Nested Learning and Hope: memory components that update at different rates

What changed

Some information should change quickly, while other knowledge should persist. Nested Learning organizes a model and its learning procedures as interacting optimization processes with different contexts and update rates. Its Continuum Memory System uses several memory components on different schedules. Hope combines that system with a self-referential extension of Titans, allowing parts of its memory processing to adapt while data arrive. The contribution here is the specified multi-timescale memory and Hope design with its reported computational demonstrations, beyond the earlier Titans and MIRAS families.

Scientific scope

Some information should change quickly, while other knowledge should persist. Nested Learning organizes a model and its learning procedures as interacting optimization processes with different contexts and update rates. Its Continuum Memory System uses several memory components on different schedules. Hope combines that system with a self-referential extension of Titans, allowing parts of its memory processing to adapt while data arrive. The contribution here is the specified multi-timescale memory and Hope design with its reported computational demonstrations, beyond the earlier Titans and MIRAS families. The authors explicitly do not claim that catastrophic forgetting is solved in general. Continual-learning experiments include substantial additional training; long-context results can require benchmark-specific fine-tuning. Transformers remain stronger on some short-recall tasks, and the multiscale optimizer has additional overhead. More memory levels do not establish unbounded knowledge retention. Biological analogies and clinical benchmarks are not separate discoveries in this record. The exact hosted source revision is retained; its 2025 conference family does not make every later revision identical.

Evidence

The linked original works support the scoped statement and contribution attribution. WRS has not independently replayed experiments or reconstructed a full mathematical proof. The authors explicitly do not claim that catastrophic forgetting is solved in general. Continual-learning experiments include substantial additional training; long-context results can require benchmark-specific fine-tuning. Transformers remain stronger on some short-recall tasks, and the multiscale optimizer has additional overhead. More memory levels do not establish unbounded knowledge retention. Biological analogies and clinical benchmarks are not separate discoveries in this record. The exact hosted source revision is retained; its 2025 conference family does not make every later revision identical.

Contributors

• The named authors in the research record · SCIENCE: Source-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred.

• Nested Learning: The Illusion of Deep Learning Architecture

Provisional WRS assessment, edition 2026-10-23.9. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction