ACL

Broken Words, Broken Performance: Effect of Tokenization on Performance of LLMs

破碎的词，破碎的性能：分词对大语言模型性能的影响

Sachin Pawar, Manoj Apte, Kshitij Jadhav, Girish Keshav Palshikar, Nitin Ramrakhiyani

机构 * TCS Research（塔塔咨询服务研究） 纠错

AI总结 本文研究了分词对大语言模型性能的影响，提出惩罚函数量化分词质量，并验证其在多个NLP任务上的统计显著性。

Comments International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2025)

CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory

CityNavAgent：基于层次语义规划和全局记忆的空中视觉-语言导航

Weichen Zhang, Chen Gao, Shiquan Yu, Ruiying Peng, Baining Zhao, Qian Zhang, Jinqiang Cui, Xinlei Chen, Yong Li

机构 * Tsinghua University（清华大学） 纠错

AI总结 CityNavAgent通过层次语义规划和全局记忆模块，提升空中视觉-语言导航在复杂城市环境中的导航性能。

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces

UrbanVideo-Bench: 基于城市空间视频数据评估视觉-语言模型的具身智能

Baining Zhao, Jianjie Fang, Zichao Dai, Ziyou Wang, Jirong Zha, Weichen Zhang, Chen Gao, Yue Wang, Jinqiang Cui, Xinlei Chen, Yong Li

机构 * Tsinghua University（清华大学） 纠错

AI总结 UrbanVideo-Bench通过城市空间视频数据评估视频大语言模型的具身智能，揭示其在城市环境中感知、推理和导航能力的局限性，并验证了Sim-to-Real迁移的潜力。

Comments 22 pages

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 32400-32423, 2025