no code implementations • 24 Mar 2024 • Yifan Shi, Yuhui Zhang, Ziyue Huang, Xiaofeng Yang, Li Shen, Wei Chen, Xueqian Wang
Federated Split Learning (FSL) is a promising distributed learning paradigm in practice, which gathers the strengths of both Federated Learning (FL) and Split Learning (SL) paradigms, to ensure model privacy while diminishing the resource overhead of each client, especially on large transformer models in a resource-constrained environment, e. g., Internet of Things (IoT).
no code implementations • 19 Mar 2024 • Mingqi Shao, Feng Xiong, Hang Zhang, Shuang Yang, Mu Xu, Wei Bian, Xueqian Wang
The global stage obtains a continuous representation of the entire scene while the focal stage decomposes the scene into multiple blocks and further processes them with distinct sub-encoders.
no code implementations • 16 Mar 2024 • Zhuowei Li, Miao Zhang, Xiaotian Lin, Meng Yin, Shuai Lu, Xueqian Wang
This paper introduces GAgent: an Gripping Agent designed for open-world environments that provides advanced cognitive abilities via VLM agents and flexible grasping abilities with variable stiffness soft grippers.
1 code implementation • 13 Mar 2024 • Qinglong Meng, Chongkun Xia, Xueqian Wang
To implement PaddingFlow, only the dimension of normalizing flows needs to be modified.
Ranked #1 on Density Estimation on MNIST (MMD-L2 metric)
1 code implementation • 4 Mar 2024 • Chenyang Cao, Zichen Yan, Renhao Lu, Junbo Tan, Xueqian Wang
Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset.
no code implementations • 12 Feb 2024 • Haoyu Wang, Guozheng Ma, Ziqiao Meng, Zeyu Qin, Li Shen, Zhong Zhang, Bingzhe Wu, Liu Liu, Yatao Bian, Tingyang Xu, Xueqian Wang, Peilin Zhao
To further exploit the capabilities of bootstrapping, we investigate and adjust the training order of data, which yields improved performance of the model.
1 code implementation • 18 Jan 2024 • Qinglong Meng, Chongkun Xia, Xueqian Wang, Songping Mai, Bin Liang
The results show that PPNet can find a near-optimal solution in 15. 3ms, which is much shorter than the state-of-the-art path planners.
no code implementations • 20 Nov 2023 • Tiantian Zhang, Kevin Zehua Shen, Zichuan Lin, Bo Yuan, Xueqian Wang, Xiu Li, Deheng Ye
On the other hand, offline learning on replayed tasks while learning a new task may induce a distributional shift between the dataset and the learned policy on old tasks, resulting in forgetting.
no code implementations • 16 Oct 2023 • Lihui Xue, Zhihao Wang, Xueqian Wang, Gang Li
In addition, our method reduces more than 60% memory costs of the subsequent pixel-level CD processing stage.
1 code implementation • 16 Oct 2023 • Yuhong Deng, Xueqian Wang, Lipeng Chen
Our method reaches much higher success rates on a variety of deformable rearrangement tasks (96. 3% on average) than state-of-the-art method in simulation experiments.
1 code implementation • 11 Oct 2023 • Guozheng Ma, Lu Li, Sen Zhang, Zixuan Liu, Zhen Wang, Yixin Chen, Li Shen, Xueqian Wang, DaCheng Tao
Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL).
1 code implementation • 9 Oct 2023 • Longxiang He, Li Shen, Linrui Zhang, Junbo Tan, Xueqian Wang
Constrained policy search (CPS) is a fundamental problem in offline reinforcement learning, which is generally solved by advantage weighted regression (AWR).
no code implementations • 4 Oct 2023 • Zihao Lin, Yan Sun, Yifan Shi, Xueqian Wang, Lifu Huang, Li Shen, DaCheng Tao
With the blowout development of pre-trained models (PTMs), the efficient tuning of these models for diverse downstream applications has emerged as a pivotal research concern.
1 code implementation • 20 Sep 2023 • Haoyu Wang, Guozheng Ma, Cong Yu, Ning Gui, Linrui Zhang, Zhiqi Huang, Suwei Ma, Yongzhe Chang, Sen Zhang, Li Shen, Xueqian Wang, Peilin Zhao, DaCheng Tao
Notably, we are surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted.
