Awesome Spiking Neural Networks

A curated reading list (a so-called "Awesome" list) collecting research papers and code about spiking neural networks (SNNs). SNNs are a type of artificial neural network loosely inspired by how biological neurons communicate — they transmit information using discrete "spikes" rather than continuous numbers. The list is actively updated by its maintainers.

What's inside

• Papers organized by year — entries are grouped under 2023, 2024, 2025, and 2026, so you can see recent work at a glance.
• Venue tags — each paper is labeled with where it was published (e.g., ICML, ICLR, AAAI, NeurIPS, CVPR, Nature, Science). This lets you filter by conference/journal prestige.
• Links — nearly every entry includes a link to the paper's page (and sometimes a link to its code repository) so you can read the full text or try the implementation.
• A news section — the top of the README tracks when batches of papers were added (e.g., "Update SNN-related papers in AAAI 2026 (33 papers)"). You can expand and collapse these updates to see the update history.

How it's built

It's a community-driven project. The README invites anyone who finds an overlooked SNN paper to add it by submitting a pull request (a standard GitHub contribution workflow). The maintainers then review and merge additions, which is why the list grows over time.

Who it's for

Researchers, students, or engineers working in or exploring the field of spiking neural networks — anyone who wants a single, organized place to find recent papers and their code without hunting across multiple conference sites. Because every entry has a clickable link, it's also a practical starting point for understanding what SNN research looks like today.

In short: a continuously updated, community-contributed directory of SNN papers and code, sorted by year and publication venue, with direct links to the original sources.