Jasper Leo

Jasper Leo

Gain and loss are equal.

Posts by Tags

AI Agents

Stealth Startup AI Algorithm Engineer Internship Experience

less than 1 minute read

Published:

The company is an overseas startup located in Canada, which wants to build Artificial General Intelligence (AGI) applications in several fields based on the hot technology of large language model. During my internship, I collaborated with several colleagues to develop and deploy web-based AGI intelligences for the Kapwing video editing website and the Instantly email management website based on the techniques of prompt engineering and tool learning.

Algorithm Improvement

Graduation Design

less than 1 minute read

Published:

The title of this graduation design is “Research on Hierarchical Reinforcement Learning Algorithm Based on Option”. After thorough research and thesis study, I implemented an algorithm improvement based on the mainstream IOC algorithm, and tested it in multiple environments for specific evaluation metrics, and verified the improvement of reward scores and interpretability metrics.

Artificial General Intelligence

Rebuttal of AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

CHI 2024

CHI alt 2024 Conference Reviewer

less than 1 minute read

Published:

CHI conference is called ACM Conference on Human Factors in Computing Systems, which belongs to CCF-A category. CHI has an open review channel for alt.CHI papers, which allows anyone to review papers under real names.

COLIEE 2024

CV

‘QA-BOT’ Business Q&A Robot

less than 1 minute read

Published:

QA-BOT is an edge AI deployment that detects human gaze, recognizes speech, and implements various business Q&A dialogues based on few-shot learning implemented by open-source large language models. It is low cost, lightweight and easy to fine-tune compared to the market.

Intelligent Car ‘GrandPa’

less than 1 minute read

Published:

The project covers environmental monitoring, intelligent tracking based on AprilTag, four-axis motor drive, and wifi image transmission and remote control. The project is based on python embedded implementation of face recognition, target tracking and other functions.

ChatGPT

CoT and Prompting

Code Generation and Understanding

Computer Vision

A Gesture-Assisted Real-Time Image Description Smart Hardware

less than 1 minute read

Published:

The project deploys deep learning algorithms such as Image Captioning and gesture recognition in AI hardware training. It helps people to get a summary description of the screen or environment and assists visually impaired people to understand their surroundings.

ConvLSTM

Data Augmentation

Meta-DM: Applications of Diffusion Models on Few-Shot Learning

less than 1 minute read

Published:

A paper was produced and submitted to the NIPS 2023 conference and has been rejected. The paper investigates a data augmentation application of the mainstream diffusion model on the small sample task of images. It mainly proposes the Meta-DM framework and verifies that several mainstream algorithms combined with Meta-DM can significantly improve their performance and achieve SOTA.

Database

Social APP ‘MINT’

less than 1 minute read

Published:

Based on uniapp and uniCloud, we implemented MINT, a campus social networking application based on “small tasks” and user personality portraits, using recommendation algorithms, front-end and back-end technologies, javascript programming, etc.

Deep Learning

Diffusion Models

Meta-DM: Applications of Diffusion Models on Few-Shot Learning

less than 1 minute read

Published:

A paper was produced and submitted to the NIPS 2023 conference and has been rejected. The paper investigates a data augmentation application of the mainstream diffusion model on the small sample task of images. It mainly proposes the Meta-DM framework and verifies that several mainstream algorithms combined with Meta-DM can significantly improve their performance and achieve SOTA.

English

Stealth Startup AI Algorithm Engineer Internship Experience

less than 1 minute read

Published:

The company is an overseas startup located in Canada, which wants to build Artificial General Intelligence (AGI) applications in several fields based on the hot technology of large language model. During my internship, I collaborated with several colleagues to develop and deploy web-based AGI intelligences for the Kapwing video editing website and the Instantly email management website based on the techniques of prompt engineering and tool learning.

Face Recognition

‘QA-BOT’ Business Q&A Robot

less than 1 minute read

Published:

QA-BOT is an edge AI deployment that detects human gaze, recognizes speech, and implements various business Q&A dialogues based on few-shot learning implemented by open-source large language models. It is low cost, lightweight and easy to fine-tune compared to the market.

Faiss

The Law Large Language Model Project

less than 1 minute read

Published:

This project mainly relies on the technical route of prompt learning and partial parameter fine-tuning of open-source large language models to realize a large-model intelligent assistant in the legal vertical field for professionals and the public, targeting legal documents, Q&A and legal data. I am responsible for framework design, deployment fine-tuning, evaluation session and interaction design. Check our project’s code, dataset and checkpoints in github.

Faiss and Vector Database

Few-Shot Learning

‘QA-BOT’ Business Q&A Robot

less than 1 minute read

Published:

QA-BOT is an edge AI deployment that detects human gaze, recognizes speech, and implements various business Q&A dialogues based on few-shot learning implemented by open-source large language models. It is low cost, lightweight and easy to fine-tune compared to the market.