1 code implementation • 21 Aug 2023 • Zixuan Liu, Liu Liu, Xueqian Wang, Peilin Zhao
Differentiable optimization has received a significant amount of attention due to its foundational role in the domain of machine learning based on neural networks.
no code implementations • 24 May 2023 • Yifan Shi, Yingqi Liu, Yan Sun, Zihao Lin, Li Shen, Xueqian Wang, DaCheng Tao
Personalized federated learning (PFL) aims to produce the greatest personalized model for each client to face an insurmountable problem--data heterogeneity in real FL systems.
no code implementations • 2 May 2023 • Yifan Shi, Kang Wei, Li Shen, Jun Li, Xueqian Wang, Bo Yuan, Song Guo
However, it suffers from issues in terms of communication, resource of MTs, and privacy.
1 code implementation • 1 May 2023 • Yifan Shi, Kang Wei, Li Shen, Yingqi Liu, Xueqian Wang, Bo Yuan, DaCheng Tao
To defend the inference attacks and mitigate the sensitive information leakages in Federated Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy protection by clipping local updates and adding random noise.
no code implementations • 3 Apr 2023 • Chengxi Li, Gang Li, Zhuoyue Wang, Xueqian Wang, Pramod K. Varshney
For this problem, an unsupervised change detection method has been proposed recently based on the image translation technique of Cycle-Consistent Adversarial Networks (CycleGANs), where one image is translated from its original modality to the modality of the other image so that the difference map can be obtained by performing arithmetical subtraction.
no code implementations • 30 Mar 2023 • Weiming Li, Xueqian Wang, Gang Li
Change detection (CD) in heterogeneous remote sensing images is a practical and challenging issue for real-life emergencies.
1 code implementation • CVPR 2023 • Yifan Shi, Yingqi Liu, Kang Wei, Li Shen, Xueqian Wang, DaCheng Tao
Specifically, DP-FedSAM integrates Sharpness Aware Minimization (SAM) optimizer to generate local flatness models with better stability and weight perturbation robustness, which results in the small norm of local updates and robustness to DP noise, thereby improving the performance.
no code implementations • 21 Feb 2023 • Yuhong Deng, Chongkun Xia, Xueqian Wang, Lipeng Chen
Rearranging deformable objects is a long-standing challenge in robotic manipulation for the high dimensionality of configuration space and the complex dynamics of deformable objects.
no code implementations • 21 Feb 2023 • Yuhong Deng, Chongkun Xia, Xueqian Wang, Lipeng Chen
Some research has been attempting to design a general framework to obtain more advanced manipulation capabilities for deformable rearranging tasks, with lots of progress achieved in simulation.
no code implementations • 8 Feb 2023 • Yifan Shi, Li Shen, Kang Wei, Yan Sun, Bo Yuan, Xueqian Wang, DaCheng Tao
To mitigate the privacy leakages and communication burdens of Federated Learning (FL), decentralized FL (DFL) discards the central server and each client only communicates with its neighbors in a decentralized communication network.
no code implementations • 28 Jan 2023 • Qin Zhang, Linrui Zhang, Haoran Xu, Li Shen, Bowen Wang, Yongzhe Chang, Xueqian Wang, Bo Yuan, DaCheng Tao
Offline safe RL is of great practical relevance for deploying agents in real-world applications.
1 code implementation • 8 Jan 2023 • Kai Mo, Chongkun Xia, Xueqian Wang, Yuhong Deng, Xuehai Gao, Bin Liang
Foldformer can complete multi-step cloth manipulation tasks even when configurations of the cloth (e. g., size and pose) vary from configurations in the general demonstrations.
no code implementations • 17 Dec 2022 • Zhecheng Yuan, Zhengrong Xue, Bo Yuan, Xueqian Wang, Yi Wu, Yang Gao, Huazhe Xu
Hence, we propose Pre-trained Image Encoder for Generalizable visual reinforcement learning (PIE-G), a simple yet effective framework that can generalize to the unseen visual scenarios in a zero-shot manner.
no code implementations • 14 Dec 2022 • Linrui Zhang, Zichen Yan, Li Shen, Shoujie Li, Xueqian Wang, DaCheng Tao
On the other hand, the safe agent mimics the baseline agent for policy improvement and learns to fulfill safety constraints via off-policy RL tuning.
no code implementations • 12 Dec 2022 • Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang, DaCheng Tao
Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those algorithms that adheres to safety constraints at each decision step under complex and unknown dynamics.
no code implementations • 30 Nov 2022 • Shoujie Li, Haixin Yu, Wenbo Ding, Houde Liu, Linqi Ye, Chongkun Xia, Xueqian Wang, Xiao-Ping Zhang
Here, a visual-tactile fusion framework for transparent object grasping under complex backgrounds and variant light conditions is proposed, including the grasping position detection, tactile calibration, and visual-tactile fusion based classification.
no code implementations • 14 Oct 2022 • Weiming Li, Lihui Xue, Xueqian Wang, Gang Li
For the task of change detection (CD) in remote sensing images, deep convolution neural networks (CNNs)-based methods have recently aggregated transformer modules to improve the capability of global feature extraction.
