2 papers
cs.CL2026
Sparse Text Diffusion under Dual Budgets: Context Connectivity and Expert Activation
Alexandros Christoforos, Chadbourne Davis, Paul Raj
Long-context diffusion repeatedly pays for both token interaction and feed-forward computation. We formulate these costs as two separate budgets: the edges available to an attentio…
cs.LG2026
DuplexTune: Coupled-State Replay for Memory-Efficient Mixture-of-Experts Adaptation
Paul Raj, Simon Caldwell, Daniel Whitmore +1
Sparse expert execution does not remove the stored states needed to adapt a mixture-of-experts language model. We present DuplexTune, a framework for replaying coupled hidden state…