Zobrazeno 1 - 10
of 12 957
pro vyhledávání: '"DING, Li"'
Autor:
Li, Jinhao, Xu, Jiaming, Huang, Shan, Chen, Yonghua, Li, Wen, Liu, Jun, Lian, Yaoxiu, Pan, Jiayi, Ding, Li, Zhou, Hao, Wang, Yu, Dai, Guohao
Large Language Models (LLMs) have demonstrated remarkable capabilities across various fields, from natural language understanding to text generation. Compared to non-generative LLMs like BERT and DeBERTa, generative LLMs like GPT series and Llama ser
Externí odkaz:
http://arxiv.org/abs/2410.04466
We propose a Mamba accelerator with reconfigurable architecture, MARCA.We propose three novel approaches in this paper. (1) Reduction alternative PE array architecture for both linear and element-wise operations. For linear operations, the reduction
Externí odkaz:
http://arxiv.org/abs/2409.11440
Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) uses human preferences to achieve this alignment. However, preferences sourced from diverse populations can
Externí odkaz:
http://arxiv.org/abs/2406.15599
Lexicase selection has been shown to provide advantages over other selection algorithms in several areas of evolutionary computation and machine learning. In its standard form, lexicase selection filters a population or other collection based on rand
Externí odkaz:
http://arxiv.org/abs/2401.12424
Autor:
Ding, Li, Spector, Lee
Publikováno v:
International Conference on Learning Representations (2022)
One potential drawback of using aggregated performance measurement in machine learning is that models may learn to accept higher errors on some training cases as compromises for lower errors on others, with the lower errors actually being instances o
Externí odkaz:
http://arxiv.org/abs/2312.12606
Navigating deceptive domains has often been a challenge in machine learning due to search algorithms getting stuck at sub-optimal local optima. Many algorithms have been proposed to navigate these domains by explicitly maintaining diversity or equiva
Externí odkaz:
http://arxiv.org/abs/2311.02283
We introduce EV3, a novel meta-optimization framework designed to efficiently train scalable machine learning models through an intuitive explore-assess-adapt protocol. In each iteration of EV3, we explore various model parameter updates, assess them
Externí odkaz:
http://arxiv.org/abs/2310.18893
Reinforcement Learning from Human Feedback (RLHF) has shown potential in qualitative tasks where easily defined performance measures are lacking. However, there are drawbacks when RLHF is commonly used to optimize for average human preferences, espec
Externí odkaz:
http://arxiv.org/abs/2310.12103
Autor:
Nan Zhang, Daifeng Tu, Ding Li, Kaixin Tang, Linpeng Nie, Houpu Li, Hongyu Li, Tao Qi, Tao Wu, Jianhui Zhou, Ziji Xiang, Xianhui Chen
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-9 (2024)
Abstract In Landau’s celebrated Fermi liquid theory, electrons in a metal obey the Wiedemann–Franz law at the lowest temperatures. This law states that electron heat and charge transport are linked by a constant L 0, i.e., the Sommerfeld value of
Externí odkaz:
https://doaj.org/article/02cc55df55044445b6e131a3e185264a
Autor:
Shengzi Jin, Yingce Zheng, Ding Li, Xingyao Liu, Tingting Zhu, Shuang Wang, Zhonghua Liu, Yun Liu
Publikováno v:
Breast Cancer Research, Vol 26, Iss 1, Pp 1-18 (2024)
Abstract Obesity is an important risk factor for breast cancer in women before and after menopause. Adipocytes, key mediators in the tumor microenvironment, play a pivotal role in the relationship between obesity with cancer. However, the potential o
Externí odkaz:
https://doaj.org/article/d747ce7a28564906b21eab1d902a7e7f