OPEN LEARNING / SHARED KNOWLEDGE

Knowledge belongs within reach.

From your first paper to your first reproducible experiment. Open resources and practical reading paths for independent exploration.

Not a course catalog. A path into discovery.

Explore freely readable documentation, original papers and open textbooks. These editorial reading paths are not degree programs and carry no credit or certification. Data and software remain subject to their own access terms and licenses.

LEARNING PATH / 01

Spatial intelligence & simulation

How can machines understand a world in three dimensions?

Read NeRF to understand volume rendering and scene representation.
Compare implicit and explicit representations with the 3DGS project.
Document data, view splits and rendering evaluation settings.

3D Gaussian Splatting · SIGGRAPH 2023↗NeRF · ECCV 2020↗

LEARNING PATH / 02

Biomedical imaging

See more detail with fewer measurements.

Understand k-space, sampling and MRI reconstruction.
Read fastMRI documentation and data-use terms.
Compare reconstruction baselines, errors and generalization limits.

fastMRI · NYU Langone Health↗fastMRI · Open-source code↗

LEARNING PATH / 03

Computer & software science

Reliable software begins with verifiable reasoning.

Start with types and propositions in the Lean documentation.
Work through basic proofs in Mathematics in Lean.
Pin toolchain versions and keep executable proof files.

Lean · Language & theorem prover↗Mathematics in Lean · Open textbook↗

LEARNING PATH / 04

Game science & reinforcement learning

Learn through interaction. Decide under uncertainty.

Understand Markov decision processes, value functions and policies.
Learn the environment API through Gymnasium documentation.
Record results across seeds, not just the best episode.

Gymnasium · Farama Foundation↗Spinning Up · OpenAI↗

Turn reading into understanding.

Start with the question

Identify the task, assumptions and scope. A sentence in the abstract cannot replace a precise problem definition.

Follow the evidence

Check data splits, baselines and metrics. Notice what the authors measured, and what they did not.

Make it reproducible

Start with a minimal example. Record versions, parameters and seeds. Separate implementation errors from method limitations.