Accepted Industry and Application Papers

01

DLRover-LM: LLM Pre-Training Framework with Thousands of Accelerators in AntGroup

Ziling Huang* (Sichuan University), Zhengmao Ye (Sichuan University), Qingsong Cai (Sichuan University), Zelong Huang (Sichuan University), Bo Sang (Ant Group), Haitao Zhang (Ant Group), Jian Sha (Ant Group), Tingfeng Lan (University of Virginia), Hui Lu (The University of Texas at Arlington), Yuanchun Zhou (Chinese Academy of Science), Mingjie Tang (Sichuan University)

02

StreamShield: A Production-Proven Resiliency Solution for Apache Flink at ByteDance

Yong Fang (ByteDance), Yuxing Han* (ByteDance), Meng Wang (ByteDance), Yifan Zhang (ByteDance), Yue Ma (ByteDance), Chi Zhang (ByteDance)

03

Tackling Workload Forecasting Challenges with an Offline-Online Dynamic Framework

Jian Jiang* (Ant Group), Yu Liu (Ant Group), Jia Li (Ant Group), Lu Han (Nanjing University), Wei Lu (Ant Group), Qiwen Deng (Ant Group), Zhibo Zhu (Ant Group), Xingyu Lu (Ant Group), Lintao Ma (Ant Group)

04

OceanBase Mercury: Building a Distributed Real-time Analytical Processing Database System

Quanqing Xu* (OceanBase, Ant Group), Chuanhui Yang (OceanBase, Ant Group), Ruijie Li (OceanBase, Ant Group), Dongdong Xie (OceanBase, Ant Group), Hui Cao (OceanBase, Ant Group), Yi Xiao (OceanBase, Ant Group), Junquan Chen (OceanBase, Ant Group), Yanzuo Wang (OceanBase, Ant Group), Saitong Zhao (OceanBase, Ant Group), Fusheng Han (OceanBase, Ant Group)

05

High-Fidelity and Complex Test Data Generation for Google SQL Code Generation Services

Yeounoh Chung* (Google), Shivasankari Kannan (Google), Amita Gondi (Google), Tristan Swadell (Google), Fatma Ozcan (Google)

06

Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance

Jihang Li* (Hong Kong University of Science and Technology (Guangzhou)), Qing Liu (Alibaba Group), Zulong Chen (Alibaba Group), Jing Wang (Alibaba Group), Wei Wang (Alibaba Group), Chuanfei Xu (Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)), Zeyi Wen (Hong Kong University of Science and Technology (Guangzhou))

07

TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting

Zhiyuan Zhao* (Georgia Institute of Technology), Sitan Yang (Keystone AI), Stan Vitebsky (Amazon), B. Aditya Prakash (Georgia Institute of Technology), Dmitry Efimov (Amazon)

08

Hierarchical Industrial Demand Forecasting with Temporal and Uncertainty Explanations

Harshavardhan Kamarthi (Georgia Institute of Technology), Shangqing Xu* (Georgia Institute of Technology), Xinjie Tong (Aspen Technology), Xingyu Zhou (The Dow Chemical Company), James Peters (The Dow Chemical Company), Joseph Czyzyk (The Dow Chemical Company), B. Aditya Prakash (Georgia Institute of Technology)

09

Automatic Parameter Tuning for Compaction in LSM-Tree based Databases

Pinshan Cao (East China Normal University), Peng Cai* (East China Normal University), Xuan Zhou (East China Normal University), Jun-Peng Zhu (East China Normal University), Kecheng Luo (East China Normal University), Sijia Li (East China Normal University), Quanqing Xu (OceanBase, Ant Group), Chuanhui Yang (OceanBase, Ant Group)

10

REVISION: Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization

Yiwen Tang* (Shanghai AI Laboratory, Alibaba), Qiuyu Zhao (Alibaba), Zenghui Sun (Alibaba), Jinsong Lan (Alibaba), Xiaoyong Zhu (Alibaba), Bo Zheng (Alibaba)

11

DBdoctor: A Fine-grained and Non-intrusive Performance Diagnosis Platform for Databases

Xinyue Shi* (Renmin University of China), Quanqi Xin (Juhaokan Technology, Hisense), Zhengjin Wang (Renmin University of China), Xinyi Zhang (Renmin University of China), Haoqiong Bian (Renmin University of China), Wei Lu (Renmin University of China), Qiyu Zhuang (Renmin University of China), Shuang Liu (Renmin University of China), Jikuan Zhang (Juhaokan Technology, Hisense), Xiang Zheng (Juhaokan Technology, Hisense), Yunpeng Chai (Renmin University of China), Xiaoyong Du (Renmin University of China)

12

CCD–Level and Load-Aware Thread Orchestration for In-Memory Vector ANNS on Multi-Core CPUs

Yuchen Huang (East China Normal University), Baiteng Ma (East China Normal University), Yiping Sun (Xiaohongshu Inc), Yang Shi (Xiaohongshu Inc), Xiao Chen (Xiaohongshu Inc), Xiaocheng Zhong (Xiaohongshu Inc), Zhiyong Wang (Xiaohongshu Inc), Yao Hu (Xiaohongshu Inc), Chuliang Weng* (East China Normal University)

