Skip to content
View tirthankar95's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report tirthankar95

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. numerical-cognition-rl-nlp numerical-cognition-rl-nlp Public

    We model how children learn numbers using PPO, custom attention-based deep neural networks, and dynamic language instructions. From this model, we try to find patterns and evaluate which pedagogica…

    Python 1

  2. agentic-physics-question-generator agentic-physics-question-generator Public

    Generating Logically Consistent and Novel Physics Word Problems with LLMs

    Jupyter Notebook 1

  3. lyapunov-optimized-neural-networks lyapunov-optimized-neural-networks Public

    This project investigates chaotic dynamics in gradient descent and proposes the use of Lyapunov exponents for hyperparameter selection in neural networks.

    Jupyter Notebook 1

  4. network-chatbot network-chatbot Public

    A wrapper on top of Open WebUI, with built in agents to retrieve exact information from traditional databases.

    JavaScript 1

  5. intelligent-ldpc-decoder intelligent-ldpc-decoder Public

    An LDPC (Low-Density Parity-Check) decoder is an iterative, soft-input soft-output (SISO) error correction component that approaches channel capacity, commonly using Belief Propagation (sum-product…

    Jupyter Notebook 2 1

  6. rlf-small-lm-grid-puzzles rlf-small-lm-grid-puzzles Public

    Forked from verl-project/verl

    Reinforcement Learning Finetuning of Small LMs for Grid Puzzles

    Python 2