Xinyu Yang

Four Methodological Foundations for Open Systems: A Manifesto on Memory Organization, Non-Global Gluing, Information Budgeting, and Distributed Kinetics

Contemporary scientific foundations across artificial intelligence, mathematical logic, cybernetics, and distributed computing face a common impasse rooted in an unexamined ontology: the postulate of the monolithic global context. This dogma presumes that open systems can be unde...

One Tick, One Link: A Non-Autoregressive Challenge–Response Memory in Which Depth Is Bought with the World's Silence

We report a sequence learner that is not autoregressive. It is challenge–response: one input per tick, one output per tick, and intervals in which the input is the identity and the model keeps emitting. Its two operations are inverses selected by the world — speech binds an obser...

Trading Interference for Retrieval Difficulty: A Content-Addressed Continual Memory with On-Demand Capacity

A learner with bounded parameters and an unbounded stream must give something up: regularisation gives up plasticity, training on regardless gives up the past. A third option is to allocate, giving distinct regimes distinct storage, and the standing objection is that adding param...