AI-SOVEREIGN
Home / AI Research / Late Entry in Looped Language Models
LAAI Research

Late Entry in Looped Language Models

by NanyangTechnologicalUniversity · Ziqi Jin, Jiaxi Li, Weiwen Xu, Aixin Sun

Looped language models deepen reasoning at a compact parameter count by iterating a shared layer stack T times per token, turning recurrence depth directly into sequential decoding latency. Conventional early-exit decoding halts after initial passes without cache completion, truncating cached key-value states of past tokens to shallow depth. We study the opposite strategy, late entry, where new tokens skip initial passes and enter directly into the final K < T passes over a deep context cache. Once lightweight fine-tuning resolves hidden-state norm mismatch at the entry boundary, deep cached context substitutes for skipped token-local passes, allowing late entry to outperform matched early…

Upvotes10
Comments2
Published17 Nov 2026

More from NanyangTechnologicalUniversity