AI & ML interests
Enterprise-grade AI models
Recent Activity
Papers
ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Articles
Granite 4.0 Nano WebGPU
In-browser tool calling with IBM Granite-4.0
Granite-4.0 WebGPU
Run Granite-4.0-Micro 100% locally in your browser on WebGPU
Granite Guardian 3.3 8B
Detect harms and risks with Granite Guardian 3.3 8B
Granite 3.1 8b Instruct
Chat with IBM Granite 3.1 8b Instruct
granite-docling-258M demo
Convert images of documents to structured data and answer queries
Multimodal RAG with Granite Vision
RAG example using Granite [vision, embedding, instruct]
Granite Embedding R2 Models Demo
Rank passages by relevance to a query using embeddings
Granite 4.0 1B Speech
Granite 4.0 1B Speech recognition and translation demo
Granite Speech WebGPU
Transcribe and translate audio to text directly in your browser
Granite Vision Document Intelligence
Document intelligence with Granite-Vision-4.1-4B
README
Granite Docling 258M WebGPU
Convert document images to editable HTML