Story

arxiv_cs_cl ยท Nov 4, 2026 ยท paper

Source brief

CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation

arxiv.orgNov 4, 2026
original source linked

In brief

Simultaneous Speech Translation (SimulST) requires balancing translation quality and latency. While Large Language Models (LLMs) excel in offline translation, current LLM-based SimulST systems predominantly rely on pr...

Feed lens
eval

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items