Zobrazeno 1 - 10
of 2 994
pro vyhledávání: '"WU Zhenyu"'
Autor:
Sun, Qiushi, Cheng, Kanzhi, Ding, Zichen, Jin, Chuanyang, Wang, Yian, Xu, Fangzhi, Wu, Zhenyu, Jia, Chengyou, Chen, Liheng, Liu, Zhoumianze, Kao, Ben, Li, Guohao, He, Junxian, Qiao, Yu, Wu, Zhiyong
Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability. Despite their utility in advancing digital automation, a critical bottleneck persists: collecting high-quality tr
Externí odkaz:
http://arxiv.org/abs/2412.19723
In recent years, infrastructure-based localization methods have achieved significant progress thanks to their reliable and drift-free localization capability. However, the pre-installed infrastructures suffer from inflexibilities and high maintenance
Externí odkaz:
http://arxiv.org/abs/2411.06182
Autor:
Wu, Zhiyong, Wu, Zhenyu, Xu, Fangzhi, Wang, Yian, Sun, Qiushi, Jia, Chengyou, Cheng, Kanzhi, Ding, Zichen, Chen, Liheng, Liang, Paul Pu, Qiao, Yu
Existing efforts in building GUI agents heavily rely on the availability of robust commercial Vision-Language Models (VLMs) such as GPT-4o and GeminiProVision. Practitioners are often reluctant to use open-source VLMs due to their significant perform
Externí odkaz:
http://arxiv.org/abs/2410.23218
Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems. However, this repeated indepen
Externí odkaz:
http://arxiv.org/abs/2410.12934
In this paper, we propose a new framework for zero-shot object navigation. Existing zero-shot object navigation methods prompt LLM with the text of spatially closed objects, which lacks enough scene context for in-depth reasoning. To better preserve
Externí odkaz:
http://arxiv.org/abs/2410.08189
Taxonomies play a crucial role in various applications by providing a structural representation of knowledge. The task of taxonomy expansion involves integrating emerging concepts into existing taxonomies by identifying appropriate parent concepts fo
Externí odkaz:
http://arxiv.org/abs/2408.09070
Autor:
Shen, Hongming, Wu, Zhenyu, Wang, Wei, Lyu, Qiyang, Zhou, Huiqin, Deng, Tianchen, Zhu, Yeqing, Wang, Danwei
In recent years, LiDAR-based localization and mapping methods have achieved significant progress thanks to their reliable and real-time localization capability. Considering single LiDAR odometry often faces hardware failures and degradation in practi
Externí odkaz:
http://arxiv.org/abs/2408.04901
Enabling embodied agents to complete complex human instructions from natural language is crucial to autonomous systems in household services. Conventional methods can only accomplish human instructions in the known environment where all interactive o
Externí odkaz:
http://arxiv.org/abs/2406.11818
Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find that a si
Externí odkaz:
http://arxiv.org/abs/2405.14092
Math word problem (MWP) solving requires generating a reasoning path based on a given problem description that often contains irrelevant conditions. Existing chain-of-thought (CoT) prompting methods elicited multi-step reasoning abilities of large la
Externí odkaz:
http://arxiv.org/abs/2403.12744