Zobrazeno 1 - 10
of 662
pro vyhledávání: '"Guo Jiayi"'
Automated Machine Learning (AutoML) has simplified complex ML processes such as data pre-processing, model selection, and hyper-parameter searching. However, traditional AutoML frameworks focus solely on discriminative tasks, often falling short in t
Externí odkaz:
http://arxiv.org/abs/2410.12841
Autor:
Ni, Zanlin, Wang, Yulin, Zhou, Renping, Lu, Rui, Guo, Jiayi, Hu, Jinyi, Liu, Zhiyuan, Yao, Yuan, Huang, Gao
Recent studies have demonstrated the effectiveness of token-based methods for visual content generation. As a representative work, non-autoregressive Transformers (NATs) are able to synthesize images with decent quality in a small number of steps. Ho
Externí odkaz:
http://arxiv.org/abs/2409.00342
Empirical risk minimization, a cornerstone in machine learning, is often hindered by the Optimizer's Curse stemming from discrepancies between the empirical and true data-generating distributions.To address this challenge, the robust satisficing fram
Externí odkaz:
http://arxiv.org/abs/2408.09157
Autor:
Pu, Yifan, Xia, Zhuofan, Guo, Jiayi, Han, Dongchen, Li, Qixiu, Li, Duo, Yuan, Yuhui, Li, Ji, Han, Yizeng, Song, Shiji, Huang, Gao, Li, Xiu
This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of denoising diffusion steps. In response to this observation, we presen
Externí odkaz:
http://arxiv.org/abs/2408.05710
Test-Time Adaptation (TTA) aims to adapt pre-trained models to the target domain during testing. In reality, this adaptability can be influenced by multiple factors. Researchers have identified various challenging scenarios and developed diverse meth
Externí odkaz:
http://arxiv.org/abs/2407.20080
Video editing is an emerging task, in which most current methods adopt the pre-trained text-to-image (T2I) diffusion model to edit the source video in a zero-shot manner. Despite extensive efforts, maintaining the temporal consistency of edited video
Externí odkaz:
http://arxiv.org/abs/2406.08850
Autor:
Ni, Zanlin, Wang, Yulin, Zhou, Renping, Guo, Jiayi, Hu, Jinyi, Liu, Zhiyuan, Song, Shiji, Yao, Yuan, Huang, Gao
The field of image synthesis is currently flourishing due to the advancements in diffusion models. While diffusion models have been successful, their computational intensity has prompted the pursuit of more efficient alternatives. As a representative
Externí odkaz:
http://arxiv.org/abs/2406.05478
Autor:
Guo, Jiayi, Zhao, Junhao, Ge, Chunjiang, Du, Chaoqun, Ni, Zanlin, Song, Shiji, Shi, Humphrey, Huang, Gao
Test-time adaptation (TTA) aims to enhance the performance of source-domain pretrained models when tested on unknown shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model performance
Externí odkaz:
http://arxiv.org/abs/2406.04295
Oriented object detection, an emerging task in recent years, aims to identify and locate objects across varied orientations. This requires the detector to accurately capture the orientation information, which varies significantly within and across im
Externí odkaz:
http://arxiv.org/abs/2403.11127
Autor:
Guo, Jiayi, Xu, Xingqian, Pu, Yifan, Ni, Zanlin, Wang, Chaofei, Vasu, Manushree, Song, Shiji, Huang, Gao, Shi, Humphrey
Recently, diffusion models have made remarkable progress in text-to-image (T2I) generation, synthesizing images with high fidelity and diverse contents. Despite this advancement, latent space smoothness within diffusion models remains largely unexplo
Externí odkaz:
http://arxiv.org/abs/2312.04410