Xinyu Zhang

Orcid: 0009-0004-6876-3669

Affiliations:
  • Huawei, Distributed and Parallel Software Lab, Huawei Poisson Lab, Hangzhou, China
  • Renmin University of China, Beijing, China (former)


According to our database1, Xinyu Zhang authored at least 30 papers between 2017 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering.
CoRR, May, 2026

Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven.
CoRR, May, 2026

VPLight: A Reinforcement Learning Approach for Traffic Signal Control With Pedestrian Dynamics.
IEEE Trans. Knowl. Data Eng., March, 2026

HIRES: A hierarchical retrieval framework for flexible whole slide image navigation.
Expert Syst. Appl., 2026

2025
Collaborative Optimization Approach for Workflow Agents in User Behavior Modeling.
Proceedings of the Companion Proceedings of the ACM on Web Conference 2025, 2025

P3: Prompts Promote Prompting.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models.
ACM Trans. Inf. Syst., September, 2024

2023
Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection.
CoRR, 2023

WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus.
CoRR, 2023

Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Rethinking Label Smoothing on Multi-Hop Question Answering.
Proceedings of the Chinese Computational Linguistics - 22nd China National Conference, 2023

Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning.
Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022
Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?
CoRR, 2022

KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models.
CoRR, 2022

Webformer: Pre-training with Web Pages for Information Retrieval.
Proceedings of the SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11, 2022

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline.
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

Triple-Fact Retriever: An explainable reasoning retrieval model for multi-hop QA problem.
Proceedings of the 38th IEEE International Conference on Data Engineering, 2022

Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding.
Proceedings of the 29th International Conference on Computational Linguistics, 2022

From Easy to Hard: A Dual Curriculum Learning Framework for Context-Aware Document Ranking.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

2021
Towards More Effective and Economic Sparsely-Activated Model.
CoRR, 2021

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline.
CoRR, 2021

YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker.
CoRR, 2021

Early Exiting with Ensemble Internal Classifiers.
CoRR, 2021

Emotion Eliciting Machine: Emotion Eliciting Conversation Generation based on Dual Generator.
CoRR, 2021

Answer Complex Questions: Path Ranker Is All You Need.
Proceedings of the SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021

Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need.
Proceedings of the CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1, 2021

Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking.
Proceedings of the CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1, 2021

2017
RUCIR at the NTCIR-13 STC-2 Task.
Proceedings of the 13th NTCIR Conference, 2017


  Loading...