Zobrazeno 1 - 10
of 2 351
pro vyhledávání: '"Zhou, Pan"'
Autor:
Liu, Jie, Zhou, Pan, Du, Yingjun, Tan, Ah-Hwee, Snoek, Cees G. M., Sonke, Jan-Jakob, Gavves, Efstratios
In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods often execute actions extemporaneously and incoherently, without long-term
Externí odkaz:
http://arxiv.org/abs/2411.04679
Autor:
Huang, Youcheng, Zhu, Fengbin, Tang, Jingkun, Zhou, Pan, Lei, Wenqiang, Lv, Jiancheng, Chua, Tat-Seng
Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new laRge-scale
Externí odkaz:
http://arxiv.org/abs/2410.22888
Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation hinders th
Externí odkaz:
http://arxiv.org/abs/2410.21708
The limited context window of contemporary large language models (LLMs) remains a huge barrier to their broader application across various domains. While continual pre-training on long-context data is a straightforward and effective solution, it incu
Externí odkaz:
http://arxiv.org/abs/2410.19318
Semi-supervised learning (SSL), exemplified by FixMatch (Sohn et al., 2020), has shown significant generalization advantages over supervised learning (SL), particularly in the context of deep neural networks (DNNs). However, it is still unclear, from
Externí odkaz:
http://arxiv.org/abs/2410.11206
Fine-tuning Large Language Models (LLMs) has proven effective for a variety of downstream tasks. However, as LLMs grow in size, the memory demands for backpropagation become increasingly prohibitive. Zeroth-order (ZO) optimization methods offer a mem
Externí odkaz:
http://arxiv.org/abs/2410.08989
Autor:
Xia, Ruihao, Liang, Yu, Jiang, Peng-Tao, Zhang, Hao, Sun, Qianru, Tang, Yang, Li, Bo, Zhou, Pan
Recent approaches attempt to adapt powerful interactive segmentation models, such as SAM, to interactive matting and fine-tune the models based on synthetic matting datasets. However, models trained on synthetic data fail to generalize to complex and
Externí odkaz:
http://arxiv.org/abs/2410.06593
Large language models (LLMs) are increasingly impacting human society, particularly in textual information. Based on more than 30,000 papers and 1,000 presentations from machine learning conferences, we examined and compared the words used in writing
Externí odkaz:
http://arxiv.org/abs/2409.13686
Recommender systems are essential for personalizing digital experiences on e-commerce sites, streaming services, and social media platforms. While these systems are necessary for modern digital interactions, they face fairness, bias, threats, and pri
Externí odkaz:
http://arxiv.org/abs/2409.12651
We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances frozen Vision Transformers (ViTs) through the integration of three core
Externí odkaz:
http://arxiv.org/abs/2409.11323