13

REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems

Haibo Xing* (Alibaba), Hao Deng (Alibaba), Yucheng Mao (Alibaba), Lingyu Mu (Alibaba), Jinxin Hu (Alibaba), Yi Xu (Alibaba), Hao Zhang (Alibaba), Jiahao Wang (Alibaba), Shizhun Wang (Alibaba), Yu Zhang (Alibaba), Xiaoyi Zeng (Alibaba), Jing Zhang (Wuhan University)

14

Graph Query Generation with Constraint-guided Large Language Agents

Mengying Wang* (Case Western Reserve University), Nicolaas Jedema (Amazon), Rahul Pandey (Amazon), RaviKiran Krishnan (Meta), Jens Lehmann (Amazon), Yinghui Wu (Case Western Reserve University)

15

JITPrune: An Efficient Online Feature Pruning Framework for Embedding-based DLRM Training

Hongzheng Li* (Beijing University of Posts and Telecommunications), Yucheng Wu (Peking University), Junjie Zhai (Tencent), Anan Liu (Tencent), Yuekui Yang (Tencent), Yingxia Shao (Beijing University of Posts and Telecommunications)

16

D2SQA: An Edge–Cloud Collaborative Slow Query Analysis Framework Deployed at DBAPPSecurity

Ziquan Fang* (Zhejiang university), Xiangheng Wang (Zhejiang university), Zijun Jia (Beihang University), Bo Liu (DBAPPSecurity Co., Ltd.), Yuan Fan (DBAPPSecurity Co., Ltd.), Haichuan Zhang (DBAPPSecurity Co., Ltd.)

17

GALA: Generative Aligned Learning for Adaptive Multimodal Representation in the Eleme Recommender System

JiPing Liu* (Alibaba Group), Zhongmin Zhang (Alibaba Group), Zisen Sang (Alibaba Group), Zhijia Fang (Alibaba Group), Tao Ouyang (Central South University), Ma Jiang (Alibaba Group), shaopeng liang (Alibaba Group), Zeyang Hou (Alibaba Group), Guodong Cao (Alibaba Group), jia jia (Alibaba Group)

18

KScaNN: Scalable Approximate Nearest Neighbor Search on Kunpeng

Oleg Senkevich (Huawei Technologies Ltd), Siyang Xu (Huawei Technologies Ltd.), Tianyi Jiang (Huawei Technologies Ltd.), Alexander Radionov (Huawei Technologies Ltd.), Jan Tabaszewski (Huawei Technologies Ltd.), Dmitriy Malyshev (Higher School of Economics), Zijian Li* (Huawei Technologies Ltd.), Daihao Xue (Huawei Technologies Ltd.), Licheng Yu (Huawei Technologies Ltd.), Weidi Zeng (Huawei Technologies Ltd.), Meiling Wang (Huawei Technologies Ltd.), Xin Yao (Huawei Technologies Ltd.), Siyu Huang (Huawei Technologies Ltd.), Gleb Neshchetkin (Huawei Technologies Ltd.), Qiuling Pan (Huawei Technologies Ltd.), Yaoyao Fu (Huawei Technologies Ltd.)

19

Efficient Data Processing using On-the-Fly Host-PIM Interactions in a Commodity PIM System

Hyojune Kim (Hanyang University), Jeonghyeon Joo (Hanyang University), TaeHyeong Park (Yonsei University), Yongjun Park (Yonsei University), Hyuck Han (FuriosaAI), Sooyong Kang* (Hanyang University)

20

RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching

Tong Wang* (Zhejiang University), Yongqin Xu (Zhejiang University), Jianfeng Zhang (Zhejiang University), Lingxi Cui (Zhejiang University), Wenqing Wei (Xiaohongshu), Suzhou Chen (Xiaohongshu), Huan Li (Zhejiang University), Ke Chen (Zhejiang University), Lidan Shou (Zhejiang University)

21

CoLIBRi: Supporting quotation through multi-modal retrieval and conversational search on manufacturing drawings

Jacob Pollack* (Leipzig University), Lucas Peter (Leipzig University), Matthias Täschner (Leipzig University), Carmen Ahnert (CPT Präzisionstechnik GmbH)

22

Building and Benchmarking Large Language Models for Machine Translation in Social Network Services

Hongcheng Guo (Fudan University), Fei Zhao (Xiaohongshu Inc.), Shaosheng Cao* (Xiaohongshu Inc.), Xinze Lyu (Xiaohongshu Inc.), Zijie Meng (Zhejiang University), Yue Wang (Nanjing University), Yao Hu (Xiaohongshu Inc.), Zhoujun Li (Xiaohongshu Inc.), Zuozhu Liu (Zhejiang University)

23

FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data

Kun Ouyang* (LIGHTSPEED STUDIOS, Tencent), Haoyu Wang (Tsinghua University), Dong Fang (LIGHTSPEED STUDIOS)

