Shangyu Wu

31 papers A* 4A 2Misc 1Journal 18Unranked 6
YearRankTypeTitle / Venue / Authors
2026 — conf
ClawMobile: Rethinking Smartphone-Native Agentic Systems.
EuroMLSys@EuroSys
Hongchao Du, Shangyu Wu, Qiao Li, Riwei Pan, Jinheng Li, Youcheng Sun, Chun Jason Xue
2026 J jnl
ClawMobile: Rethinking Smartphone-Native Agentic Systems.
CoRR
Hongchao Du, Shangyu Wu, Qiao Li, Riwei Pan, Jinheng Li, Youcheng Sun, Chun Jason Xue
2026 A conf
ColdCode: Cold Data Encoding for Enhanced Reliability and Lifetime in 3D NAND Flash.
EuroSys
Qiao Li, Shangyu Wu, Zheng Wan, Yufei Cui, Jie Zhang, Chun Jason Xue
2026 J jnl
ContiguousKV: Accelerating LLM Prefill with Granularity-Aligned KV Cache Management.
CoRR
Jing Zou, Shangyu Wu, Hancong Duan, Qiao Li, Chun Jason Xue
2026 J jnl
LAPS: A Length-Aware-Prefill LLM Serving System.
CoRR
Jianshu She, Zonghang Li, Hongchao Du, Shangyu Wu, Wenhao Zheng, Eric Xing, Zhengzhong Liu, Huaxiu Yao, Jason Xue, Qirong Ho
2026 J jnl
ReFilter: Improving Robustness of Retrieval-Augmented Generation via Gated Filter.
CoRR
Yixin Chen, Ying Xiong, Shangyu Wu, Xiangrui Ke, Nan Guan, Chun Jason Xue
2025 J jnl
A
CoRR
Junhui He, Junna Xing, Nan Wang, Rui Xu, Shangyu Wu, Peng Zhou, Qiang Liu, Chun Jason Xue, Qingan Li
2025 — conf
A²ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization.
ACL (Findings)
Junhui He, Junna Xing, Nan Wang, Rui Xu, Shangyu Wu, Peng Zhou, Qiang Liu, Chun Jason Xue, Qingan Li
2025 J jnl
Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever.
CoRR
Yixin Chen, Ying Xiong, Shangyu Wu, Yufei Cui, Xue (Steve) Liu, Nan Guan, Chun Jason Xue
2025 — conf
EvoP: Robust LLM Inference via Evolutionary Pruning.
NLPCC (1)
Shangyu Wu, Hongchao Du, Ying Xiong, Shuai Chen, Tei-Wei Kuo, Nan Guan, Chun Jason Xue
2025 J jnl
EvoP: Robust LLM Inference via Evolutionary Pruning.
CoRR
Shangyu Wu, Hongchao Du, Ying Xiong, Shuai Chen, Tei-Wei Kuo, Nan Guan, Chun Jason Xue
2025 — conf
FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference.
EuroMLSys
Hongchao Du, Shangyu Wu, Arina Kharlamova, Nan Guan, Chun Jason Xue
2025 J jnl
FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference.
CoRR
Hongchao Du, Shangyu Wu, Arina Kharlamova, Nan Guan, Chun Jason Xue
2025 — conf
GeneQuery: Generalized Gene Expression Prediction from Histology Images via Image-Gene QA.
BIBM
Ying Xiong, Linjing Liu, Yufei Cui, Shangyu Wu, Xue Liu, Antoni B. Chan, Chun Jason Xue
2025 A* conf
MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization.
EMNLP
Chun Hu, Junhui He, Shangyu Wu, Yuxin He, Chun Jason Xue, Qingan Li
2025 J jnl
Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving.
CoRR
Haibo Hu, Lianming Huang, Xinyu Wang, Yufei Cui, Shangyu Wu, Nan Guan, Chun Jason Xue
2024 A* conf
CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification.
EMNLP
Junhui He, Shangyu Wu, Weidong Wen, Chun Jason Xue, Qingan Li
2024 J jnl
CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification.
CoRR
Junhui He, Shangyu Wu, Weidong Wen, Chun Jason Xue, Qingan Li
2024 J jnl
GeneQuery: A General QA-based Framework for Spatial Gene Expression Predictions from Histology Images.
CoRR
Ying Xiong, Linjing Liu, Yufei Cui, Shangyu Wu, Xue Liu, Antoni B. Chan, Chun Jason Xue
2024 J jnl
Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion.
CoRR
Shangyu Wu, Ying Xiong, Yufei Cui, Xue Liu, Buzhou Tang, Tei-Wei Kuo, Chun Jason Xue
2024 A* conf
LeaderKV: Improving Read Performance of KV Stores via Learned Index and Decoupled KV Table.
ICDE
Yi Wang, Jianan Yuan, Shangyu Wu, Huan Liu, Jiaxian Chen, Chenlin Ma, Jianbin Qin
2024 J jnl
RAEE: A Training-Free Retrieval-Augmented Early Exiting Framework for Efficient Inference.
CoRR
Lianming Huang, Shangyu Wu, Yufei Cui, Ying Xiong, Xue Liu, Tei-Wei Kuo, Nan Guan, Chun Jason Xue
2024 A* conf
ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion.
ICLR
Shangyu Wu, Ying Xiong, Yufei Cui, Xue Liu, Buzhou Tang, Tei-Wei Kuo, Chun Jason Xue
2024 J jnl
Retrieval-Augmented Generation for Natural Language Processing: A Survey.
CoRR
Shangyu Wu, Ying Xiong, Yufei Cui, Haolun Wu, Can Chen, Ye Yuan, Lianming Huang, Xue Liu, Tei-Wei Kuo, Nan Guan, Chun Jason Xue
2023 J jnl
Tidal-Tree-Mem: Toward Read-Intensive Key-Value Stores With Tidal Structure Based on LSM-Tree.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
Chenlin Ma, Hao Yang, Shangyu Wu, Yi Wang, Rui Mao
2022 J jnl
Bits-Ensemble: Toward Light-Weight Robust Deep Ensemble by Bits-Sharing.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
Yufei Cui, Shangyu Wu, Qiao Li, Antoni B. Chan, Tei-Wei Kuo, Chun Jason Xue
2022 J jnl
NFL: Robust Learned Index via Distribution Transformation.
CoRR
Shangyu Wu, Yufei Cui, Jinghuan Yu, Xuan Sun, Tei-Wei Kuo, Chun Jason Xue
2022 J jnl
NFL: Robust Learned Index via Distribution Transformation.
Proc. VLDB Endow.
Shangyu Wu, Yufei Cui, Jinghuan Yu, Xuan Sun, Tei-Wei Kuo, Chun Jason Xue
2022 Misc conf
Work-in-Progress: Lark: A Learned Secondary Index Toward LSM-tree for Resource-Constrained Embedded Storage Systems.
CODES+ISSS
Jianan Yuan, Huan Liu, Shangyu Wu, Yiquan Lin, Tiantian Wang, Chenlin Ma, Rui Mao, Yi Wang
2020 — conf
Towards Read-Intensive Key-Value Stores with Tidal Structure Based on LSM-Tree.
ASP-DAC
Yi Wang, Shangyu Wu, Rui Mao
2019 A conf
Towards Cross-Platform Inference on Edge Devices with Emerging Neuromorphic Architecture.
DATE
Shangyu Wu, Yi Wang, Amelie Chi Zhou, Rui Mao, Zili Shao, Tao Li