10 13 3

rrr

mediiiiii3

AI & ML interests

None yet

Recent Activity

upvoted an article 18 days ago

From OpenAI to Open LLMs with Messages API

upvoted an article 18 days ago

**The Ultimate Guide to AI-Powered Browser Automation and Web Scraping**

commented on an article 18 days ago

Unlock the Power of AI in Your Browser with Transformers.js

View all activity

Organizations

mediiiiii3's activity

upvoted 2 articles 18 days ago

Article

From OpenAI to Open LLMs with Messages API

Feb 8, 2024

• 15

Article

The Ultimate Guide to AI-Powered Browser Automation and Web Scraping

•

Nov 19, 2024

• 2

commented on Unlock the Power of AI in Your Browser with Transformers.js 18 days ago

Really cool blog!

upvoted a paper 18 days ago

ACECODER: Acing Coder RL via Automated Test-Case Synthesis

Paper • 2502.01718 • Published 21 days ago • 28

liked a Space 18 days ago

Example: Javascript

📉

Display "Hello World" message

liked a Space 19 days ago

Doodle Dash

🖍

Draw and get a caption for your doodle

upvoted an article 19 days ago

Article

Unlock the Power of AI in Your Browser with Transformers.js

•

Nov 19, 2024

• 3

upvoted a paper 20 days ago

BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing

Paper • 2206.15076 • Published Jun 30, 2022 • 4

reacted to singhsidhukuldeep's post with 🤗👍 23 days ago

Post

2200

Excited to share groundbreaking research from @Baidu_Inc on enterprise information search! The team has developed EICopilot, a revolutionary agent-based solution that transforms how we explore enterprise data in large-scale knowledge graphs.

>> Technical Innovation
EICopilot leverages Large Language Models to interpret natural language queries and automatically generates Gremlin scripts for enterprise data exploration. The system processes hundreds of millions of nodes and billions of edges in real-time, handling complex enterprise relationships with remarkable precision.

Key Technical Components:
- Advanced data pre-processing pipeline that builds vector databases of representative queries
- Novel query masking strategy that significantly improves intent recognition
- Comprehensive reasoning pipeline combining Chain-of-Thought with In-context learning
- Named Entity Recognition and Natural Language Processing Customization for precise entity matching
- Schema Linking Module for efficient graph database query generation

>> Performance Metrics
The results are impressive - EICopilot achieves a syntax error rate as low as 10% and execution correctness up to 82.14%. The system handles 5000+ daily active users, demonstrating its robustness in real-world applications.

>> Implementation Details
The system uses Apache TinkerPop for graph database construction and employs sophisticated disambiguation processes, including anaphora resolution and entity retrieval. The architecture includes both offline and online phases, with continuous learning from user interactions to improve query accuracy.

Kudos to the research team from Baidu Inc., South China University of Technology, and other collaborating institutions for this significant advancement in enterprise information retrieval technology.