24

Cascading Relevance-driven Recommendation Network for CTR Prediction in Trigger-Introduced Recommendation

Kaixuan Chen* (Taobao & Tmall Group of Alibaba), Wenwen Wang (Taobao & Tmall Group of Alibaba), Xing Fang (Taobao & Tmall Group of Alibaba), Yang Huang (Taobao & Tmall Group of Alibaba), Jing Wang (Taobao & Tmall Group of Alibaba)

25

Accurate and Efficient Multi-channel Time Series Forecasting via Sparse Attention Mechanism

Hengda Bao (SF Express), Jingfei Fang (SF Express), guangzheng wu* (Zhejiang University of Technology), Weihua Zhou (Zhejiang University)

26

From Benchmarks to Production: Transferring Time Series Anomaly Detection Methods for Electricity Production Monitoring

Nicolas Vautier* (EDF Lab Paris Saclay), Paul Caron (EDF DOAAT), Nardi Xhepi (EDF DOAAT), Félicie Bizeul (EDF Lab Paris Saclay), Manel Boumghar (EDF Lab Paris Saclay), Christophe Degouy (EDF DOAAT), Paul Boniol (INRIA)

27

OpenZL: Using Graphs to Compress Smaller and Faster

Yann Collet (Meta), Nick Terrell (Meta), Winston Felix Handte (Meta Platforms), Danielle Rozenblit (Meta), Victor Zhang* (Meta), Kevin Zhang (Meta), Yaelle Goldschlag (Meta), Jennifer Lee (Meta), Elliot Gorokhovsky (Meta), Yonatan Komornik (Meta), Daniel Riegel (Meta), Stan Angelov (Meta), Nadav Rotem (Meta)

28

GaV: Guess and Verification of Column Semantics

Davide Di Stefano (TU Wien & Unlimidata Ltd), Jinsong Guo* (Unlimidata Ltd), Yang Hu (University of Leicester), Matteo Capalbo (University of Calabria), Davide Mario Longo (University of Calabria), Georg Gottlob (University of Calabria)

29

User-Adaptive Meta-Learning for Cold-Start Medication Recommendation with Uncertainty Filtering

Arya Hadizadeh Moghaddam (University of Kansas), Mohsen Nayebi Kerdabadi (University of Kansas), Dongjie Wang (University of Kansas), Mei Liu (UF Health), Zijun Yao* (University of Kansas)

30

On Efficient Materialization in Data Lakes

Andrew Harn (Google Inc), Herald Kllapi* (Google Inc), Zhepeng Yan (Google Inc)

31

Billion-scale Fintech Analytics: Scalable Data Management and Anomaly Detection at NPCI

Bharadwaj Dasari (National Payments Corporation of India), Turaga Sai Dhiraj (National Payments Corporation of India), Ganesh Jambhrunkar (National Payments Corporation of India), Thirumalai Kailasam (National Payments Corporation of India), Charu Vikram (National Payments Corporation of India), Saurav Singla (National Payments Corporation of India), Pranjal Naman (Indian Institute of Science (IISc), Bangalore), Yogesh Simmhan* (Indian Institute of Science (IISc), Bangalore)

32

Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction

Alin Fan* (Alibaba International Digital Commerce Group), Hanqing Li (Alibaba International Digital Commerce Group), Sihan Lu (Renmin University of China), Jingsong Yuan (Alibaba International Digital Commerce Group), Jiandong Zhang (Alibaba International Digital Commerce Group)

33

GalaxyRAG: Graph Retrieval-Augmented Generation for Enterprise Knowledge Systems

Bing Tong* (The Hong Kong University of Science and Technology (Guangzhou)), Yan Zhou (Zhejiang Chuanglin Technology Co., Ltd.), Chen Zhang (Zhejiang Chuanglin Technology Co., Ltd.), Zhaojie Yin (Zhejiang Chuanglin Technology Co., Ltd.), Jia Li (The Hong Kong University of Science and Technology (Guangzhou))

34

OEPO: Online Experience-based Preference Optimization for CTR Prediction

Zhichao Liao* (University of Electronic Science and Technology of China), Ziheng Ni (JD.com), Congcong Liu (JD.com), Zhiwei Fang (JD.com), Changping Peng (JD.com)

35

DM-RAG: Enhancing User Support in Dameng Databases with Retrieval-Augmented Generation

Qiang Huang* (Wuhan University), Ke Liu (Wuhan Dameng Database Co., Ltd), Liang Deng (Wuhan Dameng Database Co., Ltd), Sijing Zhang (Wuhan Dameng Database Co., Ltd), Chuang Hu (Wuhan University), Tieyun Qian (Wuhan University), Xiao Yan (Wuhan University), Jiawei Jiang (Wuhan University)

36

Relevance Matters: A Multi-Task and Multi-Stage Large Language Model Approach for E-commerce Query Rewriting

Aijun Dai* (Jingdong), Jixiang Zhang (Tsinghua University)