Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Lu, Shiyin"'
Autor:
Zhang, Yi-Kai, Lu, Shiyin, Li, Yang, Ma, Yanqing, Chen, Qing-Guo, Xu, Zhao, Luo, Weihua, Zhang, Kaifu, Zhan, De-Chuan, Ye, Han-Jia
Multimodal large language models (MLLMs), initiated with a trained LLM, first align images with text and then fine-tune on multimodal mixed inputs. However, the MLLM catastrophically forgets the text-only instructions, which do not include images and
Externí odkaz:
http://arxiv.org/abs/2406.03496
Autor:
Sun, Hai-Long, Zhou, Da-Wei, Li, Yang, Lu, Shiyin, Yi, Chao, Chen, Qing-Guo, Xu, Zhao, Luo, Weihua, Zhang, Kaifu, Zhan, De-Chuan, Ye, Han-Jia
The rapid development of Multimodal Large Language Models (MLLMs) like GPT-4V has marked a significant step towards artificial general intelligence. Existing methods mainly focus on aligning vision encoders with LLMs through supervised fine-tuning (S
Externí odkaz:
http://arxiv.org/abs/2406.02539
Current Multimodal Large Language Models (MLLMs) typically integrate a pre-trained LLM with another pre-trained vision transformer through a connector, such as an MLP, endowing the LLM with visual capabilities. However, the misalignment between two e
Externí odkaz:
http://arxiv.org/abs/2405.20797
Autor:
Wang, Yibo, Yang, Wenhao, Jiang, Wei, Lu, Shiyin, Wang, Bing, Tang, Haihong, Wan, Yuanyu, Zhang, Lijun
Projection-free online learning has drawn increasing interest due to its efficiency in solving high-dimensional problems with complicated constraints. However, most existing projection-free online methods focus on minimizing the static regret, which
Externí odkaz:
http://arxiv.org/abs/2305.11726
In this paper, we revisit the problem of smoothed online learning, in which the online learner suffers both a hitting cost and a switching cost, and target two performance metrics: competitive ratio and dynamic regret with switching cost. To bound th
Externí odkaz:
http://arxiv.org/abs/2102.06933
Regret minimization is treated as the golden rule in the traditional study of online learning. However, regret minimization algorithms tend to converge to the static optimum, thus being suboptimal for changing environments. To address this limitation
Externí odkaz:
http://arxiv.org/abs/2002.02085
Autor:
Lu, Shiyin, Zhang, Lijun
In this paper, we consider the problem of prediction with expert advice in dynamic environments. We choose tracking regret as the performance metric and develop two adaptive and efficient algorithms with data-dependent tracking regret bounds. The fir
Externí odkaz:
http://arxiv.org/abs/1909.02187
In this paper, we study the multi-objective bandits (MOB) problem, where a learner repeatedly selects one arm to play and then receives a reward vector consisting of multiple objectives. MOB has found many real-world applications as varied as online
Externí odkaz:
http://arxiv.org/abs/1905.12879
In this paper, we study adaptive online convex optimization, and aim to design a universal algorithm that achieves optimal regret bounds for multiple common types of loss functions. Existing universal methods are limited in the sense that they are op
Externí odkaz:
http://arxiv.org/abs/1905.05917
The Adam algorithm has become extremely popular for large-scale machine learning. Under convexity condition, it has been proved to enjoy a data-dependant $O(\sqrt{T})$ regret bound where $T$ is the time horizon. However, whether strong convexity can
Externí odkaz:
http://arxiv.org/abs/1905.02957