Zobrazeno 1 - 10
of 2 275
pro vyhledávání: '"Dai Bo"'
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 7, Iss 1, Pp 541-548 (2021)
In order to solve the problems of financial accounting measurement quickly and accurately, this paper starts the analysis from the perspective of mathematics and finance and establishes the differential equation and the generalised functional equatio
Externí odkaz:
https://doaj.org/article/6cc0c644f63648b38188cf0704857948
Despite the impressive generative abilities of black-box large language models (LLMs), their inherent opacity hinders further advancements in capabilities such as reasoning, planning, and personalization. Existing works aim to enhance LLM capabilitie
Externí odkaz:
http://arxiv.org/abs/2410.20749
Autor:
Yang, Tong, Mei, Jincheng, Dai, Hanjun, Wen, Zixin, Cen, Shicong, Schuurmans, Dale, Chi, Yuejie, Dai, Bo
Recent advances in aligning large language models with human preferences have corroborated the growing importance of best-of-N distillation (BOND). However, the iterative BOND algorithm is prohibitively expensive in practice due to the sample and com
Externí odkaz:
http://arxiv.org/abs/2410.20727
Off-policy evaluation (OPE) is one of the most fundamental problems in reinforcement learning (RL) to estimate the expected long-term payoff of a given target policy with only experiences from another behavior policy that is potentially unknown. The
Externí odkaz:
http://arxiv.org/abs/2410.17538
Network Markov Decision Processes (MDPs), a popular model for multi-agent control, pose a significant challenge to efficient learning due to the exponential growth of the global state-action space with the number of agents. In this work, utilizing th
Externí odkaz:
http://arxiv.org/abs/2410.17221
Autor:
Soni, Achint, Venkataraman, Sreyas, Chandra, Abhranil, Fischmeister, Sebastian, Liang, Percy, Dai, Bo, Yang, Sherry
Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video plans which are then converted to robot controls to be executed. However
Externí odkaz:
http://arxiv.org/abs/2410.10076
Diffusion transformers (DiT) have already achieved appealing synthesis and scaling properties in content recreation, e.g., image and video generation. However, scaling laws of DiT are less explored, which usually offer precise predictions regarding o
Externí odkaz:
http://arxiv.org/abs/2410.08184
Autor:
Sun, Haotian, Lei, Tao, Zhang, Bowen, Li, Yanghao, Huang, Haoshuo, Pang, Ruoming, Dai, Bo, Du, Nan
Diffusion transformers have been widely adopted for text-to-image synthesis. While scaling these models up to billions of parameters shows promise, the effectiveness of scaling beyond current sizes remains underexplored and challenging. By explicitly
Externí odkaz:
http://arxiv.org/abs/2410.02098
Autor:
Liao, Zimu, Chen, Siyan, Fu, Rong, Wang, Yi, Su, Zhongling, Luo, Hao, Ma, Li, Xu, Linning, Dai, Bo, Li, Hengjie, Pei, Zhilin, Zhang, Xingcheng
Recently, 3D Gaussian Splatting (3DGS) has garnered attention for its high fidelity and real-time rendering. However, adapting 3DGS to different camera models, particularly fisheye lenses, poses challenges due to the unique 3D to 2D projection calcul
Externí odkaz:
http://arxiv.org/abs/2409.04751
Autor:
Chen, Yiran, Rao, Anyi, Jiang, Xuekun, Xiao, Shishi, Ma, Ruiqing, Wang, Zeyu, Xiong, Hui, Dai, Bo
With advancements in video generative AI models (e.g., SORA), creators are increasingly using these techniques to enhance video previsualization. However, they face challenges with incomplete and mismatched AI workflows. Existing methods mainly rely
Externí odkaz:
http://arxiv.org/abs/2408.17424