Zobrazeno 1 - 10
of 2 559
pro vyhledávání: '"TIAN, Chao"'
Particle-based Bayesian inference methods by sampling from a partition-free target (posterior) distribution, e.g., Stein variational gradient descent (SVGD), have attracted significant attention. We propose a path-guided particle-based sampling~(PGPS
Externí odkaz:
http://arxiv.org/abs/2412.03312
Autor:
Zhang, Feng, Deng, Li, Ge, Yanjie, Wen, Jiaxing, Cui, Bo, Feng, Ke, Wang, Hao, Wu, Chen, Pan, Ziwen, Liu, Hongjie, Deng, Zhigang, Zhang, Zongxin, Chen, Liangwen, Yan, Duo, Shan, Lianqiang, Yuan, Zongqiang, Tian, Chao, Qian, Jiayi, Zhu, Jiacheng, Xu, Yi, Yu, Yuhong, Zhang, Xueheng, Yang, Lei, Zhou, Weimin, Gu, Yuqiu, Wang, Wentao, Leng, Yuxin, Sun, Zhiyu, Li, Ruxin
Muons, which play a crucial role in both fundamental and applied physics, have traditionally been generated through proton accelerators or from cosmic rays. With the advent of ultra-short high-intensity lasers capable of accelerating electrons to GeV
Externí odkaz:
http://arxiv.org/abs/2410.23829
Large language models have demonstrated impressive in-context learning (ICL) capability. However, it is still unclear how the underlying transformers accomplish it, especially in more complex scenarios. Toward this goal, several recent works studied
Externí odkaz:
http://arxiv.org/abs/2410.05493
We consider coverless steganography where a Large Language Model (LLM) drives an arithmetic coding decoder to generate stego-texts. An efficient method should embed secret message bits in as few language tokens as possible, while still keeping the st
Externí odkaz:
http://arxiv.org/abs/2410.04328
Data Generation Scheme for Thermal Modality with Edge-Guided Adversarial Conditional Diffusion Model
In challenging low light and adverse weather conditions,thermal vision algorithms,especially object detection,have exhibited remarkable potential,contrasting with the frequent struggles encountered by visible vision algorithms. Nevertheless,the effic
Externí odkaz:
http://arxiv.org/abs/2408.03748
Foundational Large Language Models (LLMs) such as GPT-3.5-turbo allow users to refine the model based on newer information, known as ``fine-tuning''. This paper leverages this ability to analyze AC-DC converter behaviors, focusing on the ripple curre
Externí odkaz:
http://arxiv.org/abs/2407.01724
Autor:
Zhou, Ruida, Tian, Chao
The rate-distortion-perception (RDP) framework has attracted significant recent attention due to its application in neural compression. It is important to understand the underlying mechanism connecting procedures with common randomness and those with
Externí odkaz:
http://arxiv.org/abs/2406.19248
This survey articles focuses on emerging connections between the fields of machine learning and data compression. While fundamental limits of classical (lossy) data compression are established using rate-distortion theory, the connections to machine
Externí odkaz:
http://arxiv.org/abs/2406.10036
Autor:
Majumder, Subir, Dong, Lin, Doudi, Fatemeh, Cai, Yuting, Tian, Chao, Kalathi, Dileep, Ding, Kevin, Thatte, Anupam A., Li, Na, Xie, Le
Large Language Models (LLMs) as chatbots have drawn remarkable attention thanks to their versatile capability in natural language processing as well as in a wide range of tasks. While there has been great enthusiasm towards adopting such foundational
Externí odkaz:
http://arxiv.org/abs/2403.09125
We study Markov potential games under the infinite horizon average reward criterion. Most previous studies have been for discounted rewards. We prove that both algorithms based on independent policy gradient and independent natural policy gradient co
Externí odkaz:
http://arxiv.org/abs/2403.05738