no code implementations • 31 Jan 2025 • Ruiyu Wang, Yu Yuan, Shizhao Sun, Jiang Bian
In this work, we introduce CADFusion, a framework that uses Large Language Models (LLMs) as the backbone and alternates between two training stages: the sequential learning (SL) stage and the visual feedback (VF) stage.
no code implementations • 27 Dec 2024 • Jiawei Lin, Shizhao Sun, Danqing Huang, Ting Liu, Ji Li, Jiang Bian
Based on the planning results, it subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context.
no code implementations • 17 Dec 2024 • Haoyi Zhang, Shizhao Sun, Yibo Lin, Runsheng Wang, Jiang Bian
Third, we introduce a proofreading strategy that allows LLMs to incrementally correct the errors in the initial design, akin to human designers who iteratively check and adjust the initial topology design to ensure accuracy.
no code implementations • 5 Nov 2024 • Zhanwei Zhang, Shizhao Sun, Wenxiao Wang, Deng Cai, Jiang Bian
First, to enhance comprehension by LLMs, we represent a CAD model as a structured text by abstracting each hierarchy as a sequence of text tokens.
no code implementations • 26 Jul 2024 • Xu Yang, Haotian Chen, Wenjun Feng, Haoxue Wang, Zeqi Ye, Xinjie Shen, Xiao Yang, Shizhao Sun, Weiqing Liu, Jiang Bian
By leveraging the strong complex problem-solving capabilities of large language models (LLMs), we propose an LLM-based autonomous agent, equipped with a strategy named Collaborative Knowledge-STudying-Enhanced Evolution by Retrieval (Co-STEER), to simultaneously address all the challenges.
1 code implementation • NeurIPS 2023 • Jiawei Lin, Jiaqi Guo, Shizhao Sun, Zijiang James Yang, Jian-Guang Lou, Dongmei Zhang
In this work, we propose LayoutPrompter, which leverages large language models (LLMs) to address the above problems through in-context learning.
no code implementations • ICCV 2023 • Jiawei Lin, Jiaqi Guo, Shizhao Sun, Weijiang Xu, Ting Liu, Jian-Guang Lou, Dongmei Zhang
To model combined and incomplete constraints, we use a Transformer-based layout generation model and carefully design a way to represent constraints and layouts as sequences.
1 code implementation • ICCV 2023 • Junyi Zhang, Jiaqi Guo, Shizhao Sun, Jian-Guang Lou, Dongmei Zhang
To tackle the challenge, we summarize three critical factors for achieving a mild forward process for the layout, i. e., legality, coordinate proximity and type disruption.
no code implementations • CVPR 2023 • Zhaoyun Jiang, Jiaqi Guo, Shizhao Sun, Huayu Deng, Zhongkai Wu, Vuksan Mijovic, Zijiang James Yang, Jian-Guang Lou, Dongmei Zhang
First, to flexibly handle diverse constraints, we propose a constraint serialization scheme, which represents different user constraints as sequences of tokens with a predefined format.
no code implementations • IJCNLP 2019 • Zhen Dong, Shizhao Sun, Hongzhi Liu, Jian-Guang Lou, Dongmei Zhang
On text-to-SQL generation, the input utterance usually contains lots of tokens that are related to column names or cells in the table, called \textit{table-related tokens}.
no code implementations • 27 Sep 2017 • Shizhao Sun, Wei Chen, Jiang Bian, Xiaoguang Liu, Tie-Yan Liu
However, with the increasing size of DNN models and the large number of workers in practice, this typical data parallelism cannot achieve satisfactory training acceleration, since it usually suffers from the heavy communication cost due to transferring huge amount of information between workers and the parameter server.
no code implementations • 2 Jun 2016 • Shizhao Sun, Wei Chen, Jiang Bian, Xiaoguang Liu, Tie-Yan Liu
In this framework, we propose to aggregate the local models by ensemble, i. e., averaging the outputs of local models instead of the parameters.
no code implementations • 17 Jun 2015 • Shizhao Sun, Wei Chen, Li-Wei Wang, Xiaoguang Liu, Tie-Yan Liu
First, we derive an upper bound for RA of DNN, and show that it increases with increasing depth.