Few-shot Learning

Meta-DM: Applications of Diffusion Models on Few-Shot Learning

less than 1 minute read

Published:

A paper was produced and submitted to the NIPS 2023 conference and has been rejected. The paper investigates a data augmentation application of the mainstream diffusion model on the small sample task of images. It mainly proposes the Meta-DM framework and verifies that several mainstream algorithms combined with Meta-DM can significantly improve their performance and achieve SOTA.

Financial

Financial Data Prediction Based on Wavelet Analysis and Kalman Filter Algorithms

less than 1 minute read

Published:

The experimental part uses real stock market data, denoising and feature extraction of the data by wavelet analysis, and Kalman filtering for state estimation and prediction. The experimental results show that the method of combining wavelet analysis and Kalman filtering can significantly improve the accuracy of prediction compared to using traditional prediction models alone.

Finetuning

Rebuttal of AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

The Law Large Language Model Project

less than 1 minute read

Published:

This project mainly relies on the technical route of prompt learning and partial parameter fine-tuning of open-source large language models to realize a large-model intelligent assistant in the legal vertical field for professionals and the public, targeting legal documents, Q&A and legal data. I am responsible for framework design, deployment fine-tuning, evaluation session and interaction design. Check our project’s code, dataset and checkpoints in github.

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

HCI

CHI alt 2024 Conference Reviewer

less than 1 minute read

Published:

CHI conference is called ACM Conference on Human Factors in Computing Systems, which belongs to CCF-A category. CHI has an open review channel for alt.CHI papers, which allows anyone to review papers under real names.

Hallucination

Hierarchical RL

Graduation Design

less than 1 minute read

Published:

The title of this graduation design is “Research on Hierarchical Reinforcement Learning Algorithm Based on Option”. After thorough research and thesis study, I implemented an algorithm improvement based on the mainstream IOC algorithm, and tested it in multiple environments for specific evaluation metrics, and verified the improvement of reward scores and interpretability metrics.

Image Captioning

A Gesture-Assisted Real-Time Image Description Smart Hardware

less than 1 minute read

Published:

The project deploys deep learning algorithms such as Image Captioning and gesture recognition in AI hardware training. It helps people to get a summary description of the screen or environment and assists visually impaired people to understand their surroundings.

In Context Learning

Instructions Finetuning

Javascript

Social APP ‘MINT’

less than 1 minute read

Published:

Based on uniapp and uniCloud, we implemented MINT, a campus social networking application based on “small tasks” and user personality portraits, using recommendation algorithms, front-end and back-end technologies, javascript programming, etc.

Kalman Filter

Financial Data Prediction Based on Wavelet Analysis and Kalman Filter Algorithms

less than 1 minute read

Published:

The experimental part uses real stock market data, denoising and feature extraction of the data by wavelet analysis, and Kalman filtering for state estimation and prediction. The experimental results show that the method of combining wavelet analysis and Kalman filtering can significantly improve the accuracy of prediction compared to using traditional prediction models alone.

LLM Agents

Rebuttal of AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

LLM Evaluation

CHI alt 2024 Conference Reviewer

less than 1 minute read

Published:

CHI conference is called ACM Conference on Human Factors in Computing Systems, which belongs to CCF-A category. CHI has an open review channel for alt.CHI papers, which allows anyone to review papers under real names.

LLM Stacking and Boosting

Language Grouding

Rebuttal of AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

Large Language Model

Rebuttal of AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

Large Language Models

The Law Large Language Model Project

less than 1 minute read

Published:

This project mainly relies on the technical route of prompt learning and partial parameter fine-tuning of open-source large language models to realize a large-model intelligent assistant in the legal vertical field for professionals and the public, targeting legal documents, Q&A and legal data. I am responsible for framework design, deployment fine-tuning, evaluation session and interaction design. Check our project’s code, dataset and checkpoints in github.

‘QA-BOT’ Business Q&A Robot

less than 1 minute read

Published:

QA-BOT is an edge AI deployment that detects human gaze, recognizes speech, and implements various business Q&A dialogues based on few-shot learning implemented by open-source large language models. It is low cost, lightweight and easy to fine-tune compared to the market.

Machine Learning

Natural Language Processing

A Gesture-Assisted Real-Time Image Description Smart Hardware

less than 1 minute read

Published:

The project deploys deep learning algorithms such as Image Captioning and gesture recognition in AI hardware training. It helps people to get a summary description of the screen or environment and assists visually impaired people to understand their surroundings.

