Zobrazeno 1 - 10
of 4 523
pro vyhledávání: '"Zhao, Zhe"'
Autor:
Chen, Jiachi, Zhong, Qingyuan, Wang, Yanlin, Ning, Kaiwen, Liu, Yongkun, Xu, Zenan, Zhao, Zhe, Chen, Ting, Zheng, Zibin
The emergence of Large Language Models (LLMs) has significantly influenced various aspects of software development activities. Despite their benefits, LLMs also pose notable risks, including the potential to generate harmful content and being abused
Externí odkaz:
http://arxiv.org/abs/2409.15154
With the expansion of business scenarios, real recommender systems are facing challenges in dealing with the constantly emerging new tasks in multi-task learning frameworks. In this paper, we attempt to improve the generalization ability of multi-tas
Externí odkaz:
http://arxiv.org/abs/2408.17214
Autor:
Khani, Nikhil, Yang, Shuo, Nath, Aniruddh, Liu, Yang, Abbo, Pendo, Wei, Li, Andrews, Shawn, Kula, Maciej, Kahn, Jarrod, Zhao, Zhe, Hong, Lichan, Chi, Ed
Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research predominantly foc
Externí odkaz:
http://arxiv.org/abs/2408.14678
We present the Learned Ranking Function (LRF), a system that takes short-term user-item behavior predictions as input and outputs a slate of recommendations that directly optimizes for long-term user satisfaction. Most previous work is based on optim
Externí odkaz:
http://arxiv.org/abs/2408.06512
Generating realistic human grasps is a crucial yet challenging task for applications involving object manipulation in computer graphics and robotics. Existing methods often struggle with generating fine-grained realistic human grasps that ensure all
Externí odkaz:
http://arxiv.org/abs/2407.14062
In this paper, we introduce a subspace-inspired Low-Rank Adaptation (LoRA) method, which is computationally efficient, easy to implement, and readily applicable to large language, multimodal, and diffusion models. Initially, we equivalently decompose
Externí odkaz:
http://arxiv.org/abs/2406.11909
Autor:
Zhang, Yichi, Huang, Yao, Sun, Yitong, Liu, Chang, Zhao, Zhe, Fang, Zhengwei, Wang, Yifan, Chen, Huanran, Yang, Xiao, Wei, Xingxing, Su, Hang, Dong, Yinpeng, Zhu, Jun
Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited, lacking a holi
Externí odkaz:
http://arxiv.org/abs/2406.07057
While current automated essay scoring (AES) methods show high agreement with human raters, their scoring mechanisms are not fully explored. Our proposed method, using counterfactual intervention assisted by Large Language Models (LLMs), reveals that
Externí odkaz:
http://arxiv.org/abs/2405.19433
Large Language Models (LLMs) have gained significant attention in the field of natural language processing (NLP) due to their wide range of applications. However, training LLMs for languages other than English poses significant challenges, due to the
Externí odkaz:
http://arxiv.org/abs/2405.10626
Autor:
Zhao, Zhe, Wang, Pengkun, Wang, Xu, Wen, Haibin, Xie, Xiaolong, Zhou, Zhengyang, Zhang, Qingfu, Wang, Yang
Pre-training GNNs to extract transferable knowledge and apply it to downstream tasks has become the de facto standard of graph representation learning. Recent works focused on designing self-supervised pre-training tasks to extract useful and univers
Externí odkaz:
http://arxiv.org/abs/2404.14941