Trainable Quantum-Native Language Models: Dissipative Memory, Capacity Limits, and Hardware Validation

Key points

• In the fixed-width recurrent setting, unitary dynamics cannot contract or reset stored distinctions; experimentally, unitary recurrence loses to its retrained one-token control in every tested variant.1
• Introducing learned dissipation, then token-conditioned dissipative gating, yields useful memory beyond one token.1
• A key-value recall benchmark shows a width-dependent threshold: one stored pair meets the pre-registered accuracy bar at 4-5 memory qubits, two pairs at 6-7, and three pairs remain unsolved.1
• As a secondary result, one-qubit models reach lower stationary memory entropy than a heuristically optimized classical predictive frontier at matched error in 9/9 seeds.1

Sources (1)

• [1]Trainable Quantum-Native Language Models: Dissipative Memory, Capacity Limits, and Hardware Validation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 11:29 PM

  We study byte-level autoregressive language models whose hidden state is a small quantum register, whose transitions are learned token-conditioned quantum channels, and whose next-byte probabilities come directly from Born-rule measurements without a learned classical vocabulary projection or softmax.

  In the fixed-width recurrent setting, unitary dynamics cannot contract or reset stored distinctions; experimentally, unitary recurrence loses to its retrained one-token control in every tested variant.

Extractive summary: sentences quoted from the sources.