Zobrazeno 1 - 10
of 105
pro vyhledávání: '"Feng, Ruili"'
Autor:
Yang, Zhantao, Feng, Ruili, Yan, Keyu, Wang, Huangji, Wang, Zhicai, Zhu, Shangwen, Zhang, Han, Xiao, Jie, Wu, Pingyu, Zhu, Kai, Chen, Jixuan, Xie, Chen-Wei, Mao, Chaojie, Yang, Yue, Zhang, Hongyang, Liu, Yu, Cheng, Fan
This paper presents Bag-of-Concept Graph (BACON) to gift models with limited linguistic abilities to taste the privilege of Vision Language Models (VLMs) and boost downstream tasks such as detection, visual question answering (VQA), and image generat
Externí odkaz:
http://arxiv.org/abs/2407.03314
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model training. This paper proposes a simple yet effective input-level backdoor
Externí odkaz:
http://arxiv.org/abs/2405.09786
Multi-agent reinforcement learning shines as the pinnacle of multi-agent systems, conquering intricate real-world challenges, fostering collaboration and coordination among agents, and unleashing the potential for intelligent decision-making across d
Externí odkaz:
http://arxiv.org/abs/2312.15674
Autor:
Zheng, Kecheng, Wu, Wei, Feng, Ruili, Zhu, Kai, Liu, Jiawei, Zhao, Deli, Zha, Zheng-Jun, Chen, Wei, Shen, Yujun
Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new type of tuning method, termed as regularized mask tuning, which masks the
Externí odkaz:
http://arxiv.org/abs/2307.15049
Autor:
Yang, Zhantao, Feng, Ruili, Zhang, Han, Shen, Yujun, Zhu, Kai, Huang, Lianghua, Zhang, Yifei, Liu, Yu, Zhao, Deli, Zhou, Jingren, Cheng, Fan
Diffusion models, which employ stochastic differential equations to sample images through integrals, have emerged as a dominant class of generative models. However, the rationality of the diffusion process itself receives limited attention, leaving t
Externí odkaz:
http://arxiv.org/abs/2306.11251
Autor:
Liu, Zhiheng, Zhang, Yifei, Shen, Yujun, Zheng, Kecheng, Zhu, Kai, Feng, Ruili, Liu, Yu, Zhao, Deli, Zhou, Jingren, Cao, Yang
Synthesizing images with user-specified subjects has received growing attention due to its practical applications. Despite the recent success in single subject customization, existing algorithms suffer from high training cost and low success rate alo
Externí odkaz:
http://arxiv.org/abs/2305.19327
Autor:
Liu, Zhiheng, Feng, Ruili, Zhu, Kai, Zhang, Yifei, Zheng, Kecheng, Liu, Yu, Zhao, Deli, Zhou, Jingren, Cao, Yang
Human brains respond to semantic features of presented stimuli with different neurons. It is then curious whether modern deep neural networks admit a similar behavior pattern. Specifically, this paper finds a small cluster of neurons in a diffusion m
Externí odkaz:
http://arxiv.org/abs/2303.05125
Cooperative multi-agent reinforcement learning (MARL) is a challenging task, as agents must learn complex and diverse individual strategies from a shared team reward. However, existing methods struggle to distinguish and exploit important individual
Externí odkaz:
http://arxiv.org/abs/2301.10574
Autor:
Zhang, Han, Feng, Ruili, Yang, Zhantao, Huang, Lianghua, Liu, Yu, Zhang, Yifei, Shen, Yujun, Zhao, Deli, Zhou, Jingren, Cheng, Fan
Diffusion models, which learn to reverse a signal destruction process to generate new data, typically require the signal at each step to have the same dimension. We argue that, considering the spatial redundancy in image signals, there is no need to
Externí odkaz:
http://arxiv.org/abs/2211.16032
Autor:
Feng, Ruili, Zheng, Kecheng, Zhu, Kai, Shen, Yujun, Zhao, Jian, Huang, Yukun, Zhao, Deli, Zhou, Jingren, Jordan, Michael, Zha, Zheng-Jun
This work presents two astonishing findings on neural networks learned for large-scale image classification. 1) Given a well-trained model, the logits predicted for some category can be directly obtained by linearly combining the predictions of a few
Externí odkaz:
http://arxiv.org/abs/2211.12339