Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
DreamingGoose: Staged Distillation from Autoregressive Transformers to Bidirectional Recurrent Diffusion Language Models
Julian Boesch, Andrew Wee, Alexander Stranzl
Pretrained autoregressive Transformers represent a large sunk investment in compute. Existing conversion methods reuse that investment by changing either the architecture (attentio…
cs.LG2026
Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It
Julian Boesch, Andrew Wee
Fixed-state recurrences--linear attention and state-space models--are reported to lag behind attention on associative recall, but whole-architecture comparisons cannot say which in…