no code implementations • 4 Feb 2025 • Haohan Zou, Jie Feng, Hao Zhao, Yuanyuan Shi
Despite advances in learning-based methods, finding valid Lyapunov functions for nonlinear dynamical systems remains challenging.
no code implementations • 16 Jan 2025 • Fengli Xu, Qianyue Hao, Zefang Zong, Jingwei Wang, Yunke Zhang, Jingyi Wang, Xiaochong Lan, Jiahui Gong, Tianjian Ouyang, Fanjin Meng, Chenyang Shao, Yuwei Yan, Qinglong Yang, Yiwen Song, Sijian Ren, Xinyuan Hu, Yu Li, Jie Feng, Chen Gao, Yong Li
This innovative paradigm enables LLMs' to mimic complex human reasoning processes, such as tree search and reflective thinking.
no code implementations • 3 Jan 2025 • Yao Ding, Weijie Kang, Aitao Yang, Zhili Zhang, Junyang Zhao, Jie Feng, Danfeng Hong, Qinhe Zheng
Meanwhile, homophily-enhanced structure learning is introduced to update the graph according to the clustering task, in which the orient correlation estimation is adopted to estimate the node connection, and graph edge sparsification is designed to adjust the edges in the graph dynamically.
no code implementations • 21 Nov 2024 • Jingtao Ding, Yunke Zhang, Yu Shang, Yuheng Zhang, Zefang Zong, Jie Feng, Yuan Yuan, Hongyuan Su, Nian Li, Nicholas Sukiennik, Fengli Xu, Yong Li
The concept of world models has garnered significant attention due to advancements in multimodal large language models such as GPT-4 and video generation models such as Sora, which are central to the pursuit of artificial general intelligence.
no code implementations • 12 Nov 2024 • Yuexin Bian, Jie Feng, Yuanyuan Shi
Real-world system control requires both high-performing and interpretable controllers.
no code implementations • 4 Nov 2024 • Mengmeng Yang, Chi-Hung Chi, Kwok-Yan Lam, Jie Feng, Taolin Guo, Wei Ni
This paper provides a comprehensive overview of existing differentially private tabular data synthesis methods, highlighting the unique challenges of each generation model for generating tabular data under differential privacy constraints.
1 code implementation • 27 Oct 2024 • Yuwei Du, Jie Feng, Jie Zhao, Yong Li
In TrajAgent, we first develop UniEnv, an execution environment with a unified data and model interface, to support the execution and training of various models.
no code implementations • 11 Oct 2024 • Yuwei Yan, Qingbin Zeng, Zhiheng Zheng, Jingzhe Yuan, Jie Feng, Jun Zhang, Fengli Xu, Yong Li
Besides, the substantial speedup of OpenCity allows us to establish a urban simulation benchmark for LLM agents for the first time, comparing simulated urban activities with real-world data in 6 major cities around the globe.
no code implementations • 29 Sep 2024 • Yiming Zhao, Dewen Guo, Zhouhui Lian, Yue Gao, Jianhong Han, Jie Feng, Guoping Wang, Bingfeng Zhou, Sheng Li
To bridge the gap between artists and non-specialists, we present a unified framework, Neural-Polyptych, to facilitate the creation of expansive, high-resolution paintings by seamlessly incorporating interactive hand-drawn sketches with fragments from original paintings.
1 code implementation • 27 Aug 2024 • Jie Feng, Wenqi Cui, Jorge Cortés, Yuanyuan Shi
The increasing integration of renewable energy resources into power grids has led to time-varying system inertia and consequent degradation in frequency dynamics.
1 code implementation • 26 Aug 2024 • Jie Feng, Yuwei Du, Jie Zhao, Yong Li
In AgentMove, we first decompose the mobility prediction task into three sub-tasks and then design corresponding modules to complete these subtasks, including spatial-temporal memory for individual mobility pattern mining, world knowledge generator for modeling the effects of urban structure and collective knowledge extractor for capturing the shared patterns among population.
