ChunTe  Lee's picture

ChunTe Lee

Chunte

AI & ML interests

None yet

Recent Activity

Organizations

Hugging Face's profile picture Social Post Explorers's profile picture Dev Mode Explorers's profile picture

Chunte's activity

upvoted an article 1 day ago
view article
Article

LeRobot goes to driving school: Worldโ€™s largest open-source self-driving dataset

โ€ข 48
New activity in julien-c/documentation-images 12 days ago
upvoted an article 26 days ago
view article
Article

Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita ๐Ÿ”ฅ

โ€ข 93
reacted to merve's post with ๐Ÿš€ about 1 month ago
reacted to albertvillanova's post with ๐Ÿ”ฅ๐Ÿค— about 1 month ago
view post
Post
3792
๐Ÿš€ Introducing @huggingface Open Deep-Research๐Ÿ’ฅ

In just 24 hours, we built an open-source agent that:
โœ… Autonomously browse the web
โœ… Search, scroll & extract info
โœ… Download & manipulate files
โœ… Run calculations on data

55% on GAIA validation set! Help us improve it!๐Ÿ’ก
https://huggingface.co/blog/open-deep-research
  • 3 replies
ยท
reacted to victor's post with ๐Ÿค—๐Ÿ”ฅโค๏ธ about 1 month ago
view post
Post
4240
Hey everyone, we've given https://hf.co/spaces page a fresh update!

Smart Search: Now just type what you want to doโ€”like "make a viral meme" or "generate music"โ€”and our search gets it.

New Categories: Check out the cool new filter bar with icons to help you pick a category fast.

Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.

Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.

Weโ€™d love to hear what you thinkโ€”drop us some feedback plz!
ยท
upvoted 2 articles about 1 month ago
view article
Article

The AI tools for Art Newsletter - Issue 1

โ€ข 70
view article
Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

By not-lain โ€ข
โ€ข 36
reacted to singhsidhukuldeep's post with โž• about 2 months ago
view post
Post
2998
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
  • 1 reply
ยท