4.4k citations
- Tsinghua UniversityCN54 papers
- Shanghai Jiao Tong UniversityCN46 papers
- Peking UniversityCN45 papers
- Zhejiang UniversityCN41 papers
- Huawei Technologies (Canada)CA31 papers
- Chinese Academy of SciencesCN29 papers
- Renmin University of ChinaCN29 papers
- University of Science and Technology of ChinaCN29 papers
- Hong Kong University of Science and TechnologyHK28 papers
- Chinese University of Hong KongHK26 papers
- Southern University of Science and TechnologyCN23 papers
- University of Hong KongHK21 papers
685 papers
SQL-RewriteBench: A Correctness-Gated, Full-Denominator Benchmark for Statement-Level SQL Rewriting [Experiment,Analysis & Benchmark]
Jiang Long, Tianci Gao, Shiyuan Hao +3
Statement-level SQL rewriting can improve query performance and maintainability without changing the DBMS kernel, but existing benchmarks do not evaluate rewrite methods as deploya…
Practical Lossless Volumetric Medical Image Compression via Tri-plane Context Tree Learning
Yuanchao Bai, Yifan Zhao, Kai Wang +5
Lossless compression of volumetric medical images is of paramount importance for clinical and research applications where data fidelity is essential. Traditional compression method…
Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs
Yidu Wu, Xiang Wang, Kejie Zhao +3
Large language models (LLMs) achieve strong generation and reasoning performance, but the Transformer architecture incurs high inference cost. Existing acceleration methods often r…
UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods
Yipeng Liu, Chang Liu, Si Shen +16
The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA's NVL72/576 and Huawei's CloudMatrix384, introduces critical challenges bey…
When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
Zhicheng Zhang, Jiwei Tang, Kuicai Dong +9
Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriev…
Point-Cloud-Assistant Localized Statistical Channel Prediction by Tangent Gaussian Splatting
Ye Xue, Yiheng Wang, Xinhua Shao +3
Accurate, site-specific channel information is crucial for optimizing next-generation wireless networks. Among various approaches, localized statistical channel modeling (LSCM), wh…