JJ
Jiawei Jiang
cs.LGcs.AIcs.CLcs.DCcs.IRcs.CVstat.MLcs.DBcs.SIcs.AR
On Valency
published · living versionsW_7mgb5ab8·v1 · currentpublished
Rethinking Positional Encoding and Interaction Granularity for CTR Prediction
with Xinxun Zhang, Yuxiang Wang, Xiaokai Zhou, Jiayue Li +6
1 version
W_yn6nd4jr·v1published
Preprints & journals
48 papers in the corpus · 2018–2026AFORE: Attention-FFN Disaggregation with Overlapped Reconfiguration of Experts2610.03203v1 · Wenshuang Li, Youhe Jiang, You Peng et al.2026 · 0 citationsarXiv
Denoising Surface: Modeling and Predicting Inference Cost for Diffusion LLM Serving2610.00499v1 · Haoyu Zheng, Fangcheng Fu, Binhang Yuan et al.2026 · 0 citationsarXiv
SiriusDeliver: Automating Data Warehouse Delivery at Tencent2608.09185v1 · Haining Xie, Xiaokai Zhou, Jiaming Yang et al.2026 · 0 citationsarXivon Valency
SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning2608.07932v2 · Yizhi Li, Jiawei Jiang, Guanhong Wang et al.2026 · 0 citationsarXiv
DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering2608.01565v1 · Dongyang Xie, Yao Tian, Hao Zhang et al.2026 · 0 citationsarXiv
Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering2607.22633v2 · Guixin Su, Qiankun Pi, Mayi Xu et al.2026 · 0 citationsarXiv
Text-attributed Graph Condensation via Text Selection and Attribute Matching2606.03839v1 · Haowei Han, Yuxiang Wang, Guojia Wan et al.2026 · 0 citationsarXiv
MiCU: End-to-End Smart Home Command Understanding with Large Language Model2606.01099v1 · Haowei Han, Kexin Hu, Weiwei Cai et al.2026 · 0 citationsarXiv
HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling2605.16637v1 · You Peng, Youhe Jiang, Wenshuang Li et al.2026 · 0 citationsarXiv
UniVA: Unified Value Alignment for Generative Recommendation in Online Advertising at Tencent2605.05803v2 · Xinxun Zhang, Yuling Xiong, Yangru Huang et al.2026 · 0 citationsarXiv
Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management2605.06472v1 · Haoyu Zheng, Fangcheng Fu, Jia Wu et al.2026 · 0 citationsarXiv
MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches2604.22881v1 · Xin Wang, Chi Ma, Shaobin Chen et al.2026 · 0 citationsarXiv
Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions2604.00499v2 · Haoyu Zheng, Yongqiang Zhang, Fangcheng Fu et al.2026 · 0 citationsarXiv
Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors2603.25088v1 · Chengxu Yang, Jingling Yuan, Chuang Hu et al.2026 · 0 citationsarXiv
AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models2603.08275v2 · Hankun Kang, Di Lin, Zhirong Liao et al.2026 · 0 citationsarXiv
FuxiShuffle: An Adaptive and Resilient Shuffle Service for Distributed Data Processing on Alibaba Cloud2602.22580v1 · Yuhao Lin, Zhipeng Tang, Jiayan Tong et al.2026 · 0 citationsarXiv
Beyond Static Snapshots: Dynamic Modeling and Forecasting of Group-Level Value Evolution with Large Language Models2602.14043v1 · Qiankun Pi, Guixin Su, Jinliang Li et al.2026 · 0 citationsarXiv
End-to-End Semantic ID Generation for Generative Advertisement Recommendation2602.10445v3 · Jie Jiang, Xinxun Zhang, Enming Zhang et al.2026 · 0 citationsarXiv
Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations2512.21635v2 · Chengxu Yang, Jingling Yuan, Siqi Cai et al.2025 · 0 citationsarXiv
REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature2512.10348v1 · Wenhan Wu, Zhili He, Huanghuang Liang et al.2025 · 0 citationsarXiv
DevPiolt: Operation Recommendation for IoT Devices at Xiaomi Home2511.14227v1 · Yuxiang Wang, Siwen Wang, Haowei Han et al.2025 · 0 citationsarXiv
Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question Answering2508.08785v2 · Yunfeng Ning, Mayi Xu, Jintao Wen et al.2025 · 2 citationsarXiv
How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG2506.06331v2 · Qiming Zeng, Hao Luo, Yuhao Lin et al.2025 · 0 citationsarXiv
