41 citations · 70 across the 13 of their papers we have counts for
14 papers
ComFuse: Fusing Complex Memory-Intensive Subgraphs with Compute-Intensive Kernels For Modern GPU Architectures
Di Mu, Tengyuan Jin, Zhenkun Wang +6
Modern deep learning workloads increasingly comprise heterogeneous computation graphs that combine compute-intensive operators with memory-intensive subgraphs. Existing deep learni…
Dynamically Detect and Fix Hardness for Efficient Approximate Nearest Neighbor Search
Zhiyuan Hua, Qiji Mo, Zebin Yao +8
Approximate Nearest Neighbor Search (ANNS) has become a fundamental component in many real-world applications. Among various ANNS algorithms, graph-based methods are state-of-the-a…
Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents
Tiannuo Yang, Zebin Yao, Bowen Jin +4
Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleav…
Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling
Sinong Zhao, Wenrui Wang, Hongzuo Xu +5
Identifying anomalies from time series data plays an important role in various fields such as infrastructure security, intelligent operation and maintenance, and space exploration.…
PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution
Yan Wang, Yusen Li, Gang Wang +1
Reducing latency is a roaring trend in recent super-resolution (SR) research. While recent progress exploits various convolutional blocks, attention modules, and backbones to unloc…
pFedAFM: Adaptive Feature Mixture for Batch-Level Personalization in Heterogeneous Federated Learning
Liping Yi, Han Yu, Chao Ren +4
Model-heterogeneous personalized federated learning (MHPFL) enables FL clients to train structurally different personalized models on non-independent and identically distributed (n…
VDTuner: Automated Performance Tuning for Vector Data Management Systems
Tiannuo Yang, Wen Hu, Wangqi Peng +4
Vector data management systems (VDMSs) have become an indispensable cornerstone in large-scale information retrieval and machine learning systems like large language models. To enh…
pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning
Liping Yi, Han Yu, Chao Ren +4
Federated learning (FL) has been widely adopted for collaborative training on decentralized data. However, it faces the challenges of data, system, and model heterogeneity. This ha…
DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution
Yan Wang, Tongtong Su, Yusen Li +3
Recent research on deep convolutional neural networks (CNNs) has provided a significant performance boost on efficient super-resolution (SR) tasks by trading off the performance an…
FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning
Liping Yi, Han Yu, Zhuan Shi +4
Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (a.k.a. FL clients) to train the same local model…
pFedES: Model Heterogeneous Personalized Federated Learning with Feature Extractor Sharing
Liping Yi, Han Yu, Gang Wang +1
As a privacy-preserving collaborative machine learning paradigm, federated learning (FL) has attracted significant interest from academia and the industry alike. To allow each data…
pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning
Liping Yi, Han Yu, Gang Wang +2
Federated learning (FL) is an emerging machine learning paradigm in which a central server coordinates multiple participants (clients) collaboratively to train on decentralized dat…
FedGH: Heterogeneous Federated Learning with Generalized Global Header
Liping Yi, Gang Wang, Xiaoguang Liu +2
Federated learning (FL) is an emerging machine learning paradigm that allows multiple parties to train a shared model collaboratively in a privacy-preserving manner. Existing horiz…
Multi-scale Attention Network for Single Image Super-Resolution
Yan Wang, Yusen Li, Gang Wang +1
ConvNets can compete with transformers in high-level tasks by exploiting larger receptive fields. To unleash the potential of ConvNet in super-resolution, we propose a multi-scale…