Search Results for author: Yixuan Sun

Found 19 papers, 5 papers with code

Quality-aware Masked Diffusion Transformer for Enhanced Music Generation

no code implementations24 May 2024 Chang Li, Ruoyu Wang, Lijuan Liu, Jun Du, Yixuan Sun, Zilu Guo, Zhenrong Zhang, Yuan Jiang

To overcome these challenges, we introduce a novel quality-aware masked diffusion transformer (QA-MDT) approach that enables generative models to discern the quality of input music waveform during training.

Streamlining Ocean Dynamics Modeling with Fourier Neural Operators: A Multiobjective Hyperparameter and Architecture Optimization Approach

no code implementations7 Apr 2024 Yixuan Sun, Ololade Sowunmi, Romain Egele, Sri Hari Krishna Narayanan, Luke Van Roekel, Prasanna Balaprakash

The experimental results show that the optimal set of hyperparameters enhanced model performance in single timestepping forecasting and greatly exceeded the baseline configuration in the autoregressive rollout for long-horizon forecasting up to 30 days.

Efficient Exploration Hyperparameter Optimization +1

A Safe Reinforcement Learning Algorithm for Supervisory Control of Power Plants

no code implementations23 Jan 2024 Yixuan Sun, Sami Khairy, Richard B. Vilim, Rui Hu, Akshay J. Dave

In power plant control, one often needs to obtain a precise representation of the system dynamics and carefully design the control scheme accordingly.

reinforcement-learning Reinforcement Learning (RL) +1

Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering

no code implementations19 Jan 2024 Haibo Wang, Chenghang Lai, Yixuan Sun, Weifeng Ge

GCG learns multiple Gaussian functions to characterize the temporal structure of the video, and sample question-critical frames as positive moments to be the visual inputs of LMMs.

Question Answering Video Question Answering

Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?

1 code implementation28 Jul 2023 Romain Egele, Isabelle Guyon, Yixuan Sun, Prasanna Balaprakash

Hyperparameter optimization (HPO) is crucial for fine-tuning machine learning models but can be computationally expensive.

Hyperparameter Optimization

Weakly Supervised Learning of Semantic Correspondence through Cascaded Online Correspondence Refinement

1 code implementation ICCV 2023 Yiwen Huang, Yixuan Sun, Chenghang Lai, Qing Xu, Xiaomei Wang, Xuli Shen, Weifeng Ge

Following the spirit of multiple instance learning (MIL), we decompose the weakly supervised correspondence learning problem into three stages: image-level matching, region-level matching, and pixel-level matching.

Multiple Instance Learning Semantic correspondence +1

Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution

1 code implementation CVPR 2023 Yixuan Sun, Dongyang Zhao, Zhangyue Yin, Yiwen Huang, Tao Gui, Wenqiang Zhang, Weifeng Ge

The asymmetric feature learning module exploits a biased cross-attention mechanism to encode token features of source images with their target counterparts.

Super-Resolution

DeepGraphONet: A Deep Graph Operator Network to Learn and Zero-shot Transfer the Dynamic Response of Networked Systems

no code implementations21 Sep 2022 Yixuan Sun, Christian Moya, Guang Lin, Meng Yue

This paper develops a Deep Graph Operator Network (DeepGraphONet) framework that learns to approximate the dynamics of a complex system (e. g. the power grid or traffic) with an underlying sub-graph structure.

Zero-Shot Learning

A data-centric weak supervised learning for highway traffic incident detection

no code implementations17 Dec 2021 Yixuan Sun, Tanwi Mallick, Prasanna Balaprakash, Jane Macfarlane

To that end, we focus on a data-centric approach to improve the accuracy and reduce the false alarm rate of traffic incident detection on highways.

Uncertainty Quantification

A Survey of Human-in-the-loop for Machine Learning

no code implementations2 Aug 2021 Xingjiao Wu, Luwei Xiao, Yixuan Sun, Junhang Zhang, Tianlong Ma, Liang He

Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for computers in the pipeline with the help of machine-based approaches.

BIG-bench Machine Learning

Survey of the Detection and Classification of Pulmonary Lesions via CT and X-Ray

no code implementations31 Dec 2020 Yixuan Sun, Chengyao Li, Qian Zhang, Aimin Zhou, Guixu Zhang

In recent years, the prevalence of several pulmonary diseases, especially the coronavirus disease 2019 (COVID-19) pandemic, has attracted worldwide attention.

General Classification

Predicting Mechanical Properties from Microstructure Images in Fiber-reinforced Polymers using Convolutional Neural Networks

1 code implementation7 Oct 2020 Yixuan Sun, Imad Hanhan, Michael D. Sangid, Guang Lin

Evaluating the mechanical response of fiber-reinforced composites can be extremely time consuming and expensive.

Cannot find the paper you are looking for? You can Submit a new open access paper.