Zobrazeno 1 - 10
of 138
pro vyhledávání: '"Shen, Chaomin"'
Knowledge distillation has become widely recognized for its ability to transfer knowledge from a large teacher network to a compact and more streamlined student network. Traditional knowledge distillation methods primarily follow a teacher-oriented p
Externí odkaz:
http://arxiv.org/abs/2409.18785
Knowledge distillation (KD), known for its ability to transfer knowledge from a cumbersome network (teacher) to a lightweight one (student) without altering the architecture, has been garnering increasing attention. Two primary categories emerge with
Externí odkaz:
http://arxiv.org/abs/2409.18565
Autor:
Zhu, Minjie, Zhu, Yichen, Li, Jinming, Wen, Junjie, Xu, Zhiyuan, Liu, Ning, Cheng, Ran, Shen, Chaomin, Peng, Yaxin, Feng, Feifei, Tang, Jian
Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model size woul
Externí odkaz:
http://arxiv.org/abs/2409.14411
Autor:
Wen, Junjie, Zhu, Yichen, Li, Jinming, Zhu, Minjie, Wu, Kun, Xu, Zhiyuan, Liu, Ning, Cheng, Ran, Shen, Chaomin, Peng, Yaxin, Feng, Feifei, Tang, Jian
Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and
Externí odkaz:
http://arxiv.org/abs/2409.12514
Blasted rock material serves a critical role in various engineering applications, yet the phenomenon of segregation-where particle sizes vary significantly along the gradient of a quarry pile-presents challenges for optimizing quarry material storage
Externí odkaz:
http://arxiv.org/abs/2406.04149
Autor:
Zhu, Minjie, Zhu, Yichen, Liu, Xin, Liu, Ning, Xu, Zhiyuan, Shen, Chaomin, Peng, Yaxin, Ou, Zhicai, Feng, Feifei, Tang, Jian
Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the training and inf
Externí odkaz:
http://arxiv.org/abs/2403.06199
Autor:
Zhu, Minjie, Zhu, Yichen, Li, Jinming, Wen, Junjie, Xu, Zhiyuan, Che, Zhengping, Shen, Chaomin, Peng, Yaxin, Liu, Dong, Feng, Feifei, Tang, Jian
The language-conditioned robotic manipulation aims to transfer natural language instructions into executable actions, from simple pick-and-place to tasks requiring intent recognition and visual reasoning. Inspired by the dual process theory in cognit
Externí odkaz:
http://arxiv.org/abs/2401.04181
Autor:
Wen, Junjie, Zhu, Yichen, Zhu, Minjie, Li, Jinming, Xu, Zhiyuan, Che, Zhengping, Shen, Chaomin, Peng, Yaxin, Liu, Dong, Feng, Feifei, Tang, Jian
Humans interpret scenes by recognizing both the identities and positions of objects in their observations. For a robot to perform tasks such as \enquote{pick and place}, understanding both what the objects are and where they are located is crucial. W
Externí odkaz:
http://arxiv.org/abs/2401.02814
Autor:
Wang, Wanying, Zhu, Yichen, Zhou, Yirui, Shen, Chaomin, Tang, Jian, Xu, Zhiyuan, Peng, Yaxin, Zhang, Yangchun
Generative Adversarial Imitation Learning (GAIL) stands as a cornerstone approach in imitation learning. This paper investigates the gradient explosion in two types of GAIL: GAIL with deterministic policy (DE-GAIL) and GAIL with stochastic policy (ST
Externí odkaz:
http://arxiv.org/abs/2312.11214
Autor:
Wei, Mingze, Huang, Yaomin, Xu, Zhiyuan, Liu, Ning, Che, Zhengping, Zhang, Xinyu, Shen, Chaomin, Feng, Feifei, Shan, Chun, Tang, Jian
In this paper, we propose a novel representation for grasping using contacts between multi-finger robotic hands and objects to be manipulated. This representation significantly reduces the prediction dimensions and accelerates the learning process. W
Externí odkaz:
http://arxiv.org/abs/2303.13182