Search Results for author: Yulin Wu

Found 14 papers, 3 papers with code

BeMERC: Behavior-Aware MLLM-based Framework for Multimodal Emotion Recognition in Conversation

no code implementations31 Mar 2025 Yumeng Fu, Junjie Wu, Zhongjie Wang, Meishan Zhang, Yulin Wu, Bingquan Liu

Multimodal emotion recognition in conversation (MERC), the task of identifying the emotion label for each utterance in a conversation, is vital for developing empathetic machines.

Emotion Recognition in Conversation Multimodal Emotion Recognition

MKDTI: Predicting drug-target interactions via multiple kernel fusion on graph attention network

no code implementations14 Jul 2024 Yuhuan Zhou, Yulin Wu, Weiwei Yuan, Xuan Wang, Junyi Li

In our work, we formulate a model called MKDTI by extracting kernel information from various layer embeddings of a graph attention network.

Graph Attention

KnobTree: Intelligent Database Parameter Configuration via Explainable Reinforcement Learning

no code implementations21 Jun 2024 Jiahan Chen, Shuhan Qi, YiFan Li, Zeyu Dong, Mingfeng Ding, Yulin Wu, Xuan Wang

However, due to black-box property of RL-based method, the generated database tuning strategies still face the urgent problem of lack explainability.

Decision Making Deep Reinforcement Learning +1

GridPE: Unifying Positional Encoding in Transformers with a Grid Cell-Inspired Framework

no code implementations11 Jun 2024 Boyang Li, Yulin Wu, Nuoxian Huang, Wenjia Zhang

In this paper, we introduce a novel positional encoding scheme inspired by Fourier analysis and the latest findings in computational neuroscience regarding grid cells.

Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems

no code implementations23 Apr 2024 Xiaoshuang Chen, Gengrui Zhang, Yao Wang, Yulin Wu, Shuo Su, Kaiqiao Zhan, Ben Wang

The recommendation with a cache is a solution to this problem, where a user-wise result cache is used to provide recommendations when the recommender system cannot afford a real-time computation.

Recommendation Systems reinforcement-learning +1

Privacy-Preserving Distributed Machine Learning Made Faster

no code implementations12 May 2022 Zoe L. Jiang, Jiajing Gu, Hongxiao Wang, Yulin Wu, Junbin Fang, Siu-Ming Yiu, Wenjian Luo, Xuan Wang

So machine learning tasks need to be spread across multiple servers, turning the centralized machine learning into a distributed one.

BIG-bench Machine Learning Privacy Preserving

Multi-Graph based Multi-Scenario Recommendation in Large-scale Online Video Services

no code implementations5 May 2022 Fan Zhang, Qiuying Peng, Yulin Wu, Zheng Pan, Rong Zeng, Da Lin, Yue Qi

Recently, industrial recommendation services have been boosted by the continual upgrade of deep learning methods.

Data Integration Graph Learning

Stock Market Trend Analysis Using Hidden Markov Model and Long Short Term Memory

1 code implementation20 Apr 2021 Mingwen Liu, Junbang Huo, Yulin Wu, Jinge Wu

This paper intends to apply the Hidden Markov Model into stock market and and make predictions.

Quantum walks on a programmable two-dimensional 62-qubit superconducting processor

no code implementations4 Feb 2021 Ming Gong, Shiyu Wang, Chen Zha, Ming-Cheng Chen, He-Liang Huang, Yulin Wu, Qingling Zhu, YouWei Zhao, Shaowei Li, Shaojun Guo, Haoran Qian, Yangsen Ye, Fusheng Chen, Jiale Yu, Daojing Fan, Dachao Wu, Hong Su, Hui Deng, Hao Rong, Jin Lin, Yu Xu, Lihua Sun, Cheng Guo, Futian Liang, Kae Nemoto, W. J. Munro, Chao-Yang Lu, Cheng-Zhi Peng, Xiaobo Zhu, Jian-Wei Pan

Quantum walks are the quantum mechanical analogue of classical random walks and an extremely powerful tool in quantum simulations, quantum search algorithms, and even for universal quantum computing.

Quantum Physics

Experimental characterization of quantum many-body localization transition

no code implementations21 Dec 2020 Ming Gong, Gentil D. de Moraes Neto, Chen Zha, Yulin Wu, Hao Rong, Yangsen Ye, Shaowei Li, Qingling Zhu, Shiyu Wang, YouWei Zhao, Futian Liang, Jin Lin, Yu Xu, Cheng-Zhi Peng, Hui Deng, Abolfazl Bayat, Xiaobo Zhu, Jian-Wei Pan

Here, we experimentally implement a scalable protocol for detecting the many-body localization transition point, using the dynamics of a $N=12$ superconducting qubit array.

Quantum Physics Mesoscale and Nanoscale Physics Strongly Correlated Electrons

RLCFR: Minimize Counterfactual Regret by Deep Reinforcement Learning

no code implementations10 Sep 2020 Huale Li, Xuan Wang, Fengwei Jia, Yi-Fan Li, Yulin Wu, Jiajia Zhang, Shuhan Qi

Extensive experimental results on various games have shown that the generalization ability of our method is significantly improved compared with existing state-of-the-art methods.

counterfactual Decision Making +3

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