no code implementations • 31 Dec 2024 • Yipeng Kang, Junqi Wang, Yexin Li, Fangwei Zhong, Xue Feng, Mengmeng Wang, Wenming Tu, Quansen Wang, Hengli Li, Zilong Zheng
As large language models (LLMs) become increasingly integrated into critical applications, aligning their behavior with human values presents significant challenges.
no code implementations • 30 Dec 2024 • Fangwei Zhong, Kui Wu, Churan Wang, Hao Chen, Hai Ci, Zhoujun Li, Yizhou Wang
We introduce UnrealZoo, a rich collection of photo-realistic 3D virtual worlds built on Unreal Engine, designed to reflect the complexity and variability of the open worlds.
no code implementations • 9 Dec 2024 • Yiding Wang, Yuxuan Chen, Fangwei Zhong, Long Ma, Yizhou Wang
Existing task-oriented AI agents often depend on explicit instructions or external rewards, limiting their ability to be driven by intrinsic motivations like humans.
1 code implementation • 9 Jul 2024 • Zhenyu Guan, Xiangyu Kong, Fangwei Zhong, Yizhou Wang
Diplomacy is one of the most sophisticated activities in human society, involving complex interactions among multiple parties that require skills in social reasoning, negotiation, and long-term strategic planning.
no code implementations • 3 May 2024 • Qian Long, Fangwei Zhong, Mingdong Wu, Yizhou Wang, Song-Chun Zhu
Multi-agent systems (MAS) need to adaptively cope with dynamic environments, changing agent populations, and diverse tasks.
no code implementations • 15 Apr 2024 • Fangwei Zhong, Kui Wu, Hai Ci, Churan Wang, Hao Chen
The results show that our agent outperforms state-of-the-art methods in terms of sample efficiency, robustness to distractors, and generalization to unseen scenarios and targets.
no code implementations • 4 Feb 2024 • Long Ma, Yuanfei Wang, Fangwei Zhong, Song-Chun Zhu, Yizhou Wang
To do so, it is crucial for the agent to probe and identify the peer's strategy efficiently, as this is the prerequisite for carrying out the best response in adaptation.
no code implementations • 7 Apr 2023 • Fangwei Zhong, Xiao Bi, Yudi Zhang, Wei zhang, Yizhou Wang
However, building a generalizable active tracker that works robustly across different scenarios remains a challenge, especially in unstructured environments with cluttered obstacles and diverse layouts.
no code implementations • 7 Mar 2023 • Hai Ci, Mickel Liu, Xuehai Pan, Fangwei Zhong, Yizhou Wang
This paper presents a multi-agent reinforcement learning (MARL) scheme for proactive Multi-Camera Collaboration in 3D Human Pose Estimation in dynamic human crowds.
1 code implementation • CVPR 2023 • Hai Ci, Mingdong Wu, Wentao Zhu, Xiaoxuan Ma, Hao Dong, Fangwei Zhong, Yizhou Wang
During the denoising process, GFPose implicitly incorporates pose priors in gradients and unifies various discriminative and generative tasks in an elegant framework.
no code implementations • 2 Sep 2022 • Mingdong Wu, Fangwei Zhong, Yulong Xia, Hao Dong
For object rearrangement, the TarGF can be used in two ways: 1) For model-based planning, we can cast the target gradient into a reference control and output actions with a distributed path planner; 2) For model-free reinforcement learning, the TarGF is not only used for estimating the likelihood-change as a reward but also provides suggested actions in residual policy learning.
no code implementations • 4 Mar 2022 • Tianhao Wu, Fangwei Zhong, Yiran Geng, Hongchen Wang, Yongjian Zhu, Yizhou Wang, Hao Dong
we formulate the dynamic grasping problem as a 'move-and-grasp' game, where the robot is to pick up the object on the mover and the adversarial mover is to find a path to escape it.
1 code implementation • NeurIPS 2021 • Yuanfei Wang, Fangwei Zhong, Jing Xu, Yizhou Wang
With ToM, each agent is capable of inferring the mental states and intentions of others according to its (local) observation.
no code implementations • 18 Jun 2021 • Fangwei Zhong, Peng Sun, Wenhan Luo, Tingyun Yan, Yizhou Wang
In active visual tracking, it is notoriously difficult when distracting objects appear, as distractors often mislead the tracker by occluding the target or bringing a confusing appearance.
1 code implementation • NeurIPS 2020 • Jing Xu, Fangwei Zhong, Yizhou Wang
Maximum target coverage by adjusting the orientation of distributed sensors is an important problem in directional sensor networks (DSNs).
no code implementations • 15 Jan 2020 • Jing Li, Jing Xu, Fangwei Zhong, Xiangyu Kong, Yu Qiao, Yizhou Wang
In the system, each camera is equipped with two controllers and a switcher: The vision-based controller tracks targets based on observed images.
no code implementations • ICLR 2019 • Fangwei Zhong, Peng Sun, Wenhan Luo, Tingyun Yan, Yizhou Wang
In AD-VAT, both the tracker and the target are approximated by end-to-end neural networks, and are trained via RL in a dueling/competitive manner: i. e., the tracker intends to lockup the target, while the target tries to escape from the tracker.
1 code implementation • CVPR 2019 • Yiming Zuo, Weichao Qiu, Lingxi Xie, Fangwei Zhong, Yizhou Wang, Alan L. Yuille
We also construct a vision-based control system for task accomplishment, for which we train a reinforcement learning agent in a virtual environment and apply it to the real-world.
no code implementations • 10 Aug 2018 • Wenhan Luo, Peng Sun, Fangwei Zhong, Wei Liu, Tong Zhang, Yizhou Wang
We further propose an environment augmentation technique and a customized reward function, which are crucial for successful training.
no code implementations • ICML 2018 • Wenhan Luo, Peng Sun, Fangwei Zhong, Wei Liu, Tong Zhang, Yizhou Wang
We study active object tracking, where a tracker takes as input the visual observation (i. e., frame sequence) and produces the camera control signal (e. g., move forward, turn left, etc.).