2 citations · 4 across the 8 of their papers we have counts for
8 papers
Physics-Constrained Co-Optimization and Data-Driven Layer-Resolved Classification of a Hybrid CZT/PIPS Detector for Mixed Radiation Fields
Renlong Jie, Fan Yang, Shouzhi Xi +2
Compact mixed-radiation instruments must preserve a low-mass charged-particle entrance while providing enough high-Z depth for photon sensitivity. We first compare two detector hea…
Prompt-Based Length Controlled Generation with Multiple Control Types
Renlong Jie, Xiaojun Meng, Lifeng Shang +2
Large language models (LLMs) have attracted great attention given their strong performance on a wide range of NLP tasks. In practice, users often expect generated texts to fall wit…
Unsupervised Extractive Summarization with Learnable Length Control Strategies
Renlong Jie, Xiaojun Meng, Xin Jiang +1
Unsupervised extractive summarization is an important technique in information extraction and retrieval. Compared with supervised method, it does not require high-quality human-lab…
Prompt-Based Length Controlled Generation with Reinforcement Learning
Renlong Jie, Xiaojun Meng, Lifeng Shang +2
Large language models (LLMs) like ChatGPT and GPT-4 have attracted great attention given their surprising performance on a wide range of NLP tasks. Length controlled generation of…
Enhancing Coherence of Extractive Summarization with Multitask Learning
Renlong Jie, Xiaojun Meng, Lifeng Shang +2
This study proposes a multitask learning architecture for extractive summarization with coherence boosting. The architecture contains an extractive summarizer and coherent discrimi…
Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures
Renlong Jie, Junbin Gao
This study aims at making the architecture search process more adaptive for one-shot or online training. It is extended from the existing study on differentiable neural architectur…
Regularized Flexible Activation Function Combinations for Deep Neural Networks
Renlong Jie, Junbin Gao, Andrey Vasnev +1
Activation in deep neural networks is fundamental to achieving non-linear mappings. Traditional studies mainly focus on finding fixed activations for a particular set of learning t…
Adaptive Hierarchical Hyper-gradient Descent
Renlong Jie, Junbin Gao, Andrey Vasnev +1
In this study, we investigate learning rate adaption at different levels based on the hyper-gradient descent framework and propose a method that adaptively learns the optimizer par…