1 code implementation • 23 Aug 2024 • Songwei Li, Jie Feng, Jiawei Chi, Xinyuan Hu, Xiaomeng Zhao, Fengli Xu
Moreover, we propose a transformer-based intention-aware mobility prediction model to effectively harness the intention inference ability of LLM.
1 code implementation • 10 Aug 2024 • Xiuyu Sun, Xiaohui Zhong, Xiaoze Xu, Yuanqing Huang, Hao Li, J. David Neelin, Deliang Chen, Jie Feng, Wei Han, Libo Wu, Yuan Qi
Weather forecasting traditionally relies on numerical weather prediction (NWP) systems that integrates global observational systems, data assimilation (DA), and forecasting models.
1 code implementation • 16 Jul 2024 • Yu Shang, Yuming Lin, Yu Zheng, Hangyu Fan, Jingtao Ding, Jie Feng, Jiansheng Chen, Li Tian, Yong Li
Toward this problem, we propose UrbanWorld, the first generative urban world model that can automatically create a customized, realistic and interactive 3D urban world with flexible control conditions.
1 code implementation • 21 Jun 2024 • Jie Feng, Haohan Zou, Yuanyuan Shi
This framework contains a neural Lyapunov function and a symbolic regression component, where symbolic regression is applied to distill the neural network to precise analytical forms.
1 code implementation • 20 Jun 2024 • Jie Feng, Jun Zhang, Tianhui Liu, Xin Zhang, Tianjian Ouyang, Junbo Yan, Yuwei Du, Siqi Guo, Yong Li
The challenge in constructing a systematic evaluation benchmark for urban research lies in the diversity of urban data, the complexity of application scenarios and the highly dynamic nature of the urban environment.
1 code implementation • 20 Jun 2024 • Jie Feng, Yuwei Du, Tianhui Liu, Siqi Guo, Yuming Lin, Yong Li
In this paper, we propose CityGPT, a systematic framework for enhancing the capability of LLMs on understanding urban space and solving the related urban tasks by building a city-scale world model in the model.
no code implementations • 20 Jun 2024 • Yile Liang, Jiuxia Zhao, Donghui Li, Jie Feng, Chen Zhang, Xuetao Ding, Jinghua Hao, Renqing He
In OFD, pooling multiple orders for simultaneous delivery in real-time order assignment is a pivotal efficiency source, which may in turn extend delivery time.
no code implementations • 12 Jun 2024 • Jie Feng, Xiaojian Zhong, Di Li, Weisheng Dong, Ronghua Shang, Licheng Jiao
However, most existing deep learning-based methods are aimed at dealing with a specific band selection dataset, and need to retrain parameters for new datasets, which significantly limits their generalizability. To address this issue, a novel multi-teacher multi-objective meta-learning network (M$^3$BS) is proposed for zero-shot hyperspectral band selection.
no code implementations • 30 May 2024 • Jie Feng, Manasa Muralidharan, Rodrigo Henriquez-Auba, Patricia Hidalgo-Gonzalez, Yuanyuan Shi
We test the proposed control on a 12-bus 3-area test network, and compare its performance with a base case linear controller, optimized linear controller, and finite-horizon Linear Quadratic Regulator (LQR).
no code implementations • 9 May 2024 • Xiaohui Zhong, Lei Chen, Hao Li, Jun Liu, Xu Fan, Jie Feng, Kan Dai, Jing-Jia Luo, Jie Wu, Bo Lu
This innovative approach makes FuXi-ENS an advancement over the traditional ones that use L1 loss combined with the KL loss in standard VAE models for ensemble weather forecasting.
no code implementations • 3 Mar 2024 • Jie Feng, Hao Huang, Junpeng Zhang, Weisheng Dong, Dingwen Zhang, Licheng Jiao
To eliminate the reliance on such priors, we propose a novel Structure-aware Mixup and Invariance Learning framework (SA-MixNet) for weakly supervised road extraction that improves the model invariance in a data-driven manner.
