Pinned Loading

1. CONSTRAINT-DECOMPOSITION-for-Multi-Objective-RLHF CONSTRAINT-DECOMPOSITION-for-Multi-Objective-RLHF Public

   Early-stage research exploring decomposed reward modeling for complex instruction-following in large language models.

   Python 1

2. ai-physicist-central-llm ai-physicist-central-llm Public

   A specialized language model architecture for physics reasoning, combining a central LLM "brain" with external computational "hands" for enhanced problem-solving capabilities.

   Python 1

3. Natural-Scaling-Predictor Natural-Scaling-Predictor Public

   Novel methodology: First comprehensive LLM performance prediction framework Empirical insights: Analysis of 127 LLMs across 15 model families Theoretical advances: Extended scaling laws with emerge…

   Python 1

4. RAG-Demo RAG-Demo Public

   A minimal, end-to-end example of a Retrieval-Augmented Generation (RAG) pipeline using Python, LangChain, OpenAI, and pgvector. It shows how to ingest unstructured documents, index them for semanti…

   Jupyter Notebook 1

5. LLM-eval-benchmark-lab LLM-eval-benchmark-lab Public

   A modular, configurable benchmarking harness for evaluating LLM behavior across tasks, constraints, and model classes.

   Python 1

6. LLM-Drift-Observatory LLM-Drift-Observatory Public

   A hands-on framework for detecting and visualizing **behavioral drift** in Large Language Models (LLMs) across versions and providers.

   Jupyter Notebook 1