1 code implementation • 3 Feb 2024 • Yichao Fu, Peter Bailis, Ion Stoica, Hao Zhang
Autoregressive decoding of large language models (LLMs) is memory bandwidth bounded, resulting in high latency and significant wastes of the parallel processing power of modern accelerators.
no code implementations • 9 Aug 2023 • Shangde Gao, Ke Liu, Yichao Fu
In typical recommendation scenarios, the user-item interaction paradigm is usually a two-stage process and requires static clustering analysis of the obtained user and item representations.
no code implementations • 27 Jul 2023 • Shangde Gao, Yichao Fu, Ke Liu, Yuqiang Han
Current methods focus on coarsely aligning teachers and students in the common representation space, making it difficult for the student to learn the proper decision boundaries from a set of heterogeneous teachers.
1 code implementation • 21 Jul 2023 • Dong Huang, Qingwen Bu, Yahao Qing, Yichao Fu, Heming Cui
Current test metrics, however, are primarily concerned with the neurons, which means that test cases that are discovered either by guided fuzzing or selection with these metrics focus on detecting fault-inducing neurons while failing to detect fault-inducing feature maps.
no code implementations • 20 Jul 2023 • Dong Huang, Qingwen Bu, Yichao Fu, Yuhao QING, Bocheng Xiao, Heming Cui
To address the above-mentioned problem, we propose NSS, Neuron Sensitivity guided test case Selection, which can reduce the labeling time by selecting valuable test cases from unlabeled datasets.
no code implementations • 11 Jun 2023 • Wensong Bai, Chao Zhang, Yichao Fu, Lingwei Peng, Hui Qian, Bin Dai
In this paper, we propose the first fully push-forward-based Distributional Reinforcement Learning algorithm, called Push-forward-based Actor-Critic EncourageR (PACER).
no code implementations • 29 Sep 2021 • Fanxin Li, Shixiong Zhao, Haowen Pi, Yuhao QING, Yichao Fu, Sen Wang, Heming Cui
Neural Architecture Search (NAS) automatically searches for well-performed network architectures from a given search space.