PPaperPicks

Dongsheng Li

National University of Defense Technology, College of Computer, Changsha, China

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

DBLP profile ↗ORCID 0000-0001-9743-2034 ↗Homepage ↗

Venues

ACL ×11ICDE ×4EMNLP ×3NeurIPS ×3WWW ×3AAAI ×2IJCAI ×1

Frequent coauthors

Zhouyang Liu
DBLP profile ↗ORCID search ↗
×3
Shilong Pan
DBLP profile ↗ORCID search ↗
×3
Zhihua Wen
DBLP profile ↗ORCID search ↗
×2
Xiaoge Deng
DBLP profile ↗ORCID search ↗
×2
Baihui Liu
DBLP profile ↗ORCID search ↗
×1
Tianlun Liu
DBLP profile ↗ORCID search ↗
×1
Tianle Liu
DBLP profile ↗ORCID search ↗
×1
Hongyan Wu
DBLP profile ↗ORCID search ↗
×1
Kaiyuan Tian
DBLP profile ↗ORCID search ↗
×1
Xinyue Fang
DBLP profile ↗ORCID search ↗
×1
Zhizhao Liu
DBLP profile ↗ORCID search ↗
×1
Qiunan Du
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
    ACL 2026 ·
    Baihui Liu
    DBLP profile ↗ORCID search ↗
  2. CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher
    ACL 2026 ·
    Tianlun Liu
    DBLP profile ↗ORCID search ↗
  3. DMHM: Density-aware Manifold Learning and Hybrid Mahalanobis Energy for LLMs-generated Text Detection
    ACL 2026 ·
    Tianle Liu
    DBLP profile ↗ORCID search ↗
  4. Emotion Trajectory-aware Retrieval for Markov-driven Emotion Anticipation in LLM-based Emotional Support Conversation
    ACL 2026 ·
    Hongyan Wu
    DBLP profile ↗ORCID search ↗
  5. GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning
    ACL 2026 ·
    Kaiyuan Tian
    DBLP profile ↗ORCID search ↗
  6. Graph2Region: Efficient Graph Similarity Learning With Structure and Scale Restoration (Extended Abstract)
    ICDE 2026 ·
    Zhouyang Liu
    DBLP profile ↗ORCID search ↗
  7. Hierarchy-Aware Neural Subgraph Matching with Enhanced Similarity Measure (Extended Abstract)
    ICDE 2026 ·
    Zhouyang Liu
    DBLP profile ↗ORCID search ↗
  8. Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs' Hallucinations
    ACL 2026 ·
    Xinyue Fang
    DBLP profile ↗ORCID search ↗
  9. Rethinking Flexible Graph Similarity Computation: One-Step Alignment with Global Guidance
    ICDE 2026 ·
    Zhouyang Liu
    DBLP profile ↗ORCID search ↗
  10. Rethinking the Hidden Risk of Reranking: Achieving Risk-aware Reranking with Information Gain for RAG with LLMs
    WWW 2026 ·
    Zhizhao Liu
    DBLP profile ↗ORCID search ↗
  11. WALKSAFE: Risk-aware Graph Random Walk with Bi-GRPO for LLM Safety
    AAAI 2026 ·
    Shilong Pan
    DBLP profile ↗ORCID search ↗
  12. AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models
    ACL 2025 ·
    Shilong Pan
    DBLP profile ↗ORCID search ↗
  13. Correlation-Aware Example Selection for In-Context Learning with Nonsymmetric Determinantal Point Processes
    EMNLP 2025 ·
    Qiunan Du
    DBLP profile ↗ORCID search ↗
  14. DPGA-TextSyn: Differentially Private Genetic Algorithm for Synthetic Text Generation
    ACL 2025 ·
    Zhonghao Sun
    DBLP profile ↗ORCID search ↗
  15. DYNTEXT: Semantic-Aware Dynamic Text Sanitization for Privacy-Preserving LLM Inference
    ACL 2025 ·
    Juhua Zhang
    DBLP profile ↗ORCID search ↗
  16. GCML: Gradient Coherence Guided Meta-Learning for Cross-Domain Emerging Topic Rumor Detection
    EMNLP 2025 ·
    Zejiang He
    DBLP profile ↗ORCID search ↗
  17. Hippocampal-like Sequential Editing for Continual Knowledge Updates in Large Language Models
    NeurIPS 2025 ·
    Quntian Fang
    DBLP profile ↗ORCID search ↗
  18. Scenario-independent Uncertainty Estimation for LLM-based Question Answering via Factor Analysis
    WWW 2025 ·
    Zhihua Wen
    DBLP profile ↗ORCID search ↗
  19. Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery
    AAAI 2024 ·
    Zimian Wei
    DBLP profile ↗ORCID search ↗
  20. Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models
    EMNLP 2024 ·
    Yuxuan Guo
    DBLP profile ↗ORCID search ↗
  21. Exploring the Inefficiency of Heavy Ball as Momentum Parameter Approaches 1
    IJCAI 2024 ·
    Xiaoge Deng
    DBLP profile ↗ORCID search ↗
  22. Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning (Extended Abstract)
    ICDE 2024 ·
    Ning Liu
    DBLP profile ↗ORCID search ↗
  23. LFDe: A Lighter, Faster and More Data-Efficient Pre-training Framework for Event Extraction
    WWW 2024 ·
    Zhigang Kan
    DBLP profile ↗ORCID search ↗
  24. POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation
    ACL 2024 ·
    Shilong Pan
    DBLP profile ↗ORCID search ↗
  25. Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering
    NeurIPS 2024 ·
    Zhihua Wen
    DBLP profile ↗ORCID search ↗
  26. Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
    NeurIPS 2024 ·
    Xiaoge Deng
    DBLP profile ↗ORCID search ↗
  27. Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models
    ACL 2024 ·
    Yifu Gao
    DBLP profile ↗ORCID search ↗