1 code implementation • 19 Feb 2024 • Yuan Yuan, Jingtao Ding, Jie Feng, Depeng Jin, Yong Li
Urban spatio-temporal prediction is crucial for informed decision-making, such as traffic management, resource optimization, and emergence response.
no code implementations • 2 Jan 2024 • Jie Feng, Ke Wei, Jinchi Chen
Natural policy gradient (NPG) and its variants are widely-used policy search methods in reinforcement learning.
1 code implementation • 19 Dec 2023 • Fengli Xu, Jun Zhang, Chen Gao, Jie Feng, Yong Li
Urban environments, characterized by their complex, multi-layered networks encompassing physical, social, economic, and environmental dimensions, face significant challenges in the face of rapid urbanization.
1 code implementation • 21 Nov 2023 • Ruimin Feng, Qing Wu, Jie Feng, Huajun She, Chunlei Liu, Yuyao Zhang, Hongjiang Wei
Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms.
no code implementations • 20 Mar 2023 • Jie Feng, Wenqi Cui, Jorge Cortés, Yuanyuan Shi
Deep reinforcement learning approaches are becoming appealing for the design of nonlinear controllers for voltage control problems, but the lack of stability guarantees hinders their deployment in real-world scenarios.
no code implementations • 31 Dec 2022 • Jie Feng, Ruimin Feng, Qing Wu, Zhiyong Zhang, Yuyao Zhang, Hongjiang Wei
The high-quality and inner continuity of the images provided by INR has great potential to further improve the spatiotemporal resolution of dynamic MRI, without the need of any training data.
1 code implementation • 15 Dec 2022 • Yanan Wu, Shuiqing Zhao, Shouliang Qi, Jie Feng, Haowen Pang, Runsheng Chang, Long Bai, Mengqi Li, Shuyue Xia, Wei Qian, Hongliang Ren
In the first stage, the total airway mask and CT images are provided to the subnetwork, and the intrapulmonary airway mask and corresponding CT scans to the subnetwork in the second stage.
1 code implementation • 16 Sep 2022 • Jie Feng, Yuanyuan Shi, Guannan Qu, Steven H. Low, Anima Anandkumar, Adam Wierman
In this paper, we propose a stability-constrained reinforcement learning (RL) method for real-time voltage control, that guarantees system stability both during policy learning and deployment of the learned policy.
no code implementations • 2 Jun 2022 • Jianhong Han, Zhaoyi Wan, Zhe Liu, Jie Feng, Bingfeng Zhou
We believe this end-to-end paradigm of SparseDet will inspire new thinking on the sparsity of 3D object detection.
1 code implementation • 13 Aug 2021 • Erzhuo Shao, Jie Feng, Yingheng Wang, Tong Xia, Yong Li
Thus, obtaining fine-grained population distribution from coarse-grained distribution becomes an important problem.
no code implementations • 8 Jun 2021 • Rongmei Lin, Xiang He, Jie Feng, Nasser Zalmout, Yan Liang, Li Xiong, Xin Luna Dong
Understanding product attributes plays an important role in improving online shopping experience for customers and serves as an integral part for constructing a product knowledge graph.
1 code implementation • 30 Apr 2021 • Fuxian Li, Jie Feng, Huan Yan, Guangyin Jin, Depeng Jin, Yong Li
Additionally, there is a severe lack of fair comparison among different methods on the same datasets.
