Zobrazeno 1 - 10
of 6 503
pro vyhledávání: '"Clark James"'
In this paper, we consider the conditional generation problem by guiding off-the-shelf unconditional diffusion models with differentiable loss functions in a plug-and-play fashion. While previous research has primarily focused on balancing the uncond
Externí odkaz:
http://arxiv.org/abs/2411.12773
Recent advances in differentially private federated learning (DPFL) algorithms have found that using correlated noise across the rounds of federated learning (DP-FTRL) yields provably and empirically better accuracy than using independent noise (DP-S
Externí odkaz:
http://arxiv.org/abs/2410.11368
Autor:
Tayaranian, Mohammadreza, Mozafari, Seyyed Hasan, Meyer, Brett H., Clark, James J., Gross, Warren J.
Transformer-based language models have shown state-of-the-art performance on a variety of natural language understanding tasks. To achieve this performance, these models are first pre-trained on general corpus and then fine-tuned on downstream tasks.
Externí odkaz:
http://arxiv.org/abs/2407.08887
Autor:
Yuan, Ye, Zhang, Youyuan, Chen, Can, Wu, Haolun, Li, Zixuan, Li, Jianmo, Clark, James J., Liu, Xue
Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores. These tasks span various domains, such as robotics, material design, and protein and molecular engineering. A
Externí odkaz:
http://arxiv.org/abs/2405.13964
Conventional image quality metrics (IQMs), such as PSNR and SSIM, are designed for perceptually uniform gamma-encoded pixel values and cannot be directly applied to perceptually non-uniform linear high-dynamic-range (HDR) colors. Similarly, most of t
Externí odkaz:
http://arxiv.org/abs/2405.00670
Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-video generation, opening up possibilities for video editing based on textual input. However, the computational cost associated with sequential sampling in diffus
Externí odkaz:
http://arxiv.org/abs/2403.06269
Autor:
Tayaranian, Mohammadreza, Mozafari, Seyyed Hasan, Clark, James J., Meyer, Brett, Gross, Warren
SWIN transformer is a prominent vision transformer model that has state-of-the-art accuracy in image classification tasks. Despite this success, its unique architecture causes slower inference compared with similar deep neural networks. Integer quant
Externí odkaz:
http://arxiv.org/abs/2402.01169
This paper describes a simple yet effective technique for refining a pretrained classifier network. The proposed AdCorDA method is based on modification of the training set and making use of the duality between network weights and layer inputs. We ca
Externí odkaz:
http://arxiv.org/abs/2401.13212
It is necessary to develop efficient DNNs deployed on edge devices with limited computation resources. However, the compressed networks often execute new tasks in the target domain, which is different from the source domain where the original network
Externí odkaz:
http://arxiv.org/abs/2401.12014