Find your next starting point.

Parameterization and execution of notebooks for repeatable computational workflows.

Parameter-efficient model adaptation methods for testing trainable-parameter budgets and adapter composition.

Reading, modifying, and writing DICOM medical-imaging metadata and datasets in Python.

Tensor expression graphs, automatic differentiation, and compilation for numerical computation.

Tensor computation and automatic differentiation framework for constructing controlled learning and gradient experiments.

Training-loop framework for studying checkpoint restoration, reproducibility and separation of model logic from orchestration.

Distributed execution and machine-learning infrastructure for studying task scheduling, tuning and fault handling.

Experiment organization and observation tooling for capturing configurations, dependencies and run outcomes.

Sparse-autoencoder research tooling for examining reconstruction, sparsity and feature interventions on neural activations.

Tensor serialization tooling for studying shape, dtype and byte-level preservation without a pickle-style object format.

Model-serving and structured-generation tooling for evaluating runtime behavior on controlled language-model workloads.

Provide Dijkstra and Bellman–Ford implementations with hand-enumerated reference graphs, explicit negative-edge rejection, and a negative-cycle control.