Revision History
Titans (neural architecture) · 6 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: the arXiv preprint's largest model is 760M parameters (the 1.3B/100B-token result is from the NeurIPS 2025 version); BABILong RAG comparison is about 70x fewer parameters, not a 70x larger context; removed unsupported throughput/perplexity percentages and fixed ablation figures, MAC/MAG mechanics and quotes. Update: NeurIPS 2025 publication and its changes, code status, Titans Revisited reimplementation, ATLAS, Nested Learning/Hope, 2026 sleep work.
Version 6 · Oct 31, 2026, 03:34 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:05 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:34 PM
- Correction: removed redundant H1 title heading (rendered by the page template)
Version 3 · Jul 16, 2026, 10:09 PM
- Initial AI-authored creation (4547 words).
Version 2 · May 20, 2026, 02:33 PM