Search Results for author: Zehua Pei

Found 5 papers, 1 papers with code

FuseGPT: Learnable Layers Fusion of Generative Pre-trained Transformers

no code implementations21 Nov 2024 Zehua Pei, Hui-Ling Zhen, Xianzhi Yu, Sinno Jialin Pan, Mingxuan Yuan, Bei Yu

In this paper, we propose FuseGPT, a novel methodology to recycle the pruned transformer blocks to further recover the model performance.

DiLA: Enhancing LLM Tool Learning with Differential Logic Layer

no code implementations19 Feb 2024 Yu Zhang, Hui-Ling Zhen, Zehua Pei, Yingzhao Lian, Lihao Yin, Mingxuan Yuan, Bei Yu

In this paper, we propose a novel differential logic layer-aided language modeling (DiLA) approach, where logical constraints are integrated into the forward and backward passes of a network layer, to provide another option for LLM tool learning.

Language Modeling Language Modelling +1

BetterV: Controlled Verilog Generation with Discriminative Guidance

no code implementations3 Feb 2024 Zehua Pei, Hui-Ling Zhen, Mingxuan Yuan, Yu Huang, Bei Yu

In this work, we propose a Verilog generation framework, BetterV, which fine-tunes the large language models (LLMs) on processed domain-specific datasets and incorporates generative discriminators for guidance on particular design demands.

Text Generation

Physics-Informed Optical Kernel Regression Using Complex-valued Neural Fields

no code implementations15 Mar 2023 Guojin Chen, Zehua Pei, HaoYu Yang, Yuzhe ma, Bei Yu, Martin D. F. Wong

Lithography is fundamental to integrated circuit fabrication, necessitating large computation overhead.

regression

A Systematic Survey of Deep Learning-based Single-Image Super-Resolution

1 code implementation29 Sep 2021 Juncheng Li, Zehua Pei, Wenjie Li, Guangwei Gao, Longguang Wang, Yingqian Wang, Tieyong Zeng

This is an exhaustive survey of SISR, which can help researchers better understand SISR and inspire more exciting research in this field.

Deep Learning Image Quality Assessment +2

Cannot find the paper you are looking for? You can Submit a new open access paper.