Výsledky vyhledávání - "Liu Jiazheng"

Akademický článek

Three-dimensional reconstruction of rat sperm using volume electron microscopy

Autor: Liu Jiazheng, Lin Limei, Zhang Lina, Ma Hongtu, Chen Xi, Pang Keliang, Li Linlin, Han Hua

Publikováno v: Acta Biochimica et Biophysica Sinica, Vol 56, Pp 1699-1705 (2024)

Three-dimensional (3D) reconstruction serves as a crucial instrument for the analysis of biological structures. In particular, a comprehensive and accurate 3D ultrastructural examination of rat sperm is vital for understanding and diagnosing male fer

Externí odkaz: https://doaj.org/article/b538d18e1c484873a0972fcb54411826

Zobrazit plný text záznamu

Report

Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds

Autor: Zheng, Sipeng, Liu, Jiazheng, Feng, Yicheng, Lu, Zongqing

Recent studies have presented compelling evidence that large language models (LLMs) can equip embodied agents with the self-driven capability to interact with the world, which marks an initial step toward versatile robotics. However, these efforts te

Externí odkaz: http://arxiv.org/abs/2310.13255

Zobrazit plný text záznamu

Report

LLaMA Rider: Spurring Large Language Models to Explore the Open World

Autor: Feng, Yicheng, Wang, Yuxuan, Liu, Jiazheng, Zheng, Sipeng, Lu, Zongqing

Recently, various studies have leveraged Large Language Models (LLMs) to help decision-making and planning in environments, and try to align the LLMs' knowledge with the world conditions. Nonetheless, the capacity of LLMs to continuously acquire envi

Externí odkaz: http://arxiv.org/abs/2310.08922

Zobrazit plný text záznamu

Report

Blind2Sound: Self-Supervised Image Denoising without Residual Noise

Autor: Wang, Zejin, Liu, Jiazheng, Zhai, Hao, Han, Hua

Self-supervised blind denoising for Poisson-Gaussian noise remains a challenging task. Pseudo-supervised pairs constructed from single noisy images re-corrupt the signal and degrade the performance. The visible blindspots solve the information loss i

Externí odkaz: http://arxiv.org/abs/2303.05183

Zobrazit plný text záznamu

Report

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots

Autor: Wang, Zejin, Liu, Jiazheng, Li, Guoqing, Han, Hua

Real noisy-clean pairs on a large scale are costly and difficult to obtain. Meanwhile, supervised denoisers trained on synthetic data perform poorly in practice. Self-supervised denoisers, which learn only from single noisy images, solve the data col

Externí odkaz: http://arxiv.org/abs/2203.06967

Zobrazit plný text záznamu