Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Yang, Xinyu"'
Autor:
Xu, Ceyu, Wu, Yongji, Yang, Xinyu, Chen, Beidi, Lentz, Matthew, Zhuo, Danyang, Wills, Lisa Wu
As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottlenecks for the training and inference of LLMs. To mitigate these bottleneck
Externí odkaz:
http://arxiv.org/abs/2407.00467
Reinforcement Learning from Human Feedback (RLHF) involves training policy models (PMs) and reward models (RMs) to align language models with human preferences. Instead of focusing solely on PMs and RMs independently, we propose to examine their inte
Externí odkaz:
http://arxiv.org/abs/2406.07971
Autor:
Guo, Wentao, Long, Jikai, Zeng, Yimeng, Liu, Zirui, Yang, Xinyu, Ran, Yide, Gardner, Jacob R., Bastani, Osbert, De Sa, Christopher, Yu, Xiaodong, Chen, Beidi, Xu, Zhaozhuo
Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language Models using only forward passes. However, the application of ZO fine-tuning in memory-constrained settings such as mobile phones and laptops is still challe
Externí odkaz:
http://arxiv.org/abs/2406.02913
Autor:
Hu, Guanyu, Papadopoulou, Eleni, Kollias, Dimitrios, Tzouveli, Paraskevi, Wei, Jie, Yang, Xinyu
The increasing integration of machine learning algorithms in daily life underscores the critical need for fairness and equity in their deployment. As these technologies play a pivotal role in decision-making, addressing biases across diverse subpopul
Externí odkaz:
http://arxiv.org/abs/2405.06841
Autor:
Mu, Zhaoxi, Yang, Xinyu
The integration of visual cues has revitalized the performance of the target speech extraction task, elevating it to the forefront of the field. Nevertheless, this multi-modal learning paradigm often encounters the challenge of modality imbalance. In
Externí odkaz:
http://arxiv.org/abs/2404.12725
With large language models (LLMs) widely deployed in long content generation recently, there has emerged an increasing demand for efficient long-sequence inference support. However, key-value (KV) cache, which is stored to avoid re-computation, has e
Externí odkaz:
http://arxiv.org/abs/2404.11912
Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational shortcut that requires storing previous KV pairs during decoding. While
Externí odkaz:
http://arxiv.org/abs/2402.09398
Autor:
Liang, Weixin, Rajani, Nazneen, Yang, Xinyu, Ozoani, Ezinwanne, Wu, Eric, Chen, Yiqun, Smith, Daniel Scott, Zou, James
The rapid proliferation of AI models has underscored the importance of thorough documentation, as it enables users to understand, trust, and effectively utilize these models in various applications. Although developers are encouraged to produce model
Externí odkaz:
http://arxiv.org/abs/2402.05160
Advances in machine learning are closely tied to the creation of datasets. While data documentation is widely recognized as essential to the reliability, reproducibility, and transparency of ML, we lack a systematic empirical understanding of current
Externí odkaz:
http://arxiv.org/abs/2401.13822
Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the reference
Externí odkaz:
http://arxiv.org/abs/2312.10305