Xinyu Ma

Orcid: 0000-0002-5511-9370

Affiliations:
  • Baidu Inc., Beijing, China
  • Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China (PhD 2023)


According to our database1, Xinyu Ma authored at least 45 papers between 2021 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
Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models.
ACM Trans. Inf. Syst., May, 2026

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains.
CoRR, May, 2026

Cold-Starts in Generative Recommendation: A Reproducibility Study.
CoRR, March, 2026

Model Editing for New Document Integration in Generative Information Retrieval.
CoRR, March, 2026

DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent.
CoRR, March, 2026

Agentic-R: Learning to Retrieve for Agentic Search.
CoRR, January, 2026

Model Editing for New Document Integration in Generative Information Retrieval.
Proceedings of the ACM Web Conference 2026, 2026

Probe-and-Fetch: Dynamic KV Cache Pruning for Accelerated Long-Context Inference in Web-Scale AI Search.
Proceedings of the ACM Web Conference 2026, 2026

Retain to Refine: Adaptive Online Question Answering via Query Routing and Long-Short Memory.
Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1, 2026

LLM-Based Listwise Reranking Under the Effect of Positional Bias.
Proceedings of the Advances in Information Retrieval, 2026

Reinforced Efficient Reasoning via Semantically Diverse Exploration.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation.
CoRR, October, 2025

ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval.
CoRR, October, 2025

Towards AI Search Paradigm.
CoRR, June, 2025

Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation.
CoRR, January, 2025

TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy.
Proceedings of the ACM on Web Conference 2025, 2025

Replication and Exploration of Generative Retrieval over Dynamic Corpora.
Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2025

Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction.
Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2025

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

FULTR: A Large-Scale Fusion Learning to Rank Dataset and Its Application for Satisfaction-Oriented Ranking.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.2, 2025

M<sup>2</sup>oERank: Multi-Objective Mixture-of-Experts Enhanced Ranking for Satisfaction-Oriented Web Search.
Proceedings of the 41st IEEE International Conference on Data Engineering, 2025

TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

CoRanking: Collaborative Ranking with Small and Large Ranking Agents.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

The Mirage of Model Editing: Revisiting Evaluation in the Wild.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024
JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework.
CoRR, 2024

MAIR: A Massive Benchmark for Evaluating Instructed Retrieval.
CoRR, 2024

The Fall of ROME: Understanding the Collapse of LLMs in Model Editing.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

MAIR: A Massive Benchmark for Evaluating Instructed Retrieval.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023
Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers.
CoRR, 2023

Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent.
CoRR, 2023

Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Pre-training with Aspect-Content Text Mutual Prediction for Multi-Aspect Dense Retrieval.
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

2022
Pre-training Methods in Information Retrieval.
Found. Trends Inf. Retr., 2022

A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval.
CoRR, 2022

Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction.
Proceedings of the SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11, 2022

A Contrastive Pre-training Approach to Discriminative Autoencoder for Dense Retrieval.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

Scattered or Connected? An Optimized Parameter-efficient Tuning Approach for Information Retrieval.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

2021
Pre-training Methods in Information Retrieval.
CoRR, 2021

A Linguistic Study on Relevance Modeling in Information Retrieval.
Proceedings of the WWW '21: The Web Conference 2021, 2021

PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval.
Proceedings of the WSDM '21, 2021

B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval.
Proceedings of the SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021


  Loading...