Výsledky vyhledávání - "Wang, Guanqun"

Report

MR-MLLM: Mutual Reinforcement of Multimodal Comprehension and Vision Perception

Autor: Wang, Guanqun, Wei, Xinyu, Liu, Jiaming, Zhang, Ray, Zhang, Yichi, Zhang, Kevin, Chong, Maurice, Zhang, Shanghang

In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception tasks, such as

Externí odkaz: http://arxiv.org/abs/2406.15768

Zobrazit plný text záznamu

Report

Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation

Autor: Liu, Jiaming, Li, Chenxuan, Wang, Guanqun, Lee, Lily, Zhou, Kaichen, Chen, Sixiang, Xiong, Chuyan, Ge, Jiaxin, Zhang, Renrui, Zhang, Shanghang

Robot manipulation policies have shown unsatisfactory action performance when confronted with novel task or object instances. Hence, the capability to automatically detect and self-correct failure action is essential for a practical robotic system. R

Externí odkaz: http://arxiv.org/abs/2405.17418

Zobrazit plný text záznamu

Report

Cloud-Device Collaborative Learning for Multimodal Large Language Models

Autor: Wang, Guanqun, Liu, Jiaming, Li, Chenxuan, Ma, Junpeng, Zhang, Yuan, Wei, Xinyu, Zhang, Kevin, Chong, Maurice, Zhang, Ray, Liu, Yijiang, Zhang, Shanghang

The burgeoning field of Multimodal Large Language Models (MLLMs) has exhibited remarkable performance in diverse tasks such as captioning, commonsense reasoning, and visual scene understanding. However, the deployment of these large-scale MLLMs on cl

Externí odkaz: http://arxiv.org/abs/2312.16279

Zobrazit plný text záznamu

Report

Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer

Autor: Liu, Jiaming, Zhang, Qizhe, Li, Xiaoqi, Li, Jianing, Wang, Guanqun, Lu, Ming, Huang, Tiejun, Zhang, Shanghang

Neuromorphic spike data, an upcoming modality with high temporal resolution, has shown promising potential in autonomous driving by mitigating the challenges posed by high-velocity motion blur. However, training the spike depth estimation network hol

Externí odkaz: http://arxiv.org/abs/2208.12527

Zobrazit plný text záznamu

Report

Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain

Autor: Zhang, Tong, Gao, Peng, Dong, Hao, Zhuang, Yin, Wang, Guanqun, Zhang, Wei, Chen, He

Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the status of c

Externí odkaz: http://arxiv.org/abs/2207.03860

Zobrazit plný text záznamu

Akademický článek

Well Logging Reconstruction Based on a Temporal Convolutional Network and Bidirectional Gated Recurrent Unit Network with Attention Mechanism Optimized by Improved Sand Cat Swarm Optimization.

Autor: Wang, Guanqun¹ (AUTHOR) wgq_neu@163.com, Teng, Haibo² (AUTHOR) a13643146699@163.com, Qiao, Lei¹ (AUTHOR), Yu, Hongtao² (AUTHOR), Cui, You¹ (AUTHOR), Xiao, Kun³ (AUTHOR)

Publikováno v: Energies (19961073). Jun2024, Vol. 17 Issue 11, p2710. 15p.