Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Chang, Yongzhe"'
Autor:
Wang, Yuxing, Li, Jie, Yu, Cong, Li, Xinyang, Huang, Simeng, Chang, Yongzhe, Wang, Xueqian, Liang, Bin
The emergence of modular satellites marks a significant transformation in spacecraft engineering, introducing a new paradigm of flexibility, resilience, and scalability in space exploration endeavors. In addressing complex challenges such as attitude
Externí odkaz:
http://arxiv.org/abs/2409.13166
Direct Preference Optimization (DPO) has recently expanded its successful application from aligning large language models (LLMs) to aligning text-to-image models with human preferences, which has generated considerable interest within the community.
Externí odkaz:
http://arxiv.org/abs/2409.09774
Large Language Models (LLMs) are implicit troublemakers. While they provide valuable insights and assist in problem-solving, they can also potentially serve as a resource for malicious activities. Implementing safety alignment could mitigate the risk
Externí odkaz:
http://arxiv.org/abs/2408.10668
Autor:
Kong, Yilun, Mao, Hangyu, Zhao, Qi, Zhang, Bin, Ruan, Jingqing, Shen, Li, Chang, Yongzhe, Wang, Xueqian, Zhao, Rui, Tao, Dacheng
Prompt engineering has demonstrated remarkable success in enhancing the performance of large language models (LLMs) across diverse tasks. However, most existing prompt optimization methods only focus on the task-level performance, overlooking the imp
Externí odkaz:
http://arxiv.org/abs/2408.10504
Classic reinforcement learning (RL) frequently confronts challenges in tasks involving delays, which cause a mismatch between received observations and subsequent actions, thereby deviating from the Markov assumption. Existing methods usually tackle
Externí odkaz:
http://arxiv.org/abs/2406.03102
Autor:
Sun, Haoyuan, Wu, Zihao, Xia, Bo, Chang, Pu, Dong, Zibin, Yuan, Yifu, Chang, Yongzhe, Wang, Xueqian
The success of artificial neural networks (ANNs) hinges greatly on the judicious selection of an activation function, introducing non-linearity into network and enabling them to model sophisticated relationships in data. However, the search of activa
Externí odkaz:
http://arxiv.org/abs/2405.12954
Autor:
Wang, Haoyu, Ma, Guozheng, Yu, Cong, Gui, Ning, Zhang, Linrui, Huang, Zhiqi, Ma, Suwei, Chang, Yongzhe, Zhang, Sen, Shen, Li, Wang, Xueqian, Zhao, Peilin, Tao, Dacheng
The swift advancement in the scales and capabilities of Large Language Models (LLMs) positions them as promising tools for a variety of downstream tasks. In addition to the pursuit of better performance and the avoidance of violent feedback on a cert
Externí odkaz:
http://arxiv.org/abs/2309.11166
Autor:
Zhang, Qin, Zhang, Linrui, Xu, Haoran, Shen, Li, Wang, Bowen, Chang, Yongzhe, Wang, Xueqian, Yuan, Bo, Tao, Dacheng
Offline safe RL is of great practical relevance for deploying agents in real-world applications. However, acquiring constraint-satisfying policies from the fixed dataset is non-trivial for conventional approaches. Even worse, the learned constraints
Externí odkaz:
http://arxiv.org/abs/2301.12203
The integration of Reinforcement Learning (RL) and Evolutionary Algorithms (EAs) aims at simultaneously exploiting the sample efficiency as well as the diversity and robustness of the two paradigms. Recently, hybrid learning frameworks based on this
Externí odkaz:
http://arxiv.org/abs/2201.00129
Imitation Learning (IL) is an effective learning paradigm exploiting the interactions between agents and environments. It does not require explicit reward signals and instead tries to recover desired policies using expert demonstrations. In general,
Externí odkaz:
http://arxiv.org/abs/2112.06746