Zobrazeno 1 - 10
of 238
pro vyhledávání: '"Hu, Tianyang"'
In-Context Learning (ICL) has been a powerful emergent property of large language models that has attracted increasing attention in recent years. In contrast to regular gradient-based learning, ICL is highly interpretable and does not require paramet
Externí odkaz:
http://arxiv.org/abs/2406.02847
Autor:
Wang, Zhiwei, Wang, Yunji, Zhang, Zhongwang, Zhou, Zhangchen, Jin, Hui, Hu, Tianyang, Sun, Jiacheng, Li, Zhenguo, Zhang, Yaoyu, Xu, Zhi-Qin John
Large language models have consistently struggled with complex reasoning tasks, such as mathematical problem-solving. Investigating the internal reasoning mechanisms of these models can help us design better model architectures and training strategie
Externí odkaz:
http://arxiv.org/abs/2405.15302
Publikováno v:
Phys. Rev. D 109, 114024 (2024)
We investigate the gravitational form factors of charmonium. Our method is based on a Hamiltonian formalism on the light front known as basis light-front quantization. The charmonium mass spectrum and light-front wave functions were obtained from dia
Externí odkaz:
http://arxiv.org/abs/2404.06259
Autor:
Xue, Shuchen, Liu, Zhaoqiang, Chen, Fei, Zhang, Shifeng, Hu, Tianyang, Xie, Enze, Li, Zhenguo
Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order nu
Externí odkaz:
http://arxiv.org/abs/2402.17376
As a dominant force in text-to-image generation tasks, Diffusion Probabilistic Models (DPMs) face a critical challenge in controllability, struggling to adhere strictly to complex, multi-faceted instructions. In this work, we aim to address this alig
Externí odkaz:
http://arxiv.org/abs/2402.16305
Autor:
Ma, Jiajun, Xue, Shuchen, Hu, Tianyang, Wang, Wenjia, Liu, Zhaoqiang, Li, Zhenguo, Ma, Zhi-Ming, Kawaguchi, Kenji
With the incorporation of the UNet architecture, diffusion probabilistic models have become a dominant force in image generation tasks. One key design in UNet is the skip connections between the encoder and decoder blocks. Although skip connections h
Externí odkaz:
http://arxiv.org/abs/2402.15170
Autor:
Gao, Yihang, Zheng, Chuanyang, Xie, Enze, Shi, Han, Hu, Tianyang, Li, Yu, Ng, Michael K., Li, Zhenguo, Liu, Zhaoqiang
Besides natural language processing, transformers exhibit extraordinary performance in solving broader applications, including scientific computing and computer vision. Previous works try to explain this from the expressive power and capability persp
Externí odkaz:
http://arxiv.org/abs/2402.13572
Guidance in conditional diffusion generation is of great importance for sample quality and controllability. However, existing guidance schemes are to be desired. On one hand, mainstream methods such as classifier guidance and classifier-free guidance
Externí odkaz:
http://arxiv.org/abs/2310.11311
In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of the latent s
Externí odkaz:
http://arxiv.org/abs/2307.08283
Energy-Based Models (EBMs) have been widely used for generative modeling. Contrastive Divergence (CD), a prevailing training objective for EBMs, requires sampling from the EBM with Markov Chain Monte Carlo methods (MCMCs), which leads to an irreconci
Externí odkaz:
http://arxiv.org/abs/2307.01668