Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Xie, Zeke"'
Text-to-image diffusion model is a popular paradigm that synthesizes personalized images by providing a text prompt and a random Gaussian noise. While people observe that some noises are ``golden noises'' that can achieve better text-image alignment
Externí odkaz:
http://arxiv.org/abs/2411.09502
Autor:
Peng, Tianhao, Li, Yuchen, Li, Xuhong, Bian, Jiang, Xie, Zeke, Sui, Ning, Mumtaz, Shahid, Xu, Yanwu, Kong, Linghe, Xiong, Haoyi
Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and pr
Externí odkaz:
http://arxiv.org/abs/2411.01401
The multi-step sampling mechanism, a key feature of visual diffusion models, has significant potential to replicate the success of OpenAI's Strawberry in enhancing performance by increasing the inference computational cost. Sufficient prior studies h
Externí odkaz:
http://arxiv.org/abs/2410.04171
Autor:
Liu, Buhua, Shao, Shitong, Li, Bao, Bai, Lichen, Xu, Zhiqiang, Xiong, Haoyi, Kwok, James, Helal, Sumi, Xie, Zeke
Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications. Despite their success, these models often misalign with human intentions, generating outputs that may not match text prompts or possess d
Externí odkaz:
http://arxiv.org/abs/2409.07253
The influence function, a technique from robust statistics, measures the impact on model parameters or related functions when training data is removed or modified. This effective and valuable post-hoc method allows for studying the interpretability o
Externí odkaz:
http://arxiv.org/abs/2408.14763
Diffusion models that can generate high-quality data from randomly sampled Gaussian noises have become the mainstream generative method in both academia and industry. Are randomly sampled Gaussian noises equally good for diffusion models? While a lar
Externí odkaz:
http://arxiv.org/abs/2407.14041
Autor:
Xiong, Haoyi, Wang, Zhiyuan, Li, Xuhong, Bian, Jiang, Xie, Zeke, Mumtaz, Shahid, Al-Dulaimi, Anwer, Barnes, Laura E.
This article explores the convergence of connectionist and symbolic artificial intelligence (AI), from historical debates to contemporary advancements. Traditionally considered distinct paradigms, connectionist AI focuses on neural networks, while sy
Externí odkaz:
http://arxiv.org/abs/2407.08516
Autor:
Yang, Jinze, Wang, Haoran, Zhu, Zining, Liu, Chenglong, Wu, Meng Wymond, Xie, Zeke, Ji, Zhong, Han, Jungong, Sun, Mingming
In this paper, we focus on resolving the problem of image outpainting, which aims to extrapolate the surrounding parts given the center contents of an image. Although recent works have achieved promising performance, the lack of versatility and custo
Externí odkaz:
http://arxiv.org/abs/2406.01059
Autor:
Yu, Zhongrui, Wang, Haoran, Yang, Jinze, Wang, Hanzhang, Xie, Zeke, Cai, Yunfeng, Cao, Jiale, Ji, Zhong, Sun, Mingming
Novel View Synthesis (NVS) for street scenes play a critical role in the autonomous driving simulation. The current mainstream technique to achieve it is neural rendering, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). Althou
Externí odkaz:
http://arxiv.org/abs/2403.20079
Autor:
Yang, Xindi, Xie, Zeke, Zhou, Xiong, Liu, Boyu, Liu, Buhua, Liu, Yi, Wang, Haoran, Cai, Yunfeng, Sun, Mingming
Neural field methods have seen great progress in various long-standing tasks in computer vision and computer graphics, including novel view synthesis and geometry reconstruction. As existing neural field methods try to predict some coordinate-based c
Externí odkaz:
http://arxiv.org/abs/2403.01058