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. 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

4. 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

5. RL-for-LLM-training-Variance-Stabilized-Dropout-Implementation RL-for-LLM-training-Variance-Stabilized-Dropout-Implementation Public

   RL Stabilized Dropout

   Python 1

6. Reinforcement-learning_ML_Profiler Reinforcement-learning_ML_Profiler Public

   This repo implements a realistic ML engineering task. Think of it like a mini-version of what you'd build at an ML company to profile model behavior during fine-tuning experiments.

   Python 1