1 code implementation • 10 Oct 2022 • Guozheng Ma, Zhen Wang, Zhecheng Yuan, Xueqian Wang, Bo Yuan, DaCheng Tao
Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains.
no code implementations • 28 Sep 2022 • Zhengrong Xue, Zhecheng Yuan, Jiashun Wang, Xueqian Wang, Yang Gao, Huazhe Xu
Can a robot manipulate intra-category unseen objects in arbitrary poses with the help of a mere demonstration of grasping pose on a single object instance?
no code implementations • 1 Sep 2022 • Tiantian Zhang, Zichuan Lin, Yuxing Wang, Deheng Ye, Qiang Fu, Wei Yang, Xueqian Wang, Bin Liang, Bo Yuan, Xiu Li
A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information.
1 code implementation • 25 Aug 2022 • Mingqi Shao, Chongkun Xia, Dongxu Duan, Xueqian Wang
We build a polarization dataset for multi-view transparent shapes reconstruction to verify our method.
1 code implementation • 17 Jun 2022 • Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang
Safe reinforcement learning (RL) has achieved significant success on risk-sensitive tasks and shown promise in autonomous driving (AD) as well.
no code implementations • 24 May 2022 • Linrui Zhang, Li Shen, Long Yang, Shixiang Chen, Bo Yuan, Xueqian Wang, DaCheng Tao
Safe reinforcement learning aims to learn the optimal policy while satisfying safety constraints, which is essential in real-world applications.
1 code implementation • ICCV 2023 • Mingqi Shao, Chongkun Xia, Zhendong Yang, Junnan Huang, Xueqian Wang
To train and test our method, we construct a dataset for transparent shape from polarization with paired polarization images and ground-truth normal maps.
no code implementations • 14 Mar 2022 • Jiabao He, Xuan Zhang, Feng Xu, Junbo Tan, Xueqian Wang
Given the recent surge of interest in data-driven control, this paper proposes a two-step method to study robust data-driven control for a parameter-unknown linear time-invariant (LTI) system that is affected by energy-bounded noises.
1 code implementation • 21 Feb 2022 • Zhecheng Yuan, Guozheng Ma, Yao Mu, Bo Xia, Bo Yuan, Xueqian Wang, Ping Luo, Huazhe Xu
One of the key challenges in visual Reinforcement Learning (RL) is to learn policies that can generalize to unseen environments.
no code implementations • 1 Jan 2022 • Yuxing Wang, Tiantian Zhang, Yongzhe Chang, Bin Liang, Xueqian Wang, Bo Yuan
The integration of Reinforcement Learning (RL) and Evolutionary Algorithms (EAs) aims at simultaneously exploiting the sample efficiency as well as the diversity and robustness of the two paradigms.
no code implementations • 13 Dec 2021 • Yang Liu, Yongzhe Chang, Shilei Jiang, Xueqian Wang, Bin Liang, Bo Yuan
In general, IL methods can be categorized into Behavioral Cloning (BC) and Inverse Reinforcement Learning (IRL).
no code implementations • 7 Dec 2021 • Jiabao He, Xuan Zhang, Feng Xu, Junbo Tan, Xueqian Wang
For a parameter-unknown linear descriptor system, this paper proposes data-driven methods to testify the system's type and controllability and then to stabilize it.
no code implementations • 15 Oct 2021 • Chengqian Gao, Ke Xu, Kuangqi Zhou, Lanqing Li, Xueqian Wang, Bo Yuan, Peilin Zhao
To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm.
1 code implementation • 1 Sep 2021 • Tiantian Zhang, Xueqian Wang, Bin Liang, Bo Yuan
In this paper, we present IQ, i. e., interference-aware deep Q-learning, to mitigate catastrophic interference in single-task deep reinforcement learning.