PPaperPicks

Zirui Liu

University of Minnesota, Minneapolis, MN, USA

27 papers at tracked venues · 17 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0009-0004-4335-1115 ↗Google Scholar ↗Homepage ↗

Venues

EMNLP ×8ICML ×7NeurIPS ×4AAAI ×2ICLR ×2ACL ×1CVPR ×1ICDM ×1NAACL ×1

Frequent coauthors

Jiayi Yuan
DBLP profile ↗ORCID search ↗
×2
Zhimeng Jiang
DBLP profile ↗ORCID search ↗
×2
Guanchu Wang
DBLP profile ↗ORCID search ↗
×2
Zidi Xiong
DBLP profile ↗ORCID search ↗
×1
Seyyed Saeid Cheshmi
DBLP profile ↗ORCID search ↗
×1
An Luo
DBLP profile ↗ORCID search ↗
×1
Haochen Zhang
DBLP profile ↗ORCID search ↗
×1
Jiamu Zhang
DBLP profile ↗ORCID search ↗
×1
Zeru Shi
DBLP profile ↗ORCID search ↗
×1
Zihao Li
DBLP profile ↗ORCID search ↗
×1
Hongyi Liu
DBLP profile ↗ORCID search ↗
×1
Wang Yang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
    ACL 2026 ·
    Zidi Xiong
    DBLP profile ↗ORCID search ↗
  2. Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling
    EMNLP 2025 ·
    Seyyed Saeid Cheshmi
    DBLP profile ↗ORCID search ↗
  3. AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science
    EMNLP 2025 ·
    An Luo
    DBLP profile ↗ORCID search ↗
  4. Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
    NeurIPS 2025 ·
    Haochen Zhang
    DBLP profile ↗ORCID search ↗
  5. Flexible Group Count Enables Hassle-Free Structured Pruning
    CVPR 2025 ·
    Jiamu Zhang
    DBLP profile ↗ORCID search ↗
  6. From Commands to Prompts: LLM-based Semantic File System for AIOS
    ICLR 2025 ·
    Zeru Shi
    DBLP profile ↗ORCID search ↗
  7. Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
    AAAI 2025 ·
    Zihao Li
    DBLP profile ↗ORCID search ↗
  8. LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
    EMNLP 2025 ·
    Hongyi Liu
    DBLP profile ↗ORCID search ↗
  9. Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
    NeurIPS 2025 ·
    Wang Yang
    DBLP profile ↗ORCID search ↗
  10. Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
    ICML 2025 ·
    Mingyu Jin
    DBLP profile ↗ORCID search ↗
  11. Spireeval: Transforming Gameplay into Sequential Datasets for LLM Decision-Making Analysis
    ICDM 2025 ·
    Maxim Suslov
    DBLP profile ↗ORCID search ↗
  12. Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
    NeurIPS 2025 ·
    Jiayi Yuan
    DBLP profile ↗ORCID search ↗
  13. Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly
    EMNLP 2025 ·
    Wenya Xie
    DBLP profile ↗ORCID search ↗
  14. Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity
    ICLR 2025 ·
    Wentao Guo
    DBLP profile ↗ORCID search ↗
  15. Chasing Fairness in Graphs: A GNN Architecture Perspective
    AAAI 2024 ·
    Zhimeng Jiang
    DBLP profile ↗ORCID search ↗
  16. GNNs Also Deserve Editing, and They Need It More Than Once
    ICML 2024 ·
    Shaochen (Henry) Zhong
    DBLP profile ↗ORCID search ↗
  17. Gradient Rewiring for Editable Graph Neural Network Training
    NeurIPS 2024 ·
    Zhimeng Jiang
    DBLP profile ↗ORCID search ↗
  18. In Defense of Structural Sparse Adapters for Concurrent LLM Serving
    EMNLP 2024 ·
    Junda Su
    DBLP profile ↗ORCID search ↗
  19. KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
    ICML 2024 · Zirui Liu
  20. KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
    EMNLP 2024 ·
    Jiayi Yuan
    DBLP profile ↗ORCID search ↗
  21. Knowledge Graphs Can be Learned with Just Intersection Features
    ICML 2024 ·
    Duy Le
    DBLP profile ↗ORCID search ↗
  22. LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning
    ICML 2024 ·
    Hongye Jin
    DBLP profile ↗ORCID search ↗
  23. Learning to Compress Prompt in Natural Language Formats
    NAACL 2024 ·
    Yu-Neng Chuang
    DBLP profile ↗ORCID search ↗
  24. QUEST: Efficient Extreme Multi-Label Text Classification with Large Language Models on Commodity Hardware
    EMNLP 2024 ·
    Chuang Zhou
    DBLP profile ↗ORCID search ↗
  25. Soft Prompt Recovers Compressed LLMs, Transferably
    ICML 2024 ·
    Zhaozhuo Xu
    DBLP profile ↗ORCID search ↗
  26. TVE: Learning Meta-attribution for Transferable Vision Explainer
    ICML 2024 ·
    Guanchu Wang
    DBLP profile ↗ORCID search ↗
  27. Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
    EMNLP 2024 ·
    Guanchu Wang
    DBLP profile ↗ORCID search ↗