关于我

我现以青云计划加入腾讯。此前在中国科学技术大学计算机科学与技术学院攻读博士，师从陈恩红教授，并在认知智能国家重点实验室开展研究。我的研究聚焦信息检索、高效表征学习与检索增强生成；近年来在 TOIS、KDD、WWW、ACL、ICLR、EMNLP、AAAI、ACM MM 等期刊和会议发表或接收论文 20 余篇，并申请或获授权国家发明专利 5 项。曾获博士研究生国家奖学金、杨元庆奖学金、苏州工业园区奖学金、CCFAI 2025 最佳学生论文奖，以及 2025 年腾讯犀牛鸟精英人才计划优秀学生奖。

ICLR 2026

ChronoPlay diagram showing game knowledge evolution and user interest drift

查看论文

ICLR2026

ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks

Liyang He, Yuren Zhang, Ziwei Zhu, Zhenghui Li, Shiwei Tong

论文代码

ACL 2025

Ranking sentences generation diagram with directionally controlled semantic examples

查看论文

ACL2025

Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models

Liyang He, Chenglong Liu, Rui Li, Zhenya Huang, Shulan Ruan, Jun Zhou, Enhong Chen

论文代码

ACM MM 2024

One-bit Deep Hashing architecture with adaptive hash centers and two-stage training

查看论文

ACM MM2024

One-bit Deep Hashing: Towards Resource-Efficient Hashing Model with Binary Neural Network

Liyang He, Zhenya Huang, Chenglong Liu, Rui Li, Runze Wu, Qi Liu, Enhong Chen

论文

WWW 2024

BRCD framework illustrating structural and individual retrieval knowledge distillation

查看论文

WWW2024

Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing

Liyang He, Zhenya Huang, Jiayu Liu, Enhong Chen, Fei Wang, Jing Sha, Shijin Wang

论文代码

TOIS 2023

SMASH semantic hashing model with relevance propagation and external memory

查看论文

TOIS2023

An Efficient and Robust Semantic Hashing Framework for Similar Text Search

Liyang He, Zhenya Huang, Enhong Chen, Qi Liu, Shiwei Tong, Hao Wang, Defu Lian, Shijin Wang

论文代码

2026KDD

已接收

Find tailored step example for next step: A Targeted Step-wise Retrieval Framework for Guiding LLM Reasoning

Cheng Yang, Zhenya Huang, Liyang He, Weibo Gao, Wei Huang, Tong Wei, Xin Li

2026ECCV

已接收

CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation

Chenglong Liu, Xin Zhang, Yimeng Zhu, Liyang He, Yixiao Ma, Yu Su, Zhenya Huang, Qi Liu

2026AAAI

From Diagnosis to Generalization: A Cognitive Approach to Data Selection for Educational LLMs

Yuxiang Guo, Yan Zhuang, Qi Liu, Zhenya Huang, Xianquan Wang, Liyang He, Jiatong Li, Rui Li, Shijin Wang

论文 ↗ 代码 ↗

2025ACL

UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation

Rui Li, Liyang He, Qi Liu, Zheng Zhang, Heng Yu, Yuyang Ye, Linbo Zhu, Yu Su

论文 ↗

2025ACL Findings

CA-GAR: Context-Aware Alignment of LLM Generation for Document Retrieval

Heng Yu, Junfeng Kang, Rui Li, Qi Liu, Liyang He, Zhenya Huang, Shuanghong Shen, Junyu Lu

论文 ↗

2025KDD

MGS3: A Multi-Granularity Self-Supervised Code Search Framework

Rui Li, Junfeng Kang, Qi Liu, Liyang He, Zheng Zhang, Yunhao Sha, Linbo Zhu, Zhenya Huang

论文 ↗

2025COLING

Multi-perspective Preference Alignment of LLMs for Programming-Community Question Answering

Hongyu Yang, Jiahui Hou, Liyang He, Rui Li

论文 ↗

2024KDD Workshop

A Simple yet Effective Retrieval-Augmented Generation Framework for the Meta KDD Cup 2024

Liyang He, Rui Li, Shuanghong Shen, Junyu Lu, Linbo Zhu, Yu Su, Zhenya Huang

论文 ↗ 代码 ↗

2024EMNLP

Optimizing Code Retrieval: High-Quality and Scalable Dataset Annotation through Large Language Models

Rui Li, Qi Liu, Liyang He, Zheng Zhang, Hao Zhang, Shengyu Ye, Junyu Lu, Zhenya Huang

论文 ↗

2024AAAI

CONSIDER: Commonalities and Specialties Driven Multilingual Code Retrieval Framework

Rui Li, Liyang He, Qi Liu, Yuze Zhao, Zheng Zhang, Zhenya Huang, Yu Su, Shijin Wang

论文 ↗ 代码 ↗

何理扬

关于我

代表性论文

ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks

Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models

One-bit Deep Hashing: Towards Resource-Efficient Hashing Model with Binary Neural Network

Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing

An Efficient and Robust Semantic Hashing Framework for Similar Text Search

其他论文

Find tailored step example for next step: A Targeted Step-wise Retrieval Framework for Guiding LLM Reasoning

CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation

From Diagnosis to Generalization: A Cognitive Approach to Data Selection for Educational LLMs

UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation

CA-GAR: Context-Aware Alignment of LLM Generation for Document Retrieval

MGS3: A Multi-Granularity Self-Supervised Code Search Framework

Multi-perspective Preference Alignment of LLMs for Programming-Community Question Answering

A Simple yet Effective Retrieval-Augmented Generation Framework for the Meta KDD Cup 2024

Optimizing Code Retrieval: High-Quality and Scalable Dataset Annotation through Large Language Models

CONSIDER: Commonalities and Specialties Driven Multilingual Code Retrieval Framework