ChunTe Lee
Chunte
AI & ML interests
None yet
Recent Activity
reacted
to
singhsidhukuldeep's
post
with 😔
about 14 hours ago
Exciting breakthrough in Retrieval-Augmented Generation (RAG): Introducing MiniRAG - a revolutionary approach that makes RAG systems accessible for edge devices and resource-constrained environments.
Key innovations that set MiniRAG apart:
Semantic-aware Heterogeneous Graph Indexing
- Combines text chunks and named entities in a unified structure
- Reduces reliance on complex semantic understanding
- Creates rich semantic networks for precise information retrieval
Lightweight Topology-Enhanced Retrieval
- Leverages graph structures for efficient knowledge discovery
- Uses pattern matching and localized text processing
- Implements query-guided reasoning path discovery
Impressive Performance Metrics
- Achieves comparable results to LLM-based methods while using Small Language Models (SLMs)
- Requires only 25% of storage space compared to existing solutions
- Maintains robust performance with accuracy reduction ranging from just 0.8% to 20%
The researchers from Hong Kong University have also contributed a comprehensive benchmark dataset specifically designed for evaluating lightweight RAG systems under realistic on-device scenarios.
This breakthrough opens new possibilities for:
- Edge device AI applications
- Privacy-sensitive implementations
- Real-time processing systems
- Resource-constrained environments
The full implementation and datasets are available on GitHub: HKUDS/MiniRAG
reacted
to
singhsidhukuldeep's
post
with 🤝
about 14 hours ago
Exciting breakthrough in Retrieval-Augmented Generation (RAG): Introducing MiniRAG - a revolutionary approach that makes RAG systems accessible for edge devices and resource-constrained environments.
Key innovations that set MiniRAG apart:
Semantic-aware Heterogeneous Graph Indexing
- Combines text chunks and named entities in a unified structure
- Reduces reliance on complex semantic understanding
- Creates rich semantic networks for precise information retrieval
Lightweight Topology-Enhanced Retrieval
- Leverages graph structures for efficient knowledge discovery
- Uses pattern matching and localized text processing
- Implements query-guided reasoning path discovery
Impressive Performance Metrics
- Achieves comparable results to LLM-based methods while using Small Language Models (SLMs)
- Requires only 25% of storage space compared to existing solutions
- Maintains robust performance with accuracy reduction ranging from just 0.8% to 20%
The researchers from Hong Kong University have also contributed a comprehensive benchmark dataset specifically designed for evaluating lightweight RAG systems under realistic on-device scenarios.
This breakthrough opens new possibilities for:
- Edge device AI applications
- Privacy-sensitive implementations
- Real-time processing systems
- Resource-constrained environments
The full implementation and datasets are available on GitHub: HKUDS/MiniRAG
reacted
to
singhsidhukuldeep's
post
with 👍
about 14 hours ago
Exciting breakthrough in Retrieval-Augmented Generation (RAG): Introducing MiniRAG - a revolutionary approach that makes RAG systems accessible for edge devices and resource-constrained environments.
Key innovations that set MiniRAG apart:
Semantic-aware Heterogeneous Graph Indexing
- Combines text chunks and named entities in a unified structure
- Reduces reliance on complex semantic understanding
- Creates rich semantic networks for precise information retrieval
Lightweight Topology-Enhanced Retrieval
- Leverages graph structures for efficient knowledge discovery
- Uses pattern matching and localized text processing
- Implements query-guided reasoning path discovery
Impressive Performance Metrics
- Achieves comparable results to LLM-based methods while using Small Language Models (SLMs)
- Requires only 25% of storage space compared to existing solutions
- Maintains robust performance with accuracy reduction ranging from just 0.8% to 20%
The researchers from Hong Kong University have also contributed a comprehensive benchmark dataset specifically designed for evaluating lightweight RAG systems under realistic on-device scenarios.
This breakthrough opens new possibilities for:
- Edge device AI applications
- Privacy-sensitive implementations
- Real-time processing systems
- Resource-constrained environments
The full implementation and datasets are available on GitHub: HKUDS/MiniRAG
Organizations
Chunte's activity
Fix metadata tag
1
#2 opened 4 months ago
by
lucataco
Add generated example
2
#1 opened 4 months ago
by
nbroad
What do you recommend for a small monochrome icon?
5
#2 opened 9 months ago
by
severo
Social thumbnail suggestion
1
#2 opened 6 months ago
by
Chunte
Social thumbnail proposal
1
#2 opened 6 months ago
by
Chunte
Add a banner
#9 opened 8 months ago
by
Chunte
Upload index.html
#1 opened 12 months ago
by
Chunte
Delete dataset-on-hf-sm-1.svg
1
#28 opened about 1 year ago
by
Chunte
model-on-hf badge fix
#30 opened about 1 year ago
by
Chunte
model-on-hf-sm badge
#29 opened about 1 year ago
by
Chunte
Model/Dataset on HF README update
#27 opened about 1 year ago
by
Chunte
Upload 16 files
#26 opened about 1 year ago
by
Chunte
Add a custom social thumbnail
6
#8 opened about 1 year ago
by
julien-c
README Follow-me-on-HF update
#24 opened about 1 year ago
by
Chunte
Follow me on HF badges upload
#23 opened about 1 year ago
by
Chunte
new subscribe to pro update
#21 opened over 1 year ago
by
Chunte
new subscribe to pro badges
#20 opened over 1 year ago
by
Chunte
a fresh logo for your orgnization profile :)
7
#4 opened over 1 year ago
by
Chunte
Upload 4 files
#18 opened over 1 year ago
by
Chunte
paper page readme update
#17 opened over 1 year ago
by
Chunte