Online Meeting

Stealth Startup AI Algorithm Engineer Internship Experience

less than 1 minute read

Published:

The company is an overseas startup located in Canada, which wants to build Artificial General Intelligence (AGI) applications in several fields based on the hot technology of large language model. During my internship, I collaborated with several colleagues to develop and deploy web-based AGI intelligences for the Kapwing video editing website and the Instantly email management website based on the techniques of prompt engineering and tool learning.

OpenMV

Intelligent Car ‘GrandPa’

less than 1 minute read

Published:

The project covers environmental monitoring, intelligent tracking based on AprilTag, four-axis motor drive, and wifi image transmission and remote control. The project is based on python embedded implementation of face recognition, target tracking and other functions.

Prompting

Rebuttal of AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

The Law Large Language Model Project

less than 1 minute read

Published:

This project mainly relies on the technical route of prompt learning and partial parameter fine-tuning of open-source large language models to realize a large-model intelligent assistant in the legal vertical field for professionals and the public, targeting legal documents, Q&A and legal data. I am responsible for framework design, deployment fine-tuning, evaluation session and interaction design. Check our project’s code, dataset and checkpoints in github.

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

Stealth Startup AI Algorithm Engineer Internship Experience

less than 1 minute read

Published:

The company is an overseas startup located in Canada, which wants to build Artificial General Intelligence (AGI) applications in several fields based on the hot technology of large language model. During my internship, I collaborated with several colleagues to develop and deploy web-based AGI intelligences for the Kapwing video editing website and the Instantly email management website based on the techniques of prompt engineering and tool learning.

Reading

Recommendation System Algorithm

Social APP ‘MINT’

less than 1 minute read

Published:

Based on uniapp and uniCloud, we implemented MINT, a campus social networking application based on “small tasks” and user personality portraits, using recommendation algorithms, front-end and back-end technologies, javascript programming, etc.

Reinforcement Learning

Graduation Design

less than 1 minute read

Published:

The title of this graduation design is “Research on Hierarchical Reinforcement Learning Algorithm Based on Option”. After thorough research and thesis study, I implemented an algorithm improvement based on the mainstream IOC algorithm, and tested it in multiple environments for specific evaluation metrics, and verified the improvement of reward scores and interpretability metrics.

Reviewer

CHI alt 2024 Conference Reviewer

less than 1 minute read

Published:

CHI conference is called ACM Conference on Human Factors in Computing Systems, which belongs to CCF-A category. CHI has an open review channel for alt.CHI papers, which allows anyone to review papers under real names.

Scholarship

Segmentation

A Gesture-Assisted Real-Time Image Description Smart Hardware

less than 1 minute read

Published:

The project deploys deep learning algorithms such as Image Captioning and gesture recognition in AI hardware training. It helps people to get a summary description of the screen or environment and assists visually impaired people to understand their surroundings.

Socket

A Gesture-Assisted Real-Time Image Description Smart Hardware

less than 1 minute read

Published:

The project deploys deep learning algorithms such as Image Captioning and gesture recognition in AI hardware training. It helps people to get a summary description of the screen or environment and assists visually impaired people to understand their surroundings.

Intelligent Car ‘GrandPa’

less than 1 minute read

Published:

The project covers environmental monitoring, intelligent tracking based on AprilTag, four-axis motor drive, and wifi image transmission and remote control. The project is based on python embedded implementation of face recognition, target tracking and other functions.

Spatial-Temporal Prediction

Specific Task

The Law Large Language Model Project

less than 1 minute read

Published:

This project mainly relies on the technical route of prompt learning and partial parameter fine-tuning of open-source large language models to realize a large-model intelligent assistant in the legal vertical field for professionals and the public, targeting legal documents, Q&A and legal data. I am responsible for framework design, deployment fine-tuning, evaluation session and interaction design. Check our project’s code, dataset and checkpoints in github.

Statistical Machine Learning

Time Series Prediction

Financial Data Prediction Based on Wavelet Analysis and Kalman Filter Algorithms

less than 1 minute read

Published:

The experimental part uses real stock market data, denoising and feature extraction of the data by wavelet analysis, and Kalman filtering for state estimation and prediction. The experimental results show that the method of combining wavelet analysis and Kalman filtering can significantly improve the accuracy of prediction compared to using traditional prediction models alone.

Tool Learning

Stealth Startup AI Algorithm Engineer Internship Experience

less than 1 minute read

Published:

The company is an overseas startup located in Canada, which wants to build Artificial General Intelligence (AGI) applications in several fields based on the hot technology of large language model. During my internship, I collaborated with several colleagues to develop and deploy web-based AGI intelligences for the Kapwing video editing website and the Instantly email management website based on the techniques of prompt engineering and tool learning.

Uniapp

Social APP ‘MINT’

less than 1 minute read

Published:

Based on uniapp and uniCloud, we implemented MINT, a campus social networking application based on “small tasks” and user personality portraits, using recommendation algorithms, front-end and back-end technologies, javascript programming, etc.

