AlignAtt4LLM adapts AlignAtt to decoder-only LLMs via prompt layout, head selection, and attention replay, outperforming IWSLT 2026 baselines for En-De and En-It at ~2s and <4s latency.
Maja Popovi´c
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A 1B-parameter multilingual offline model is adapted with AlignAtt policy for simultaneous speech translation and submitted to IWSLT 2026 for three language pairs.
citing papers explorer
-
AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task
AlignAtt4LLM adapts AlignAtt to decoder-only LLMs via prompt layout, head selection, and attention replay, outperforming IWSLT 2026 baselines for En-De and En-It at ~2s and <4s latency.
-
A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026
A 1B-parameter multilingual offline model is adapted with AlignAtt policy for simultaneous speech translation and submitted to IWSLT 2026 for three language pairs.