Hello! I'm Naveen Mysore, a Research and Software Engineer with 8+ years of experience across machine learning, reinforcement learning, distributed systems, and causal inference.
At UC Santa Barbara, I trained reasoning LLMs using reinforcement learning and worked on causal structure discovery, interpretable AI, and time-series forecasting. Previously at Salesforce, Tableau and Dell EMC, I shipped large-scale enterprise systems: backend services, cloud infrastructure, data pipelines, and distributed systems serving millions of users.
I believe the hardest problems in AI for Science and AI for Health demand models that are trustworthy, not just powerful. The AI Alignment problem drew me to causal reinforcement learning — building agents that reason about cause and effect so we can deploy AI safely in healthcare, climate, and scientific discovery.
I bring the full stack to my research — from CUDA kernels and distributed training to production APIs. M.S. in Computer Science from UNC Charlotte, B.E. in Electrical Engineering from PES University.
Open to collaborations in interpretable AI, causal reasoning, RL, or AI for scientific discovery — reach out at nmysore.work [at] gmail.com.
Year 2026
Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement Learning
Introduces prediction-based Markov Violation Scores (MVS) to detect when observations in RL violate the Markov property. The method leverages prediction errors from learned dynamics models to quantify non-Markovian behavior, enabling more robust policy learning under partial observability.
🎉 Accepted at RLC 2026 and published in Reinforcement Learning Journal.
Paper
Temporal Functional Circuits: From Spline Plots to Faithful Explanations in KAN Forecasting
Proposes Temporal Functional Circuits (TFCs), a framework for extracting faithful, interpretable explanations from Kolmogorov-Arnold Networks (KANs) applied to time-series forecasting. By analyzing learned spline activations, TFCs reveal how individual input features are transformed and combined, offering transparent insight into KAN predictions.
Status: Under review for NeurIPS 2026
arXiv Paper
Reasoning LLM Model trained using RL
Scan the QR code above to try our live nutrition estimation service! Text a meal description like "I had a bagel for breakfast" and get instant nutrition analysis. This LLM was trained on the NutriBench dataset and fine-tuned using Reinforcement Learning on the Llama3.1B model. The inference model is hosted on AWS for real-time responses.
GitHub Repository
Fog on a Mountain Run Run Run: A Story of AI
A thriller set in the San Francisco Bay Area about interpretable AI, invisible failures, and the cost of building machines we cannot understand. Inspired by real events and grounded in real science, this is not a story against AI — it's a story for building AI we can trust.
Available on AmazonProjects
Sept 2021
N arm bandits is a classical problem in computer science. In this Jupyter note book we will empirically verify that near greedy approch converges to optimal values faster than non greedy or greedy approches and maximizes the expected rewards. Jupyter Notebook
Jun 2021
Causal Structure Discovery is the problem of identifying causal relationships from large quantities of data through computational methods. Solution to this problem can have wide of applications in non empirical scientific studies like climate, biodiversity and health. The current problem is existing methods are computationally not scalable and are data intensive. Jupyter Notebook
Apr 2017
Reinforcement Learning (Q Learning based) agent trained to play Flappy Bird. demo
May 2018
Object detection on raspberry pi. demo
Mar 2021
Robot trained to sort metal and plastic. demo
2020
Generative adverserial network with variational auto encoder. details
Jul 2020
Gaussian noise based latent vector to image. details