MTGenRec: An Efficient Distributed Training System for Generative Recommendation Models in Meituan2505.12663v3 · Yuxiang Wang, Chi Ma, Xiao Yan et al.2025 · 0 citationsarXiv
Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph2505.08168v1 · Yuxiang Wang, Xiao Yan, Shiyu Jin et al.2025 · 2 citationsarXiv
Guiding LLM-based Smart Contract Generation with Finite State Machine2505.08542v1 · Hao Luo, Yuhao Lin, Xiao Yan et al.2025 · 9 citationsarXiv
RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference2505.02922v3 · Yaoqi Chen, Jinkai Zhang, Baotong Lu et al.2025 · 1 citationPVLDB, 19(5): 1016-1031, 2026
Towards Scalable and Deep Graph Neural Networks via Noise Masking2412.14602v2 · Yuxuan Liang, Wentao Zhang, Zeang Sheng et al.2024 · 3 citationsarXiv
Origin-Destination Demand Prediction: An Urban Radiation and Attraction Perspective2412.00167v2 · Xuan Ma, Zepeng Bao, Ming Zhong et al.2024 · 0 citationsarXiv
Retrofitting Temporal Graph Neural Networks with Transformer2409.05477v3 · Qiang Huang, Xiao Yan, Xin Wang et al.2024 · 0 citationsarXiv
Hound: Hunting Supervision Signals for Few and Zero Shot Node Classification on Text-attributed Graph2409.00727v1 · Yuxiang Wang, Xiao Yan, Shiyu Jin et al.2024 · 0 citationsarXiv
TreeCSS: An Efficient Framework for Vertical Federated Learning2408.01691v1 · Qinbo Zhang, Xiao Yan, Yukai Ding et al.2024 · 3 citationsarXiv
PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory System2404.07164v2 · Steve Rhyner, Haocong Luo, Juan G'omez-Luna et al.2024 · 22 citationsarXiv
Distribution-Aware Data Expansion with Diffusion Models2403.06741v2 · Haowei Zhu, Ling Yang, Jun-Hai Yong et al.2024 · 6 citationsarXiv
Learning Diffusions under Uncertainty2312.07942v1 · Hao Huang, Qian Yan, Keqi Han et al.2023 · 7 citationsarXiv
Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning2310.15523v1 · Yuxiang Wang, Xiao Yan, Chuang Hu et al.2023 · 12 citationsarXiv
BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networks2308.16385v1 · Qiang Huang, Jiawei Jiang, Xi Susie Rao et al.2023 · 8 citationsarXiv
Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates2207.14628v1 · Fangcheng Fu, Xupeng Miao, Jiawei Jiang et al.2022 · 33 citationsarXiv
Stochastic Gradient Descent without Full Data Shuffle2206.05830v1 · Lijie Xu, Shuang Qiu, Binhang Yuan et al.2022 · 1 citationarXiv
BRIGHT -- Graph Neural Networks in Real-Time Fraud Detection2205.13084v2 · Mingxuan Lu, Zhichao Han, Susie Xi Rao et al.2022 · 48 citationsarXiv
Efficient Diversity-Driven Ensemble for Deep Neural Networks2112.13316v1 · Wentao Zhang, Jiawei Jiang, Yingxia Shao et al.2021 · 20 citations2020 IEEE 36th International Conference on Data Engineering (ICDE)
BAGUA: Scaling up Distributed Learning with System Relaxations2107.01499v4 · Shaoduo Gan, Xiangru Lian, Rui Wang et al.2021 · 3 citationsarXiv
OpenBox: A Generalized Black-box Optimization Service2106.00421v3 · Yang Li, Yu Shen, Wentao Zhang et al.2021 · 76 citationsProceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD-2021)
Towards Demystifying Serverless Machine Learning Training2105.07806v1 · Jiawei Jiang, Shaoduo Gan, Yue Liu et al.2021 · 117 citationsarXiv
Efficient Automatic CASH via Rising Bandits2012.04371v1 · Yang Li, Jiawei Jiang, Jinyang Gao et al.2020 · 28 citationsProceedings of the AAAI Conference on Artificial Intelligence, 34(04), 4763-4771 (2020)
MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements2012.03011v2 · Yang Li, Yu Shen, Jiawei Jiang et al.2020 · 23 citationsThe Thirty-Fifth AAAI Conference on Artifici4l Intelligence (AAAI-2021)
An Experimental Evaluation of Large Scale GBDT Systems1907.01882v2 · Fangcheng Fu, Jiawei Jiang, Yingxia Shao et al.2019 · 35 citationsarXiv
Fast Hyperparameter Optimization of Deep Neural Networks via Ensembling Multiple Surrogates1811.02319v3 · Yang Li, Jiawei Jiang, Yingxia Shao et al.2018 · 1 citationarXiv
Career total: 153 works. 48 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.