Zobrazeno 1 - 10
of 726
pro vyhledávání: '"LI Boyu"'
This paper explores the representational structure of linear Simple Cycle Reservoirs (SCR) operating at the edge of stability. We view SCR as providing in their state space feature representations of the input-driving time series. By endowing the sta
Externí odkaz:
http://arxiv.org/abs/2412.00295
Recently, multimodal large language models (MLLMs) have demonstrated strong visual understanding and decision-making capabilities, enabling the exploration of autonomously improving MLLMs in unknown environments. However, external feedback like human
Externí odkaz:
http://arxiv.org/abs/2410.03303
Reservoir Computing (RC) models, a subclass of recurrent neural networks, are distinguished by their fixed, non-trainable input layer and dynamically coupled reservoir, with only the static readout layer being trained. This design circumvents the iss
Externí odkaz:
http://arxiv.org/abs/2408.08071
Autor:
Fang, Zhirui, Yang, Ming, Zeng, Weishuai, Li, Boyu, Yue, Junpeng, Ding, Ziluo, Li, Xiu, Lu, Zongqing
We explore leveraging large multi-modal models (LMMs) and text2image models to build a more general embodied agent. LMMs excel in planning long-horizon tasks over symbolic abstractions but struggle with grounding in the physical world, often failing
Externí odkaz:
http://arxiv.org/abs/2408.05802
The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, the colossal scale of LLM presents significant operational challenges, pa
Externí odkaz:
http://arxiv.org/abs/2407.21325
The classical temporal point process (TPP) constructs an intensity function by taking the occurrence times into account. Nevertheless, occurrence time may not be the only relevant factor, other contextual data, termed covariates, may also impact the
Externí odkaz:
http://arxiv.org/abs/2407.16161
Training latency is critical for the success of numerous intrigued applications ignited by federated learning (FL) over heterogeneous mobile devices. By revolutionarily overlapping local gradient transmission with continuous local computing, FL can r
Externí odkaz:
http://arxiv.org/abs/2407.00943
Autor:
Duwenig, Anna, Li, Boyu
We define and study the external and the internal Zappa-Sz\'{e}p product of twists over groupoids. We determine when a pair $(\Sigma_{1},\Sigma_{2})$ of twists over a matched pair $(\mathcal{G}_{1},\mathcal{G}_{2})$ of groupoids gives rise to a Zappa
Externí odkaz:
http://arxiv.org/abs/2406.00466
Autor:
Tan, Weihao, Zhang, Wentao, Xu, Xinrun, Xia, Haochong, Ding, Ziluo, Li, Boyu, Zhou, Bohan, Yue, Junpeng, Jiang, Jiechuan, Li, Yewen, An, Ruyi, Qin, Molei, Zong, Chuqiao, Zheng, Longtao, Wu, Yujie, Chai, Xiaoqiang, Bi, Yifei, Xie, Tianbao, Gu, Pengjie, Li, Xiyun, Zhang, Ceyao, Tian, Long, Wang, Chaojie, Wang, Xinrun, Karlsson, Börje F., An, Bo, Yan, Shuicheng, Lu, Zongqing
Despite the success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encapsulations of environments with manually designed observation and action
Externí odkaz:
http://arxiv.org/abs/2403.03186
Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques. As a novel design paradigm that separates training and inference, a structural re-parameterized (SR) network
Externí odkaz:
http://arxiv.org/abs/2402.07200