Zobrazeno 1 - 10
of 36 614
pro vyhledávání: '"Jingbo A"'
This study employs Deep Reinforcement Learning (DRL) for active flow control in a turbulent flow field of high Reynolds numbers at $Re=274000$. That is, an agent is trained to obtain a control strategy that can reduce the drag of a cylinder while als
Externí odkaz:
http://arxiv.org/abs/2412.15975
Autor:
Lu, Shunlin, Wang, Jingbo, Lu, Zeyu, Chen, Ling-Hao, Dai, Wenxun, Dong, Junting, Dou, Zhiyang, Dai, Bo, Zhang, Ruimao
The scaling law has been validated in various domains, such as natural language processing (NLP) and massive computer vision tasks; however, its application to motion generation remains largely unexplored. In this paper, we introduce a scalable motio
Externí odkaz:
http://arxiv.org/abs/2412.14559
We propose a method for conducting algebraic program analysis (APA) incrementally in response to changes of the program under analysis. APA is a program analysis paradigm that consists of two distinct steps: computing a path expression that succinctl
Externí odkaz:
http://arxiv.org/abs/2412.10632
Comparing two (large) language models (LMs) side-by-side and pinpointing their prediction similarities and differences on the same set of inputs are crucial in many real-world scenarios, e.g., one can test if a licensed model was potentially plagiari
Externí odkaz:
http://arxiv.org/abs/2412.12177
Publikováno v:
Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI2025)
Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy by optimizing the learned rew
Externí odkaz:
http://arxiv.org/abs/2412.09104
Autor:
Wei, Yuxi, Wang, Jingbo, Du, Yuwen, Wang, Dingju, Pan, Liang, Xu, Chenxin, Feng, Yao, Dai, Bo, Chen, Siheng
Generating realistic and interactive dynamics of traffic participants according to specific instruction is critical for street scene simulation. However, there is currently a lack of a comprehensive method that generates realistic dynamics of differe
Externí odkaz:
http://arxiv.org/abs/2412.08685
Story visualization, the task of creating visual narratives from textual descriptions, has seen progress with text-to-image generation models. However, these models often lack effective control over character appearances and interactions, particularl
Externí odkaz:
http://arxiv.org/abs/2412.07589
Ion traps stand at the forefront of quantum hardware technology, presenting unparalleled benefits for quantum computing, such as high-fidelity gates, extensive connectivity, and prolonged coherence times. In this context, we explore the critical role
Externí odkaz:
http://arxiv.org/abs/2412.03443
Autor:
Yuan, Qi, Guo, Hengxiao, Gu, Minfeng, Stevens, Jamie, Edwards, Philip G., Chen, Yongjun, Zuo, Wenwen, Sun, Jingbo, Yang, Jun, Lira, Paulina, An, Tao, Su, Renzhi, Liu, Yuanqi, Wang, Yijun, Chang, Ning, Jiang, Pengfei, Zhang, Ming
We present the first multi-band centimeter detection of POX 52, a nearby dwarf galaxy believed to habor a robust intermediate mass black hole (IMBH). We conducted the deep observations using the Australia Telescope Compact Array (ATCA), spanning freq
Externí odkaz:
http://arxiv.org/abs/2412.03316
Autor:
Shan, Weiqiao, Meng, Long, Zheng, Tong, Luo, Yingfeng, Li, Bei, Wang, junxin, Xiao, Tong, Zhu, Jingbo
Large language models (LLMs) exhibit exceptional performance across various downstream tasks. However, they encounter limitations due to slow inference speeds stemming from their extensive parameters. The early exit (EE) is an approach that aims to a
Externí odkaz:
http://arxiv.org/abs/2412.01455