Ranked #2 on
Traffic Prediction
on NE-BJ
1 code implementation • 21 Jan 2021 • Ruimin Feng, Jiayi Zhao, He Wang, Baofeng Yang, Jie Feng, Yuting Shi, Ming Zhang, Chunlei Liu, Yuyao Zhang, Jie Zhuang, Hongjiang Wei
However, there exists a mismatch between the observed phase and the theoretical forward phase estimated by the susceptibility label.
no code implementations • 3 Jan 2021 • Tong Xia, Yunhan Qi, Jie Feng, Fengli Xu, Funing Sun, Diansheng Guo, Yong Li
A considerable amount of mobility data has been accumulated due to the proliferation of location-based service.
no code implementations • 19 Aug 2020 • Yueyang Wang, Ziheng Duan, Yida Huang, Haoyan Xu, Jie Feng, Anni Ren
To characterize complex relations among variables, a relation embedding module is designed in MTHetGNN, where each variable is regarded as a graph node, and each type of edge represents a specific static or dynamic relationship.
no code implementations • 18 Aug 2020 • Yifu Zhou, Ziheng Duan, Haoyan Xu, Jie Feng, Anni Ren, Yueyang Wang, Xiaoqian Wang
In this paper, a MTS forecasting framework that can capture the long-term trends and short-term fluctuations of time series in parallel is proposed.
no code implementations • 26 May 2020 • XiangJi Wu, Ziwen Zhang, Jie Feng, Lei Zhou, Junmin Wu
We present an end-to-end trainable framework for P-frame compression in this paper.
no code implementations • 16 May 2020 • Haoyan Xu, Ziheng Duan, Jie Feng, Runjian Chen, Qianru Zhang, Zhongbin Xu, Yueyang Wang
Next, a novel graph neural network with an attention mechanism is designed to map each subgraph into an embedding vector.
no code implementations • 14 May 2020 • Haoyan Xu, Runjian Chen, Yueyang Wang, Ziheng Duan, Jie Feng
In this paper, we focus on similarity computation for large-scale graphs and propose the "embedding-coarsening-matching" framework CoSimGNN, which first embeds and coarsens large graphs with adaptive pooling operation and then deploys fine-grained interactions on the coarsened graphs for final similarity scores.
2 code implementations • 3 May 2020 • Ziheng Duan, Haoyan Xu, Yida Huang, Jie Feng, Yueyang Wang
Multivariate time series (MTS) forecasting is an essential problem in many fields.
no code implementations • Remote Sensing 2020 • Jie Feng, Xueliang Feng, Jiantong Chen, Xianghai Cao, Xiangrong Zhang, Licheng Jiao, Tao Yu
To address this problem, a symmetric convolutional GAN based on collaborative learning and attention mechanism (CA-GAN) is proposed.
Ranked #7 on
Hyperspectral Image Classification
on Indian Pines
Few-Shot Image Classification
Generative Adversarial Network
+2
1 code implementation • 1 Dec 2019 • Bo Li, Jie Feng, Bingfeng Zhou
We present a pipeline for modeling spatially varying BRDFs (svBRDFs) of planar materials which only requires a mobile phone for data acquisition.
Graphics
1 code implementation • 12 May 2019 • Guanjie Zheng, Yuanhao Xiong, Xinshi Zang, Jie Feng, Hua Wei, Huichu Zhang, Yong Li, Kai Xu, Zhenhui Li
Increasingly available city data and advanced learning techniques have empowered people to improve the efficiency of our city functions.
no code implementations • 25 Oct 2018 • Zefang Zong, Jie Feng, Kechun Liu, Hongzhi Shi, Yong Li
In this paper, we first propose the idea to generate dynamic population distributions in full-time series, then we design dynamic population mapping via deep neural network(DeepDPM), a model that describes both spatial and temporal patterns using coarse data and point of interest information.
no code implementations • 16 Jun 2016 • Jie Feng, Svebor Karaman, I-Hong Jhuo, Shih-Fu Chang
Learning-based hashing is often used in large scale image retrieval as they provide a compact representation of each sample and the Hamming distance can be used to efficiently compare two samples.
no code implementations • CVPR 2016 • Jie Feng, Brian Price, Scott Cohen, Shih-Fu Chang
While these methods achieve better results than color-based methods, they are still limited in either using depth as an additional color channel or simply combining depth with color in a linear way.
no code implementations • 21 Oct 2014 • Jie Feng, Wei Liu, Yan Wang
Binary codes have been widely used in vision problems as a compact feature representation to achieve both space and time advantages.