Zobrazeno 1 - 10
of 1 431
pro vyhledávání: '"Liu, Jinxin"'
In this paper, we propose a novel approach called DIffusion-guided DIversity (DIDI) for offline behavioral generation. The goal of DIDI is to learn a diverse set of skills from a mixture of label-free offline data. We achieve this by leveraging diffu
Externí odkaz:
http://arxiv.org/abs/2405.14790
As a data-driven paradigm, offline reinforcement learning (RL) has been formulated as sequence modeling that conditions on the hindsight information including returns, goal or future trajectory. Although promising, this supervised paradigm overlooks
Externí odkaz:
http://arxiv.org/abs/2405.08740
Across a wide range of hardware scenarios, the computational efficiency and physical size of the arithmetic units significantly influence the speed and footprint of the overall hardware system. Nevertheless, the effectiveness of prior arithmetic desi
Externí odkaz:
http://arxiv.org/abs/2405.06758
Two-dimensional conjugated metal–organic frameworks (2D c-MOFs), possessing extended π–d conjugated planar structure, are emerging as a unique class of electronic materials due to their intrinsic electrical conductivities. Taking advantage of th
Externí odkaz:
https://tud.qucosa.de/id/qucosa%3A91208
https://tud.qucosa.de/api/qucosa%3A91208/attachment/ATT-0/
https://tud.qucosa.de/api/qucosa%3A91208/attachment/ATT-0/
Autor:
Liu, Jinxin, Chen, Yunxu, Huang, Xing, Ren, Yanhan, Hambsch, Mike, Bodesheim, David, Pohl, Darius, Li, Xiaodong, Deconinck, Marielle, Zhang, Bowen, Löffler, Markus, Liao, Zhongquan, Zhao, Fengxiang, Dianat, Arezoo, Cuniberti, Gianaurelio, Vaynzof, Yana, Gao, Junfeng, Hao, Jingcheng, Mannsfeld, Stefan C. B., Feng, Xinliang, Dong, Renhao
Conductive metal-organic frameworks (MOFs) are emerging electroactive materials for (opto-)electronics. However, it remains a great challenge to achieve reliable MOF-based devices via the existing synthesis methods that are compatible with the comple
Externí odkaz:
http://arxiv.org/abs/2404.15357
This paper proposes an adaptive behavioral decision-making method for autonomous vehicles (AVs) focusing on complex merging scenarios. Leveraging principles from non-cooperative game theory, we develop a vehicle interaction behavior model that define
Externí odkaz:
http://arxiv.org/abs/2402.11467
Autor:
Vakili, Mohammad Ghazi, Gorgulla, Christoph, Nigam, AkshatKumar, Bezrukov, Dmitry, Varoli, Daniel, Aliper, Alex, Polykovsky, Daniil, Das, Krishna M. Padmanabha, Snider, Jamie, Lyakisheva, Anna, Mansob, Ardalan Hosseini, Yao, Zhong, Bitar, Lela, Radchenko, Eugene, Ding, Xiao, Liu, Jinxin, Meng, Fanye, Ren, Feng, Cao, Yudong, Stagljar, Igor, Aspuru-Guzik, Alán, Zhavoronkov, Alex
The discovery of small molecules with therapeutic potential is a long-standing challenge in chemistry and biology. Researchers have increasingly leveraged novel computational techniques to streamline the drug development process to increase hit rates
Externí odkaz:
http://arxiv.org/abs/2402.08210
Autor:
Zhang, Ziqi, Xu, Jingzehua, Liu, Jinxin, Zhuang, Zifeng, Wang, Donglin, Liu, Miao, Zhang, Shuai
Offline reinforcement learning (RL) algorithms can learn better decision-making compared to behavior policies by stitching the suboptimal trajectories to derive more optimal ones. Meanwhile, Decision Transformer (DT) abstracts the RL as sequence mode
Externí odkaz:
http://arxiv.org/abs/2401.16452
We propose Deep Dict, a deep learning-based lossy time series compressor designed to achieve a high compression ratio while maintaining decompression error within a predefined range. Deep Dict incorporates two essential components: the Bernoulli tran
Externí odkaz:
http://arxiv.org/abs/2401.10396
Autor:
Liu, Jinxin, Cao, Shulin, Shi, Jiaxin, Zhang, Tingjian, Nie, Lunyiu, Hu, Linmei, Hou, Lei, Li, Juanzi
Knowledge Base Question Answering (KBQA) aims to answer natural language questions based on facts in knowledge bases. A typical approach to KBQA is semantic parsing, which translates a question into an executable logical form in a formal language. Re
Externí odkaz:
http://arxiv.org/abs/2401.05777