Zobrazeno 1 - 10
of 8 143
pro vyhledávání: '"An, Wenji"'
Autor:
Wang, Minzheng, Zhang, Xinghua, Chen, Kun, Xu, Nan, Yu, Haiyang, Huang, Fei, Mao, Wenji, Li, Yongbin
Large language models (LLMs) have made dialogue one of the central modes of human-machine interaction, leading to the accumulation of vast amounts of conversation logs and increasing demand for dialogue generation. A conversational life-cycle spans f
Externí odkaz:
http://arxiv.org/abs/2412.04905
Autor:
Li, Yuchen, Chen, Zhizhong, Deng, Chuhan, Dong, Boyan, Wang, Daqi, Pan, Zuojian, Zhang, Haodong, Nie, Jingxin, Chen, Weihua, Jiao, Fei, Kang, Xiangning, Wang, Qi, Zhang, Guoyi, Shen, Bo, Liang, Wenji
To meet the demand for high-speed response in display applications, a more detailed study of the capacitive effects in LEDs is required. This work tested the capacitance of LEDs at different frequencies and proposed an effective capacitance model, wh
Externí odkaz:
http://arxiv.org/abs/2411.16626
Assertion-based verification (ABV) is a critical method to ensure logic designs comply with their architectural specifications. ABV requires assertions, which are generally converted from specifications through human interpretation by verification en
Externí odkaz:
http://arxiv.org/abs/2411.14436
Autor:
Zhuang, Jiafan, Xia, Zihao, Han, Gaofei, Wang, Boxi, Li, Wenji, Wang, Dongliang, Hao, Zhifeng, Cai, Ruichu, Fan, Zhun
Deep reinforcement learning (DRL) has achieved remarkable progress in online path planning tasks for multi-UAV systems. However, existing DRL-based methods often suffer from performance degradation when tackling unseen scenarios, since the non-causal
Externí odkaz:
http://arxiv.org/abs/2407.04064
Autor:
Zhuang, Jiafan, Han, Gaofei, Xia, Zihao, Wang, Boxi, Li, Wenji, Wang, Dongliang, Hao, Zhifeng, Cai, Ruichu, Fan, Zhun
In unseen and complex outdoor environments, collision avoidance navigation for unmanned aerial vehicle (UAV) swarms presents a challenging problem. It requires UAVs to navigate through various obstacles and complex backgrounds. Existing collision avo
Externí odkaz:
http://arxiv.org/abs/2407.04056
Autor:
Huang, Jialong, Song, Junlin, Lian, Penglong, Gan, Mengjie, Su, Zhiheng, Wang, Benhao, Zhu, Wenji, Pu, Xiaomin, Zou, Jianxiao, Fan, Shicai
Due to the scarcity of fault samples and the complexity of non-linear and non-smooth characteristics data in hydroelectric units, most of the traditional hydroelectric unit fault localization methods are difficult to carry out accurate localization.
Externí odkaz:
http://arxiv.org/abs/2405.19665
Leveraging generative retrieval (GR) techniques to enhance search systems is an emerging methodology that has shown promising results in recent years. In GR, a text-to-text model maps string queries directly to relevant document identifiers (docIDs),
Externí odkaz:
http://arxiv.org/abs/2404.15675
Annotating Slack Directly on Your Verilog: Fine-Grained RTL Timing Evaluation for Early Optimization
In digital IC design, compared with post-synthesis netlists or layouts, the early register-transfer level (RTL) stage offers greater optimization flexibility for both designers and EDA tools. However, timing information is typically unavailable at th
Externí odkaz:
http://arxiv.org/abs/2403.18453
Graph representation learning is a fundamental research issue in various domains of applications, of which the inductive learning problem is particularly challenging as it requires models to generalize to unseen graph structures during inference. In
Externí odkaz:
http://arxiv.org/abs/2403.17500
Autor:
Chen, Lei, Chen, Yiqi, Chu, Zhufei, Fang, Wenji, Ho, Tsung-Yi, Huang, Ru, Huang, Yu, Khan, Sadaf, Li, Min, Li, Xingquan, Li, Yu, Liang, Yun, Liu, Jinwei, Liu, Yi, Lin, Yibo, Luo, Guojie, Shi, Zhengyuan, Sun, Guangyu, Tsaras, Dimitrios, Wang, Runsheng, Wang, Ziyi, Wei, Xinming, Xie, Zhiyao, Xu, Qiang, Xue, Chenhao, Yan, Junchi, Yang, Jun, Yu, Bei, Yuan, Mingxuan, Young, Evangeline F. Y., Zeng, Xuan, Zhang, Haoyi, Zhang, Zuodong, Zhao, Yuxiang, Zhen, Hui-Ling, Zheng, Ziyang, Zhu, Binwu, Zhu, Keren, Zou, Sunan
Within the Electronic Design Automation (EDA) domain, AI-driven solutions have emerged as formidable tools, yet they typically augment rather than redefine existing methodologies. These solutions often repurpose deep learning models from other domain
Externí odkaz:
http://arxiv.org/abs/2403.07257