Výsledky vyhledávání

Report

Large Language Models Overcome the Machine Penalty When Acting Fairly but Not When Acting Selfishly or Altruistically

Autor: Wang, Zhen, Song, Ruiqi, Shen, Chen, Yin, Shiya, Song, Zhao, Battu, Balaraju, Shi, Lei, Jia, Danyang, Rahwan, Talal, Hu, Shuyue

In social dilemmas where the collective and self-interests are at odds, people typically cooperate less with machines than with fellow humans, a phenomenon termed the machine penalty. Overcoming this penalty is critical for successful human-machine c

Externí odkaz: http://arxiv.org/abs/2410.03724

Zobrazit plný text záznamu

Report

Emergence of Social Norms in Generative Agent Societies: Principles and Architecture

Autor: Ren, Siyue, Cui, Zhiyao, Song, Ruiqi, Wang, Zhen, Hu, Shuyue

Social norms play a crucial role in guiding agents towards understanding and adhering to standards of behavior, thus reducing social conflicts within multi-agent systems (MASs). However, current LLM-based (or generative) MASs lack the capability to b

Externí odkaz: http://arxiv.org/abs/2403.08251

Zobrazit plný text záznamu

Report

GenAD: Generative End-to-End Autonomous Driving

Autor: Zheng, Wenzhao, Song, Ruiqi, Guo, Xianda, Zhang, Chenming, Chen, Long

Directly producing planning results from raw sensors has been a long-desired solution for autonomous driving and has attracted increasing attention recently. Most existing end-to-end autonomous driving methods factorize this problem into perception,

Externí odkaz: http://arxiv.org/abs/2402.11502

Zobrazit plný text záznamu

Report

DAIRstega: Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel

Autor: Wang, Yihao, Song, Ruiqi, Li, Lingxiao, Zhang, Ru, Liu, Jianyi

Linguistic steganography (LS) tasks aim to generate steganographic text (stego) based on secret. Only authorized receivers can perceive and extract secrets, thereby protecting privacy. However, existing generative LS schemes often do not consider the

Externí odkaz: http://arxiv.org/abs/2401.15656

Zobrazit plný text záznamu

Report

UP4LS: User Profile Constructed by Multiple Attributes for Enhancing Linguistic Steganalysis

Autor: Wang, Yihao, Song, Ruiqi, Li, Lingxiao, Tang, Yifan, Zhang, Ru, Liu, Jianyi

Linguistic steganalysis (LS) tasks aim to detect whether a text contains secret information. Existing LS methods focus on the deep-learning model design and they achieve excellent results in ideal data. However, they overlook the unique user characte

Externí odkaz: http://arxiv.org/abs/2311.01775

Zobrazit plný text záznamu

Report

Glassy crystals with colossal multi-baroresponsivities

Autor: Zhang, Kun, Zhang, Zhe, Pan, Hailong, Zhao, Xueting, Qi, Ji, Zhang, Zhao, Song, Ruiqi, Yu, Chenyang, Huang, Biaohong, Li, Xujing, Chen, Huaican, Tan, Changlong, Yin, Wen, Hu, Weijin, Wübbenhorst, Michael, Luo, Jiangshui, Yu, Dehong, Zhang, Zhidong, Li, Bing

As a nontrivial solid state of matter, the glassy-crystal state embraces physical features of both crystalline and amorphous solids, where a long-range ordered periodic structure formed by the mass centers of constituent molecules accommodates orient

Externí odkaz: http://arxiv.org/abs/2209.04763

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání