Matthew Chen

X-Star: Endogenous Continuous Plasticity and Commutative Latent Deliberation for Compact Neural Architectures

Small language models (<= 3B parameters) are severely constrained by parameter capacity, autoregressive order bias, and catastrophic forgetting during continuous adaptation. While existing System-2 approaches rely on expensive external scaffolding (e.g., tree-search verifiers and multi-agent coordination), they introdu...