Zobrazeno 1 - 10
of 531
pro vyhledávání: '"Liu, Zichen"'
Autor:
Liu, Zichen, Yu, Yue, Ouyang, Hao, Wang, Qiuyu, Cheng, Ka Leong, Wang, Wen, Liu, Zhiheng, Chen, Qifeng, Shen, Yujun
Image editing involves a variety of complex tasks and requires efficient and precise manipulation techniques. In this paper, we present MagicQuill, an integrated image editing system that enables swift actualization of creative ideas. Our system feat
Externí odkaz:
http://arxiv.org/abs/2411.09703
We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the frame of contextual dueling bandits. This formulation, subsuming recent
Externí odkaz:
http://arxiv.org/abs/2411.01493
This paper presents an Improved Extended-state-observer based Line-of-Sight (IELOS) guidance law for path following of underactuated Autonomous Underwater helicopter (AUH) utilizing a nonlinear tracking differentiator and anti-saturation controller.
Externí odkaz:
http://arxiv.org/abs/2410.06998
Autor:
Zhao, Yuan-yuan, Yue, Fuyong, Gao, Feng, Wang, Qibing, Li, Chao, Liu, Zichen, Wang, Lei, He, Zhixue
Entanglement distribution is a critical technique that enables numerous quantum applications. Most fiber-based long-distance experiments reported to date have utilized photon pair sources generated in bulk optical crystals, with the entanglement enco
Externí odkaz:
http://arxiv.org/abs/2407.21305
Autor:
Chen, Changyu, Liu, Zichen, Du, Chao, Pang, Tianyu, Liu, Qian, Sinha, Arunesh, Varakantham, Pradeep, Lin, Min
Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human feedback (RLHF)
Externí odkaz:
http://arxiv.org/abs/2406.09760
Text animation serves as an expressive medium, transforming static communication into dynamic experiences by infusing words with motion to evoke emotions, emphasize meanings, and construct compelling narratives. Crafting animations that are semantica
Externí odkaz:
http://arxiv.org/abs/2404.11614
Autor:
Huang, Shengyi, Gallouédec, Quentin, Felten, Florian, Raffin, Antonin, Dossa, Rousslan Fernand Julien, Zhao, Yanxiao, Sullivan, Ryan, Makoviychuk, Viktor, Makoviichuk, Denys, Danesh, Mohamad H., Roumégous, Cyril, Weng, Jiayi, Chen, Chufan, Rahman, Md Masudur, Araújo, João G. M., Quan, Guorui, Tan, Daniel, Klein, Timo, Charakorn, Rujikorn, Towers, Mark, Berthelot, Yann, Mehta, Kinal, Chakraborty, Dipam, KG, Arjun, Charraut, Valentin, Ye, Chang, Liu, Zichen, Alegre, Lucas N., Nikulin, Alexander, Hu, Xiao, Liu, Tianlin, Choi, Jongwook, Yi, Brent
In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curves are rarely available. As a result, it is usually necessary to repro
Externí odkaz:
http://arxiv.org/abs/2402.03046
Acquiring an accurate world model online for model-based reinforcement learning (MBRL) is challenging due to data nonstationarity, which typically causes catastrophic forgetting for neural networks (NNs). From the online learning perspective, a Follo
Externí odkaz:
http://arxiv.org/abs/2401.13034
Inspired by cognitive theories, we introduce AnyHome, a framework that translates any text into well-structured and textured indoor scenes at a house-scale. By prompting Large Language Models (LLMs) with designed templates, our approach converts prov
Externí odkaz:
http://arxiv.org/abs/2312.06644
Autor:
Wu Mian, Yang Chao, Gong Yuhan, Wu Lin, Luo Ming, Qiu Ying, Zeng Yongquan, Li Zile, Liu Zichen, Li Chao, Li Hanbing, Xiao Xi, He Zhixue, Zheng Guoxing, Yu Shaohua, Tao Jin
Publikováno v:
Nanophotonics, Vol 13, Iss 23, Pp 4347-4356 (2024)
Beam-steered infrared (IR) light communication has gained tremendous attention as one of the solutions of congested wireless communication traffic. High performance active beam-steering devices play a crucial role in data allocation and exchange. Con
Externí odkaz:
https://doaj.org/article/10e1ad62cddf46bd846c936371c842df
