Deep Learning Researcher & Engineer
Exploring the frontiers of Large Language Models, Natural Language Processing, and Reinforcement Learning.
I am a researcher with a deep interest in building intelligent systems that understand, reason, and interact with the world through language. My work spans across foundational and applied aspects of LLMs, NLP, and deep RL, focusing on alignment, generalization, and real-world deployment.
- ๐ง Focus: LLMs, Transformers, RLHF, Model Evaluation, Prompt Engineering
- ๐งช Research interests: interpretability, alignment, multi-agent systems, societal simulations
- ๐ ๏ธ Tools: PyTorch, Hugging Face, RLlib, LangChain, Weights & Biases
- ๐ฏ Goal: Contribute to responsible AI research and advance understanding of intelligent behavior
A conceptual and experimental framework modeling societal systems as neural networks, aiming to balance fairness, efficiency, and meritocracy using deep learning and RL.
Keywords: Social Simulation, Policy Optimization, Ethics in AI
๐ Paper Draft (available on request)
๐ GitHub: navid72m/society-as-a-network
Research initiative exploring model quantization, compression, and distillation to deploy LLMs on edge hardware like Jetson Orin Nano.
Focus: Efficient inference, low-latency deployment, hardware-aware design.
๐ GitHub: navid72m/llm-embedded
End-to-end framework for visualizing, analyzing, and forecasting time series data using statistical and deep learning approaches.
Tools: Prophet, ARIMA, LSTM
๐ GitHub: navid72m/time-series-lab
Exploring how human feedback can guide the behavior of language models through reinforcement learning.
Includes policy optimization experiments and reward model training.
๐ GitHub: navid72m/rlhf-lab
- ๐ Language models in multi-agent environments for emergent behavior analysis
- ๐ฒ Game-theoretic approaches to fairness and alignment in RL settings
- ๐งฉ Investigating hallucinations in LLMs and developing robust evaluation metrics
- ๐ง Preparing for a potential PhD on the intersection of AI, philosophy, and decision theory
Currently reading:
- "Hands-On Large Language Models"
- Papers on mechanistic interpretability
- Stanford / DeepMind publications on RLHF and AI alignment
