Source codes of all my works will be shared on GitHub, the trained models and datasets will be released on 🤗 Hugging Face, and some of my applied research on Vision and Language will be developed as Web or Android/iOS mobile apps.

Boston University:

Topic 1: Large Language Models (LLMs):

• 🔥 𝐁𝐞𝐧𝐜𝐡𝐦𝐚𝐫𝐤 𝐃𝐚𝐭𝐚𝐬𝐞𝐭 - GSM8K-Consistency Benchmark (available on 🤗 Hugging Face)

• 🔨 𝐓𝐨𝐨𝐥𝐤𝐢𝐭 - PromptCraft: A Prompt Perturbation Toolkit and the released PyPI Package

• 📚 𝐏𝐚𝐩𝐞𝐫 𝐒𝐮𝐫𝐯𝐞𝐲 - Awesome LLM Self-Consistency

• 📚 𝐏𝐚𝐩𝐞𝐫 𝐒𝐮𝐫𝐯𝐞𝐲 - Awesome Semantic Textual Similarity (STS)

  LLMs Research Topic	Description
  𝗟𝗟𝗠𝘀 𝗘𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 𝗯𝘆 𝗔𝗱𝘃𝗲𝗿𝘀𝗮𝗿𝗶𝗮𝗹 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴	CoEvolve LLMs: Co-Evolution of LLMs via Adversarial Learning
  𝗕𝗶𝗱𝗶𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝗮𝗹 𝗖𝗼𝗧	Bidirectional Chain-of-Thought (Bi-CoT) Prompting
  𝗣𝗿𝗼𝗺𝗽𝘁 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗮𝗻𝗱 𝗦𝗲𝗹𝗳-𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆	Prompt Consistency (PC)
  𝗙𝗶𝗻𝗲-𝗧𝘂𝗻𝗶𝗻𝗴 𝗟𝗟𝗠𝘀	Fine-Tune LLaMA2 (7B) with LoRA Adapter on MetaMath and The Trained LoRA models for inference on 🤗 Hugging Face

Topic 2: Multimodal Foundation Models: We will be deploying all our Multimodal Machine Learning Models on the following platform.

• 🚀 𝐍𝐞𝐮𝐫𝐨𝐆𝐏𝐓 𝐎𝐧𝐥𝐢𝐧𝐞 𝐏𝐥𝐚𝐭𝐟𝐨𝐫𝐦 - NeuroGPT (Currently Boston University Access Only)

Topic 3: Medical Imaging with AI:

• 🖼️ 𝐎𝐧𝐥𝐢𝐧𝐞 𝐌𝐞𝐝𝐢𝐜𝐚𝐥 𝐈𝐦𝐚𝐠𝐢𝐧𝐠 𝐕𝐢𝐬𝐮𝐚𝐥𝐢𝐳𝐞𝐫 - Online Medical Imaging Visualizer (based on Papaya)

City University of Hong Kong:

• 𝐍𝐨𝐧-𝐥𝐨𝐜𝐚𝐥 𝐌𝐨𝐝𝐞𝐥𝐢𝐧𝐠 - Non-local Modeling for Image Quality Assessment
• 𝐍𝐨𝐧-𝐥𝐨𝐜𝐚𝐥 𝐌𝐨𝐝𝐞𝐥𝐢𝐧𝐠 - Context-aware Non-local Compensation for Image Quality Assessment

Northeast Electric Power University:

• 🔥 𝐋𝐢𝐛𝐫𝐚𝐫𝐲 - EEG Deep Learning Library
• 𝐒𝐜𝐨𝐮𝐭 𝐄𝐒𝐈 𝐚𝐧𝐝 𝐂𝐍𝐍 - EEG Motor Imagery Signals Classification via CNN
• 𝐒𝐨𝐧𝐚𝐫 𝐈𝐦𝐚𝐠𝐞 𝐒𝐞𝐠𝐦𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 - Sonar Image Segmentation via Entropy Method

Philips Research:

• Medical Named Entity Recognition
• Medical Concept Mapping
• Deploy PyTorch NER Model with Flask and Docker as Web App
• Dynamic Webs Crawlering in Python

Others:

• Download Papers through Terminal based on Sci-Hub
• Awesome Poster Presentation
• CVPR LaTeX Template
• Download Google Scholar Citation Papers
• Python Programming Standards (Tencent, in Chinese)