Výsledky vyhledávání - "Zhang, Bowei"

Report

QUILL: Quotation Generation Enhancement of Large Language Models

Autor: Xiao, Jin, Zhang, Bowei, He, Qianyu, Liang, Jiaqing, Wei, Feng, Chen, Jinglei, Liang, Zujie, Yang, Deqing, Xiao, Yanghua

While Large language models (LLMs) have become excellent writing assistants, they still struggle with quotation generation. This is because they either hallucinate when providing factual quotations or fail to provide quotes that exceed human expectat

Externí odkaz: http://arxiv.org/abs/2411.03675

Zobrazit plný text záznamu

Report

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

Autor: Wang, Zihao, Cai, Shaofei, Liu, Anji, Jin, Yonggang, Hou, Jinbing, Zhang, Bowei, Lin, Haowei, He, Zhaofeng, Zheng, Zilong, Yang, Yaodong, Ma, Xiaojian, Liang, Yitao

Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle

Externí odkaz: http://arxiv.org/abs/2311.05997

Zobrazit plný text záznamu

Report

GROOT: Learning to Follow Instructions by Watching Gameplay Videos

Autor: Cai, Shaofei, Zhang, Bowei, Wang, Zihao, Ma, Xiaojian, Liu, Anji, Liang, Yitao

We study the problem of building a controller that can follow open-ended instructions in open-world environments. We propose to follow reference videos as instructions, which offer expressive goal specifications while eliminating the need for expensi

Externí odkaz: http://arxiv.org/abs/2310.08235

Zobrazit plný text záznamu

Dissertation/ Thesis

Guidelines for Identifying and Combating Over Work for Creative Worker while Working from Home

Autor: Zhang, Bowei

COVID-19 greatly accelerated the adoption of work from home, and exposed many more people to the challenges of keeping a healthy work-life balance without commuting. At the same time more and more people are choosing to freelance instead of work for

Externí odkaz: http://rave.ohiolink.edu/etdc/view?acc_num=ucin1649762160075231

Zobrazit plný text záznamu

Report

Efficient Algorithms for Obnoxious Facility Location on a Line Segment or Circle

Autor: Zhang, Bowei

We study different restricted variations of the obnoxious facility location problem on a plane. The first is the constrained obnoxious facility location on a line segment (COFL-Line) problem. We provide an efficient algorithm for this problem that ex

Externí odkaz: http://arxiv.org/abs/2210.07146

Zobrazit plný text záznamu