Simple Papers

A better way to read scientific papers.

Simple Papers transforms complex academic papers into digestible, simplified content with AI-powered explanations, interactive annotations, and audio narration.

Check out the app here!

Or watch this video demo here.

📚 Available Papers

• Attention Is All You Need
• ReAct: Synergizing Reasoning and Acting in Language Models
• XGBoost: A Scalable Tree Boosting System
• Latent Dirichlet Allocation
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• High-Resolution Image Synthesis with Latent Diffusion Models
• A Unified Approach to Interpreting Model Predictions
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• A Practical Guide for Evaluating LLMs and LLM-Reliant Systems
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

🛠️ Technologies Used

• AWS Bedrock - AI foundation models
• LangChain - Framework for building AI applications
• agentic-doc - Document parsing and extraction
• ElevenLabs - AI voice synthesis for audio narration
• Streamlit - Web application framework

⚙️ How It Works

Simple Papers can be used in two ways:

🌐 Online Mode (Streamlit Community Cloud)

• Access pre-parsed and simplified academic papers
• No setup required - just click and read
• Perfect for exploring research without the complexity

💻 Local/Dev Mode

• Parse and simplify your own PDF papers
• Full control over processing and customization
• Ideal for researchers working with specific documents
• Note: Currently a proof-of-concept that requires multiple API keys for the end-to-end workflow. This complexity will be streamlined if the app gains sufficient user engagement and traction.

🚀 Installation

git clone https://github.com/syasini/simple_papers.git
cd simple_papers
pip install -e .

🏃 Usage

Run the Streamlit app:

streamlit run app.py

Then open your browser to http://localhost:8501 and start simplifying papers!

📋 Requirements

• Python 3.12+
• Streamlit
• API keys for local processing (see secrets.toml.example for setup details)
• AWS credentials (for advanced features)

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License.