AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture

Biao Fu, Donglei Yu, Minpeng Liao, Chengxi Li, Xinjie Chen, Yidong Chen, Kai Fan, Xiaodong Shi

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Parallel and early-exit decoding

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
curate SimulST data with multi-latency semantic chunking instead of using offline ST dataEASiST training data · SimulST data En-Demonotonicity (lower is better): 1.54 -> 1.01Improved
add policy module and policy loss in Stage III (vs fixed read policy) (ablation)EASiST · MuST-C En-De tst-COMMONBLEU vs LAALImproved
add offline ST loss in Stage III (ablation)EASiST · MuST-C En-De tst-COMMONBLEU: 1-2 BLEU at medium and high latencyImproved
add Stage II speech-text modality alignment (ablation)EASiST · MuST-C En-De tst-COMMONBLEU vs LAALImproved
add Stage I SimulMT pre-training (ablation)EASiST · MuST-C En-De tst-COMMONBLEU vs LAALImproved
use multi-stage training instead of single-stage (ablation)EASiST · MuST-C En-De tst-COMMONBLEU and training hours: 154 -> 33 hoursImproved
fine-tune encoder and adapter instead of only encoder (ablation)EASiST Stage III · MuST-C En-De tst-COMMONBLEU vs LAALImproved
fine-tune adapter only instead of encoder+adapter (ablation)EASiST Stage III · MuST-C En-De tst-COMMONBLEU vs LAALNo clear effect
also update the LLM during Stage III (ablation)EASiST Stage III · MuST-C En-De tst-COMMONBLEU vs LAALHurt
raise policy threshold tau from 0.1 to 0.6 (ablation)EASiST · MuST-C En-De fluencyfluency: 7.51 -> 8.29Improved
use fully unidirectional architecture with KV cache reuseEASiST · Inference speedms/token: 123.75 (AlignAtt) -> 28.95Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy