102 citations · 340 across the 23 of their papers we have counts for
23 papers
PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving
Zhongkai Yu, Ohm Rishabh Venkatachalam, Zheng Wang +9
Multi-LoRA serving is how one base model becomes thousands of specialized variants, one adapter per user, task, or agent, and the deployments can hold 1000-plus adapters. Serving t…
NNVISR: Bring Neural Network Video Interpolation and Super Resolution into Video Processing Framework
Yuan Tong, Mengshun Hu, Zheng Wang
We present NNVISR - an open-source filter plugin for the VapourSynth video processing framework, which facilitates the application of neural networks for various kinds of video enh…
TransRef: Multi-Scale Reference Embedding Transformer for Reference-Guided Image Inpainting
Taorong Liu, Liang Liao, Delin Chen +4
Image inpainting for completing complicated semantic environments and diverse hole patterns of corrupted images is challenging even for state-of-the-art learning-based inpainting m…
Hierarchical Graph Neural Networks for Causal Discovery and Root Cause Localization
Dongjie Wang, Zhengzhang Chen, Jingchao Ni +4
In this paper, we propose REASON, a novel framework that enables the automatic discovery of both intra-level (i.e., within-network) and inter-level (i.e., across-network) causal re…
Unleashing the Potential of Acquisition Functions in High-Dimensional Bayesian Optimization
Jiayu Zhao, Renyu Yang, Shenghao Qiu +1
Bayesian optimization (BO) is widely used to optimize expensive-to-evaluate black-box functions.BO first builds a surrogate model to represent the objective function and assesses i…
UmeTrack: Unified multi-view end-to-end hand tracking for VR
Shangchen Han, Po-chen Wu, Yubo Zhang +13
Real-time tracking of 3D hand pose in world space is a challenging problem and plays an important role in VR interaction. Existing work in this space are limited to either producin…
Programming Bare-Metal Accelerators with Heterogeneous Threading Models: A Case Study of Matrix-3000
Jianbin Fang, Peng Zhang, Chun Huang +4
As the hardware industry moves towards using specialized heterogeneous many-cores to avoid the effects of the power wall, software developers are finding it hard to deal with the c…
MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platforms
Yuke Wang, Boyuan Feng, Zheng Wang +4
The increasing size of input graphs for graph neural networks (GNNs) highlights the demand for using multi-GPU platforms. However, existing multi-GPU GNN systems optimize the compu…
Magic ELF: Image Deraining Meets Association Learning and Transformer
Kui Jiang, Zhongyuan Wang, Chen Chen +3
Convolutional neural network (CNN) and Transformer have achieved great success in multimedia applications. However, little effort has been made to effectively and efficiently harmo…
You Only Align Once: Bidirectional Interaction for Spatial-Temporal Video Super-Resolution
Mengshun Hu, Kui Jiang, Zhixiang Nie +1
Spatial-Temporal Video Super-Resolution (ST-VSR) technology generates high-quality videos with higher resolution and higher frame rates. Existing advanced methods accomplish ST-VSR…
Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning
Mengshun Hu, Kui Jiang, Liang Liao +3
Spatial-Temporal Video Super-Resolution (ST-VSR) aims to generate super-resolved videos with higher resolution(HR) and higher frame rate (HFR). Quite intuitively, pioneering two-st…
Dynamic GPU Energy Optimization for Machine Learning Training Workloads
Farui Wang, Weizhe Zhang, Shichao Lai +2
GPUs are widely used to accelerate the training of machine learning workloads. As modern machine learning models become increasingly larger, they require a longer time to train, le…
TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs
Yuke Wang, Boyuan Feng, Zheng Wang +2
Recently, graph neural networks (GNNs), as the backbone of graph-based machine learning, demonstrate great success in various domains (e.g., e-commerce). However, the performance o…
Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding
Xianzheng Ma, Zhixiang Wang, Yacheng Zhan +4
Although considerable progress has been made in semantic scene understanding under clear weather, it is still a tough problem under adverse weather conditions, such as dense fog, d…
Optimizing Sparse Matrix Multiplications for Graph Neural Networks
Shenghao Qiu, You Liang, Zheng Wang
Graph neural networks (GNNs) are emerging as a powerful technique for modeling graph structures. Due to the sparsity of real-world graph data, GNN performance is limited by extensi…
Meta-Learning with Adjoint Methods
Shibo Li, Zheng Wang, Akil Narayan +2
Model Agnostic Meta Learning (MAML) is widely used to find a good initialization for a family of tasks. Despite its success, a critical challenge in MAML is to calculate the gradie…
CNTLS: A Benchmark Dataset for Abstractive or Extractive Chinese Timeline Summarization
Qianren Mao, Jiazheng Wang, Zheng Wang +3
Timeline summarization (TLS) involves creating summaries of long-running events using dated summaries from numerous news articles. However, limited data availability has significan…
Automated Conformance Testing for JavaScript Engines via Deep Compiler Fuzzing
Guixin Ye, Zhanyong Tang, Shin Hwei Tan +6
JavaScript (JS) is a popular, platform-independent programming language. To ensure the interoperability of JS programs across different platforms, the implementation of a JS engine…
Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement
Kui Jiang, Zhongyuan Wang, Zheng Wang +4
Low-light image enhancement aims to improve an image's visibility while keeping its visual naturalness. Different from existing methods tending to accomplish the relighting task di…
Marrying up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding
Bingfeng Luo, Yansong Feng, Zheng Wang +3
The success of many natural language processing (NLP) tasks is bound by the number and quality of annotated data, but there is often a shortage of such training data. In this paper…
Adaptive Selection of Deep Learning Models on Embedded Systems
Ben Taylor, Vicent Sanz Marco, Willy Wolff +2
The recent ground-breaking advances in deep learning networks ( DNNs ) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on…
Scale Up Event Extraction Learning via Automatic Training Data Generation
Ying Zeng, Yansong Feng, Rong Ma +4
The task of event extraction has long been investigated in a supervised learning paradigm, which is bound by the number and the quality of the training instances. Existing training…
Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix
Bingfeng Luo, Yansong Feng, Zheng Wang +4
Distant supervision significantly reduces human efforts in building training data for many classification tasks. While promising, this technique often introduces noise to the gener…