Author

Haijin Liang

Observed name: Liang, Haijin

Institution: Tencent (China)

Observed institutions: Macau University of Science and Technology, Harbin Institute of Technology, Tencent (China), Baidu (China)

ORCID: 0009-0006-3464-9192

Observed ORCID: 0009-0006-3464-9192

OpenAlex ID: A5048582949

2020 · Xiaomin Fang, Jizhou Huang, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · 172

DuIE: A Large-Scale Chinese Dataset for Information Extraction

2019 · Shuangjie Li, Wei He, et al. · Lecture notes in computer science · 93

A Normal-Traffic Network Covert Channel

2009 · Liping Ji, Haijin Liang, et al. · International Conference on Computational Intelligence and Security (CIS) · 29

FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction

2025 · Cai, Yuxuan, Liang, Xiaozhuan, et al. · arXiv (Cornell University) · 21

TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking

2026 · Yongqi Fan, Xiaoyang Chen, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 8

Applying Large Language Model For Relevance Search In Tencent

2025 · Dezhi Ye, Jie Liu, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · 7

Beyond Closed-Pool Video Retrieval: A Benchmark and Agent Framework for Real-World Video Search and Moment Localization

2026 · Yu, Tao, Yang, Yujia, et al. · arXiv (Cornell University) · 5

Training Documents Reranker with Search Rubrics for Deep Research Agent

2026 · Liu, Wenhan, Lu, Yu, et al. · arXiv (Cornell University) · 4

VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents

2026 · Yi, Hongzhu, Yang, Yujia, et al. · arXiv (Cornell University) · 4

EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking

2026 · Enjun Du, Siyi Liu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 4

Type-enriched Hierarchical Contrastive Strategy for Fine-Grained Entity Typing

2022 · Zuo, Xinyu, Liang, Haijin, et al. · arXiv (Cornell University) · 4

Can LLMs Really Help Query Understanding In Web Search? A Practical Perspective

2025 · Dezhi Ye, Ye Qin, et al. · ACM International Conference on Information and Knowledge Management (CIKM) · 3

2022 · Bingning Wang, Feiyang Lv, et al. · ACM International Conference on Information and Knowledge Management (CIKM) · 3

Omni IIE Bench: Benchmarking the Practical Capabilities of Image Editing Models

2026 · Yang, Yujia, Wang, Yuanxiang, et al. · arXiv (Cornell University) · 2

Rank4Gen: RAG-Preference-Aligned Document Set Selection and Ranking

2026 · Yongqi Fan, Yuxiang Chu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 2

Best Practices for Distilling Large Language Models into BERT for Web Search Ranking

2024 · Ye, Dezhi, Hu, Junwei, et al. · arXiv (Cornell University) · 2

Bridging the Gap Between Training and Inference of Bayesian Controllable Language Models

2022 · Liu, Han, Wang, Bingning, et al. · arXiv (Cornell University) · 2

Learning Multimodal Embeddings with Evidence-Aligned Readout

2026 · Chen, Zirong, Ye, Fuda, et al. · arXiv (Cornell University) · 1

OPOD: On-Policy Omni Distillation

2026 · Zhao, Tong, Hu, Yuyang, et al. · arXiv (Cornell University) · 1

Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Reranking

2026 · Xiaoyang Chen, Jie Liu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 1

From Saliency to Discriminability: Rank-Preserving Visual Token Pruning for VLM Rerankers

2026 · Siyi Liu, Hanjun Yang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1

QSpell 250K: A Large-Scale, Practical Dataset for Chinese Search Query Spell Correction

2025 · Dezhi Ye, Haomei Jia, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 1

Span Confusion is All You Need for Chinese Spelling Correction

2024 · Dezhi Ye, Haomei Jia, et al. · ACM International Conference on Information and Knowledge Management (CIKM) · 1

Learn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents

2026 · Zhao, Tong, Li, Reed, et al. · arXiv (Cornell University)

UniRank: A Unified Framework for Efficient Multi-Objective LLM Ranking in Industrial Search

2026 · Dezhi Ye, Junwei Hu, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

Works count: 29

Citation count: 371

H-index: 6

I10-index: 4