SAGE: Segment-Aware Gloss-Free Encoding for Token-Efficient Sign Language Translation 事件

SAGE: Segment-Aware Gloss-Free Encoding for Token-Efficient Sign Language Translation arXiv:2507.09266v2 Announce Type: replace Abstract: Gloss-free Sign Language Translation (SLT) has advanced rapidly, achieving strong performances without relying on gloss annotations. However, these gains have often come with increased model complexity and high computational demands, raising concerns about scalability, especially as large-scale sign language datasets become more common. We propose a segment-a