Search Results for author: Yiming Shi

Found 7 papers, 3 papers with code

LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning

1 code implementation17 Oct 2024 Yiming Shi, Jiwei Wei, Yujia Wu, Ran Ran, ChengWei Sun, Shiyuan He, Yang Yang

However, LoRA utilize random initialization and optimization of low-rank matrices to approximate updated weights, which can result in suboptimal convergence and an accuracy gap compared to full fine-tuning.

Image Classification Image Generation +3

Machine Translation Evaluation Benchmark for Wu Chinese: Workflow and Analysis

no code implementations14 Oct 2024 Hongjian Yu, Yiming Shi, Zherui Zhou, Christopher Haberland

We introduce a FLORES+ dataset as an evaluation benchmark for modern Wu Chinese machine translation models and showcase its compatibility with existing Wu data.

Machine Translation Translation

SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values

no code implementations9 Sep 2024 ChengWei Sun, Jiwei Wei, Yujia Wu, Yiming Shi, Shiyuan He, Zeyu Ma, Ning Xie, Yang Yang

Large pre-trained models (LPMs) have demonstrated exceptional performance in diverse natural language processing and computer vision tasks.

Domain Adaptation Image Classification +3

Rhyme-aware Chinese lyric generator based on GPT

no code implementations19 Aug 2024 Yixiao Yuan, Yangchen Huang, Yu Ma, Xinjin Li, Zhenglin Li, Yiming Shi, Huapeng Zhou

Neural language representation models such as GPT, pre-trained on large-scale corpora, can effectively capture rich semantic patterns from plain text and be fine-tuned to consistently improve natural language generation performance.

Text Generation

DiffLoRA: Generating Personalized Low-Rank Adaptation Weights with Diffusion

no code implementations13 Aug 2024 Yujia Wu, Yiming Shi, Jiwei Wei, ChengWei Sun, Yuyang Zhou, Yang Yang, Heng Tao Shen

Personalized text-to-image generation has gained significant attention for its capability to generate high-fidelity portraits of specific identities conditioned on user-defined prompts.

Text-to-Image Generation

USD: Unsupervised Soft Contrastive Learning for Fault Detection in Multivariate Time Series

1 code implementation25 May 2024 Hong Liu, Xiuxiu Qiu, Yiming Shi, Zelin Zang

Unsupervised fault detection in multivariate time series is critical for maintaining the integrity and efficiency of complex systems, with current methodologies largely focusing on statistical and machine learning techniques.

Contrastive Learning Data Augmentation +3

TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models

2 code implementations20 May 2024 Junlong Jia, Ying Hu, Xi Weng, Yiming Shi, Miao Li, Xingjian Zhang, Baichuan Zhou, Ziyu Liu, Jie Luo, Lei Huang, Ji Wu

We present TinyLLaVA Factory, an open-source modular codebase for small-scale large multimodal models (LMMs) with a focus on simplicity of code implementations, extensibility of new features, and reproducibility of training results.

Philosophy

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