Projects

Kaggle-AI Model Prediction 2023/11

A competition that explores optimization objectives and methods for AI algorithms. In this competition, our aim was to train a machine learning model based on the runtime data provided to you in the training dataset and further predict the runtime of graphs and configurations in the test dataset. We used a Graph Convolutional Network (GCN) model to address this challenge. We also useadopted GCN convolution layers (GCNConv) to process the graph structure, facilitating the flow and integration of information between nodes. To further enhance the accuracy of predictions, we decided to employ model fusion on the aforementioned model. Our work achieved prediction and optimization of the operation of artificial intelligence models and algorithms. I received a Silver medal(4%) for this competition.

Competition AI Algorithm GitHub

Kaggle-LLM 2023/10

A competition of Kaggle that explore the potential of LLMs. We encoded the input using DeBERTa-v3-large and built a reading comprehension model using the AutoModelForMultipleChoice model from the Transformers library. When our model answers multiple-choice questions automatically, we first match the prompt and options with the original text and then use the model to predict the correct answer. We adopted a sentence vector approach by measuring the similarity between the prompt and the original Wikipedia texts to extract the most similar original text, which serves as the primary reference for the questions. Our model achieved a MAP@3 of 0.906 on the test set. Our work will effecively help researchers better understand the ability of LLMs to test themselves. I received a Bronze medal(7%) for this competition.

Competition LLM GitHub

CV-Hardware Co-designing for Steelworks 2023/09-Present

> Ported YOLOv5 model to FPGA using HLS Compiler and optimized the algorithms for hardware deployment scenarios. > Leveraged FPGA programmability to explore customized design for YOLOv5 in industrial settings. > Utilized a large dataset of images and videos from actual production to annotate the components of clay gun machines and trained the object detection model with YOLOv5. > Annotated feature sub-blocks on moving block images and fixed block images respectively, and trained the segmentation model for feature sub-blocks with YOLOv5.

Research CV Hardware FPGA Industrial application GitHub

COVID-19 Related Medical Text Summarization with BERT 2022/12-2023/01

> Developed a Chinese text encoding method based on BiLSTM and embedded it into the encoding layer. > Constructed innovatively an encoder comprising four components: a fine-tuned BERT-Embedding layer, a BiLSTM layer, a series of convolutional gates, and a self-attention mechanism layer. > Collected corpora independently from various medical-related Chinese publications and pre-trained the preprocessed data using BERT to enhance semantic representations in sentences. > Achieved automatic summarization for medical texts, significantly reducing the time cost of reading and material collection.

Project NLP BERT GitHub

See all 9 projects

Essays

[IJCAI2024] An LDA Model Augmented with BERT for Aspect Level Sentiment Analysis

06 Jan 2024

Aspect level sentiment analysis is a fine-grained task in affective analysis. It extracts aspects and their corresponding emotional polarities from opinionated texts. The first sub task of identifying the aspects with comments is called aspect extraction, which is the focus...

Paper LDA BERT NLP

[COLING 2024] Awareness of Time: Video-Language Models Embedding with Temporal Reasoning

25 Oct 2023

Video-language pre-training has significantly improved the performance of diverse downstream tasks related to video and language. However, existing approaches often directly adapt image-language pre-training paradigms to video-language tasks, neglecting the unique temporal characteristics of videos. In this paper, we present...

Paper Pre-trained language model Video-language model multimode

[Report] CoCoGPT

30 Jan 2023

Today, with the increasing risk of COVID-19 infection in the society, people who are suspected of COVID-19’s symptoms or have a greater risk of infection for various reasons will have some anxiety about medical consultation. Relatively, the pressure on the...

Report GPT BERT NLP

[Report] COVID-19 Related Medical Text Summarization Model Based on BERT

20 Jan 2023

Due to the unique nature of the COVID-19 pandemic, text data related to it has exhibited explosive growth in scale within a short period. This data is characterized by its diversity and significant variations. To comprehensively study this textual information...

Report BERT NLP

[Report] Monocular Depth Estimation on Atlas 200DK Develop Board

02 Jan 2023

The Atlas 200 DK Developer Kit (Model: 3000) is a high-performance AI application development board integrated with Ascend processors. It facilitates users in rapid development and validation, making it versatile for applications such as developer solution verification, higher education, and...

Report CV Hardware

[CONF-SPML 2023] BERT for Sentiment Analysis in the Era of Epidemic

30 Sep 2022

With the continuous progress of Internet technology, the network platform has gradually entered everyone’s life, providing a platform for ordinary people to express their ideas. Since the occurrence of COVID-19, monitoring and analyzing public opinion on the Internet platform has...

Paper NLP Data Science Deep Learning

Josh Li