Zirui Liu

Orcid: 0009-0004-4335-1115

Affiliations:
  • University of Minnesota, Minneapolis, MN, USA
  • Rice University, Houston, TX, USA (PhD 2024)
  • Texas A&M University, College Station, TX, USA (2019 - 2021)
  • Harbin Institute of Technology, School of Electrical Engineering and Automation, China (former)


According to our database1, Zirui Liu authored at least 55 papers between 2017 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
PME: pruning-based multi-size embedding for recommender systems.
Frontiers Big Data, 2024

Weighted Diversified Sampling for Efficient Data-Driven Single-Cell Gene-Gene Interaction Discovery.
CoRR, 2024

Gradient Rewiring for Editable Graph Neural Network Training.
CoRR, 2024

From Commands to Prompts: LLM-based Semantic File System for AIOS.
CoRR, 2024

Assessing and Enhancing Large Language Models in Rare Disease Question-answering.
CoRR, 2024

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity.
CoRR, 2024

Quantifying Multilingual Performance of Large Language Models Across Languages.
CoRR, 2024

LoRA-as-an-Attack! Piercing LLM Safety Under The Share-and-Play Scenario.
CoRR, 2024

FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference.
CoRR, 2024

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning.
CoRR, 2024

Learning to Compress Prompt in Natural Language Formats.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

GNNs Also Deserve Editing, and They Need It More Than Once.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Soft Prompt Recovers Compressed LLMs, Transferably.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

TVE: Learning Meta-attribution for Transferable Vision Explainer.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Knowledge Graphs Can be Learned with Just Intersection Features.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

In Defense of Structural Sparse Adapters for Concurrent LLM Serving.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

QUEST: Efficient Extreme Multi-Label Text Classification with Large Language Models on Commodity Hardware.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Chasing Fairness in Graphs: A GNN Architecture Perspective.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
DSpar: An Embarrassingly Simple Strategy for Efficient GNN training and inference via Degree-based Sparsification.
Trans. Mach. Learn. Res., 2023

Retiring ΔDP: New Distribution-Level Metrics for Demographic Parity.
Trans. Mach. Learn. Res., 2023

LETA: Learning Transferable Attribution for Generic Vision Explainer.
CoRR, 2023

Efficient GNN Explanation via Learning Removal-based Attribution.
CoRR, 2023

Editable Graph Neural Network for Node Classifications.
CoRR, 2023

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model.
CoRR, 2023

Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt.
CoRR, 2023

Efficient XAI Techniques: A Taxonomic Survey.
CoRR, 2023

Retiring $Δ$DP: New Distribution-Level Metrics for Demographic Parity.
CoRR, 2023

Adaptive Label Smoothing To Regularize Large-Scale Graph Training.
Proceedings of the 2023 SIAM International Conference on Data Mining, 2023

One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models.
Proceedings of the Sixth Conference on Machine Learning and Systems, 2023

DIVISION: Memory Efficient Training via Dual Activation Precision.
Proceedings of the International Conference on Machine Learning, 2023

RSC: Accelerate Graph Neural Networks Training via Randomized Sparse Computations.
Proceedings of the International Conference on Machine Learning, 2023

2022
RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations.
CoRR, 2022

Towards Memory Efficient Training via Dual Activation Precision.
CoRR, 2022

FMP: Toward Fair Graph Message Passing against Topology Bias.
CoRR, 2022

DreamShard: Generalizable Embedding Table Placement for Recommender Systems.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Table2Graph: Transforming Tabular Data to Unified Weighted Graph.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression.
Proceedings of the Tenth International Conference on Learning Representations, 2022

An Information Fusion Approach to Learning with Instance-Dependent Label Noise.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
The application of machine learning algorithms in predicting the length of stay following femoral neck fracture.
Int. J. Medical Informatics, 2021

Mitigating Gender Bias in Captioning Systems.
Proceedings of the WWW '21: The Web Conference 2021, 2021

DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximization.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020
Motor Speed Signature Analysis for Local Bearing Fault Detection With Noise Cancellation Based on Improved Drive Algorithm.
IEEE Trans. Ind. Electron., 2020

Towards Interaction Detection Using Topological Analysis on Neural Networks.
CoRR, 2020

Mitigating Gender Bias in Captioning Systems.
CoRR, 2020

AutoRec: An Automated Recommender System.
Proceedings of the RecSys 2020: Fourteenth ACM Conference on Recommender Systems, 2020

Detecting Interactions from Neural Networks via Topological Analysis.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2017
A novel algorithm for on-line inertia identification via adaptive recursive least squares.
Proceedings of the IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, Beijing, China, October 29, 2017


  Loading...