Kaixin Wu

20 papers A* 2A 1B 1Journal 7Unranked 9
YearRankTypeTitle / Venue / Authors
2026 — conf
GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection.
EACL (Volume 1: Long Papers)
Kai Yao, Zhenghan Song, Kaixin Wu, Mingjie Zhong, Danzhao Cheng, Zhaorui Tan, Yixin Ji, Penglei Gao
2026 J jnl
GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection.
CoRR
Kai Yao, Zhenghan Song, Kaixin Wu, Mingjie Zhong, Danzhao Cheng, Zhaorui Tan, Yixin Ji, Penglei Gao
2025 A* conf
Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search.
SIGIR
Yedan Shen, Kaixin Wu, Yuechen Ding, Jingyuan Wen, Hong Liu, Mingjie Zhong, Zhouhan Lin, Jia Xu, Linjian Mo
2025 J jnl
Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search.
CoRR
Yedan Shen, Kaixin Wu, Yuechen Ding, Jingyuan Wen, Hong Liu, Mingjie Zhong, Zhouhan Lin, Jia Xu, Linjian Mo
2025 — conf
CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search.
NAACL (Industry Track)
Kaixin Wu, Yixin Ji, Zeyuan Chen, Qiang Wang, Cunxiang Wang, Hong Liu, Baijun Ji, Jia Xu, Zhongyi Liu, Jinjie Gu, Yuan Zhou, Linjian Mo
2025 — conf
GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models.
ACL (1)
Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Jianke Zhu, Wei Wang
2025 J jnl
GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models.
CoRR
Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Wei Wang, Jianke Zhu
2025 A* conf
MAAQR: An LLM-based Multi-Agent Framework for Adaptive Query Rewriting in Alipay Search.
SIGIR
Qi Zheng, Mingjie Zhong, Saisai Gong, Huimin Jiang, Kaixin Wu, Hong Liu, Jia Xu, Linjian Mo
2025 — conf
PanoExtend: An omnidirectional image super-resolution method based on spherical expansion.
MMAsia Workshops
Xingtao Wang, Kaixin Wu, Jinyu Zhang, Yuxuan Wang, Wenrui Li
2025 J jnl
Test-time Computing: from System-1 Thinking to System-2 Thinking.
CoRR
Yixin Ji, Juntao Li, Hai Ye, Kaixin Wu, Jia Xu, Linjian Mo, Min Zhang
2025 — conf
Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting.
COLING (Industry)
Zeyuan Chen, Haiyan Wu, Kaixin Wu, Wei Chen, Mingjie Zhong, Jia Xu, Zhongyi Liu, Wei Zhang
2024 A conf
Boosting LLM-based Relevance Modeling with Distribution-Aware Robust Learning.
CIKM
Hong Liu, Saisai Gong, Yixin Ji, Kaixin Wu, Jia Xu, Jinjie Gu
2024 J jnl
Boosting LLM-based Relevance Modeling with Distribution-Aware Robust Learning.
CoRR
Hong Liu, Saisai Gong, Yixin Ji, Kaixin Wu, Jia Xu, Jinjie Gu
2024 J jnl
CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search.
CoRR
Kaixin Wu, Yixin Ji, Zeyuan Chen, Qiang Wang, Cunxiang Wang, Hong Liu, Baijun Ji, Jia Xu, Zhongyi Liu, Jinjie Gu, Yuan Zhou, Linjian Mo
2024 — conf
Panoramic Video Inter Frame Prediction and Viewport Prediction Based on Background Modeling.
ICIC (10)
Changli Wang, Xingtao Wang, Kaixin Wu, Xiaopeng Fan
2024 — conf
Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question Answering.
EMNLP (Findings)
Yixin Ji, Kaixin Wu, Juntao Li, Wei Chen, Mingjie Zhong, Jia Xu, Min Zhang
2024 J jnl
Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting.
CoRR
Zeyuan Chen, Haiyan Wu, Kaixin Wu, Wei Chen, Mingjie Zhong, Jia Xu, Zhongyi Liu, Wei Zhang
2023 — conf
Hybrid Control Strategy for Rumor Spread in Social Networks.
IAIC (3)
Haiyan Zi, Shixing Wu, Kaixin Wu
2022 B conf
Speeding up Transformer Decoding via an Attention Refinement Network.
COLING
Kaixin Wu, Yue Zhang, Bojie Hu, Tong Zhang
2021 — conf
TenTrans High-Performance Inference Toolkit for WMT2021 Efficiency Task.
WMT@EMNLP
Kaixin Wu, Bojie Hu, Qi Ju