Unicloud

Social APP ‘MINT’

less than 1 minute read

Published:

Based on uniapp and uniCloud, we implemented MINT, a campus social networking application based on “small tasks” and user personality portraits, using recommendation algorithms, front-end and back-end technologies, javascript programming, etc.

Vector Database

The Law Large Language Model Project

less than 1 minute read

Published:

This project mainly relies on the technical route of prompt learning and partial parameter fine-tuning of open-source large language models to realize a large-model intelligent assistant in the legal vertical field for professionals and the public, targeting legal documents, Q&A and legal data. I am responsible for framework design, deployment fine-tuning, evaluation session and interaction design. Check our project’s code, dataset and checkpoints in github.

Vue

Social APP ‘MINT’

less than 1 minute read

Published:

Based on uniapp and uniCloud, we implemented MINT, a campus social networking application based on “small tasks” and user personality portraits, using recommendation algorithms, front-end and back-end technologies, javascript programming, etc.

WIFI

Intelligent Car ‘GrandPa’

less than 1 minute read

Published:

The project covers environmental monitoring, intelligent tracking based on AprilTag, four-axis motor drive, and wifi image transmission and remote control. The project is based on python embedded implementation of face recognition, target tracking and other functions.

Wave Transform

Financial Data Prediction Based on Wavelet Analysis and Kalman Filter Algorithms

less than 1 minute read

Published:

The experimental part uses real stock market data, denoising and feature extraction of the data by wavelet analysis, and Kalman filtering for state estimation and prediction. The experimental results show that the method of combining wavelet analysis and Kalman filtering can significantly improve the accuracy of prediction compared to using traditional prediction models alone.

Web Navigation

Rebuttal of AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

Web RAG

github

huggingface AnglE

langchain

Stealth Startup AI Algorithm Engineer Internship Experience

less than 1 minute read

Published:

The company is an overseas startup located in Canada, which wants to build Artificial General Intelligence (AGI) applications in several fields based on the hot technology of large language model. During my internship, I collaborated with several colleagues to develop and deploy web-based AGI intelligences for the Kapwing video editing website and the Instantly email management website based on the techniques of prompt engineering and tool learning.

markdown

microPython

Intelligent Car ‘GrandPa’

less than 1 minute read

Published:

The project covers environmental monitoring, intelligent tracking based on AprilTag, four-axis motor drive, and wifi image transmission and remote control. The project is based on python embedded implementation of face recognition, target tracking and other functions.

personal Website

python

Stealth Startup AI Algorithm Engineer Internship Experience

less than 1 minute read

Published:

The company is an overseas startup located in Canada, which wants to build Artificial General Intelligence (AGI) applications in several fields based on the hot technology of large language model. During my internship, I collaborated with several colleagues to develop and deploy web-based AGI intelligences for the Kapwing video editing website and the Instantly email management website based on the techniques of prompt engineering and tool learning.

‘QA-BOT’ Business Q&A Robot

less than 1 minute read

Published:

QA-BOT is an edge AI deployment that detects human gaze, recognizes speech, and implements various business Q&A dialogues based on few-shot learning implemented by open-source large language models. It is low cost, lightweight and easy to fine-tune compared to the market.

A Gesture-Assisted Real-Time Image Description Smart Hardware

less than 1 minute read

Published:

The project deploys deep learning algorithms such as Image Captioning and gesture recognition in AI hardware training. It helps people to get a summary description of the screen or environment and assists visually impaired people to understand their surroundings.

Intelligent Car ‘GrandPa’

less than 1 minute read

Published:

The project covers environmental monitoring, intelligent tracking based on AprilTag, four-axis motor drive, and wifi image transmission and remote control. The project is based on python embedded implementation of face recognition, target tracking and other functions.

pytorch

Rebuttal of AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

less than 1 minute read

Published:

This paper was submitted to COLING 2024 based on the “Class of Talent” Innovation Fund Program. The paper investigates the performance and evaluation of intelligences based on a generalized LLM in accomplishing the Web Navigation task, and designs the AllTogether method to enhance the language grounding capability of the pretrained language model.

‘QA-BOT’ Business Q&A Robot

less than 1 minute read

Published:

QA-BOT is an edge AI deployment that detects human gaze, recognizes speech, and implements various business Q&A dialogues based on few-shot learning implemented by open-source large language models. It is low cost, lightweight and easy to fine-tune compared to the market.

A Gesture-Assisted Real-Time Image Description Smart Hardware

less than 1 minute read

Published:

The project deploys deep learning algorithms such as Image Captioning and gesture recognition in AI hardware training. It helps people to get a summary description of the screen or environment and assists visually impaired people to understand their surroundings.