↗ORCID search ↗
14. SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings
    ACL 2025 ·

    Weikai Lu

    DBLP profile ↗ORCID search ↗
15. Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
    ICML 2025 ·

    Run He

    DBLP profile ↗ORCID search ↗
16. ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference
    AAAI 2024 · Ziqian Zeng
17. DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning
    AAAI 2024 ·

    Huiping Zhuang

    DBLP profile ↗ORCID search ↗
18. Dissecting Fine-Tuning Unlearning in Large Language Models
    EMNLP 2024 ·

    Yihuai Hong

    DBLP profile ↗ORCID search ↗
19. F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
    NeurIPS 2024 ·

    Huiping Zhuang

    DBLP profile ↗ORCID search ↗
20. GACL: Exemplar-Free Generalized Analytic Continual Learning
    NeurIPS 2024 ·

    Huiping Zhuang

    DBLP profile ↗ORCID search ↗
21. PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation
    EMNLP 2024 ·

    Libo Zhao

    DBLP profile ↗ORCID search ↗
22. Zero-shot Explainable Mental Health Analysis on Social Media by Incorporating Mental Scales
    WWW 2024 ·

    Wenyu Li

    DBLP profile ↗ORCID search ↗