SS
Shixuan Sun
cs.DBcs.DCcs.LGcs.AIcs.ARcs.CLcs.IRcs.OScs.PF
On Valency
published · living versionsW_h4bz275s·v1 · currentpublished
MemDerive: A Diagnostic Benchmark for Agent Memory over Evolving Data
with Sen Gao, Yongan Li, Han Chen, Bingsheng He +3
1 version
Preprints & journals
27 papers in the corpus · 2021–2026MemDerive: A Diagnostic Benchmark for Agent Memory over Evolving Data2610.25373v1 · Sen Gao, Yongan Li, Han Chen et al.2026 · 0 citationsarXivon Valency
Dissecting How Die Scaling Breaks GPU Fine-grained Scheduling2609.24270v1 · Xiaoze Fan, Jianhao Wang, Weihao Cui et al.2026 · 0 citationsarXiv
Weave: Fine-Grained Dynamic SM Scheduling in an MoE Megakernel for Compute-Communication Overlap2609.21483v3 · Ziyu Huang, Yangjie Zhou, Chenhao Zhu et al.2026 · 0 citationsarXiv
A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation2608.19628v1 · Zihan Liu, Jingwen Leng, Yangjie Zhou et al.2026 · 0 citationsarXiv
GPU-Tile-Sim: A Tile-Centric GPU Simulation Framework for LLM Hardware-Software Co-Design2607.11262v1 · Yitong Ding, Jiawei Huang, Renyang Guan et al.2026 · 0 citationsarXiv
GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving2606.13501v2 · Xinwei Qiang, Yifan Hu, Shixuan Sun et al.2026 · 0 citationsarXiv
CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels2605.05023v1 · Xing Ma, Yangjie Zhou, Wu Sun et al.2026 · 1 citationarXiv
gMatch: Fine-Grained and Hardware-Efficient Subgraph Matching on GPUs2604.10601v1 · Weitian Chen, Shixuan Sun, Cheng Chen et al.2026 · 0 citationsarXiv
InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models2604.07173v1 · Hongyu Chen, Letian Ruan, Zilin Xu et al.2026 · 0 citationsarXiv
Efficient Densest Flow Queries in Transaction Flow Networks (Complete Version)2602.15773v1 · Jiaxin Jiang, Yunxiang Zhao, Lyu Xu et al.2026 · 0 citationsarXiv
DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training2601.21824v1 · Xinwei Qiang, Hongmin Chen, Shixuan Sun et al.2026 · 0 citationsProceedings of the International Conference on Learning Representations (ICLR), 2026
LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving2509.01229v1 · Huanqi Hu, Bowen Xiao, Shixuan Sun et al.2025 · 2 citationsarXiv
ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive2508.18850v1 · Xinhao Luo, Zihan Liu, Yangjie Zhou et al.2025 · 1 citationarXiv
RapidStore: An Efficient Dynamic Graph Storage System for Concurrent Queries2507.00839v1 · Chiyu Hao, Jixian Su, Shixuan Sun et al.2025 · 3 citationsarXiv
Efficient Serving of LLM Applications with Probabilistic Demand Modeling2506.14851v1 · Yifei Liu, Zuo Gan, Zhenghao Gan et al.2025 · 1 citationACM Transactions on Architecture and Code Optimization 23, 2, Article (June 2026), 1-25
Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy2506.05682v1 · Yu Feng, Weikai Lin, Yuge Cheng et al.2025 · 0 citationsarXiv
Towards High-Goodput LLM Serving with Prefill-decode Multiplexing2504.14489v3 · Yukang Chen, Weihao Cui, Han Zhao et al.2025 · 1 citationarXiv
Revisiting the Design of In-Memory Dynamic Graph Storage2502.10959v1 · Jixian Su, Chiyu Hao, Shixuan Sun et al.2025 · 6 citationsarXiv
vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving2407.15309v1 · Jiale Xu, Rui Zhang, Cong Guo et al.2024 · 2 citationsarXiv
CANDY: A Benchmark for Continuous Approximate Nearest Neighbor Search with Dynamic Data Ingestion2406.19651v1 · Xianzhi Zeng, Zhuoyan Wu, Xinjing Hu et al.2024 · 0 citationsarXiv
FlowWalker: A Memory-efficient and High-performance GPU-based Dynamic Graph Random Walk Framework2404.08364v3 · Junyi Mei, Shixuan Sun, Chao Li et al.2024 · 10 citationsarXiv
Async-fork: Mitigating Query Latency Spikes Incurred by the Fork-based Snapshot Mechanism from the OS Level2301.05861v1 · Pu Pang, Gang Deng, Kaihao Bai et al.2023 · 9 citationsarXiv
An In-Depth Study of Continuous Subgraph Matching (Complete Version)2203.06913v1 · Xibo Sun, Shixuan Sun, Qiong Luo et al.2022 · 1 citationarXiv
ThunderRW: An In-Memory Graph Random Walk Engine (Complete Version)2107.11983v1 · Shixuan Sun, Yuhang Chen, Shengliang Lu et al.2021 · 1 citationarXiv
Cache-Efficient Fork-Processing Patterns on Large Graphs2103.14915v2 · Shengliang Lu, Shixuan Sun, Johns Paul et al.2021 · 13 citationsarXiv
Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workload2103.12465v1 · Johan Kok Zhi Kang, Gaurav, Sien Yi Tan et al.2021 · 32 citationsarXiv
PathEnum: Towards Real-Time Hop-Constrained s-t Path Enumeration2103.11137v2 · Shixuan Sun, Yuhang Chen, Bingsheng He et al.2021 · 28 citationsarXiv
Career total: 72 works. 27 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.