Zobrazeno 1 - 10
of 229
pro vyhledávání: '"Wei, Zhongyu"'
Autor:
Liu, Shujun, Shen, Xiaoyu, Lai, Yuhang, Wang, Siyuan, Yue, Shengbin, Huang, Zengfeng, Huang, Xuanjing, Wei, Zhongyu
The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the conventional trai
Externí odkaz:
http://arxiv.org/abs/2407.04185
The rapid development of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has exposed vulnerabilities to various adversarial attacks. This paper provides a comprehensive overview of jailbreaking research targeting both LLMs a
Externí odkaz:
http://arxiv.org/abs/2406.14859
Autor:
Liang, Jingcong, Wang, Junlong, Zhai, Xinyu, Zhuang, Yungui, Zheng, Yiyang, Xu, Xin, Ran, Xiandong, Dong, Xiaozheng, Rong, Honghui, Liu, Yanlun, Chen, Hao, Wei, Yuhan, Li, Donghai, Peng, Jiajie, Huang, Xuanjing, Shi, Chongde, Feng, Yansong, Song, Yun, Wei, Zhongyu
We give a detailed overview of the CAIL 2023 Argument Mining Track, one of the Chinese AI and Law Challenge (CAIL) 2023 tracks. The main goal of the track is to identify and extract interacting argument pairs in trial dialogs. It mainly uses summariz
Externí odkaz:
http://arxiv.org/abs/2406.14503
The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly evaluated, leaving the gap bet
Externí odkaz:
http://arxiv.org/abs/2406.05756
While large multi-modal models (LMMs) have exhibited impressive capabilities across diverse tasks, their effectiveness in handling complex tasks has been limited by the prevailing single-step reasoning paradigm. To this end, this paper proposes VoCoT
Externí odkaz:
http://arxiv.org/abs/2405.16919
Autor:
Jiao, Shujian, Li, Bingxuan, Wang, Lei, Zhang, Xiaojin, Chen, Wei, Peng, Jiajie, Wei, Zhongyu
Proteins are essential to life's processes, underpinning evolution and diversity. Advances in sequencing technology have revealed millions of proteins, underscoring the need for sophisticated pre-trained protein models for biological analysis and AI
Externí odkaz:
http://arxiv.org/abs/2404.15805
Autor:
Du, Mengfei, Wu, Binhao, Zhang, Jiwen, Fan, Zhihao, Li, Zejun, Luo, Ruipu, Huang, Xuanjing, Wei, Zhongyu
Vision-and-Language navigation (VLN) requires an agent to navigate in unseen environment by following natural language instruction. For task completion, the agent needs to align and integrate various navigation modalities, including instruction, obse
Externí odkaz:
http://arxiv.org/abs/2404.01994
Autor:
Liang, Jingcong, Ye, Rong, Han, Meng, Lai, Ruofei, Zhang, Xinyu, Huang, Xuanjing, Wei, Zhongyu
How can we construct an automated debate judge to evaluate an extensive, vibrant, multi-turn debate? This task is challenging, as judging a debate involves grappling with lengthy texts, intricate argument relationships, and multi-dimensional assessme
Externí odkaz:
http://arxiv.org/abs/2403.08010
We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework addresses the
Externí odkaz:
http://arxiv.org/abs/2403.06754
Autor:
Zhang, Jiwen, Wu, Jihao, Teng, Yihua, Liao, Minghui, Xu, Nuo, Xiao, Xiao, Wei, Zhongyu, Tang, Duyu
Large language model (LLM) leads to a surge of autonomous GUI agents for smartphone, which completes a task triggered by natural language through predicting a sequence of actions of API. Even though the task highly relies on past actions and visual o
Externí odkaz:
http://arxiv.org/abs/2403.02713