AI Paper Atlas

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

Diverse Sign Language Translation

Xin Shen, Shen Lei, Shaozu Yuan, Heming Du, Haiyang Sun, Xin Yu

IJCV 2026 · Large language models › Language, safety and interpretability · approach: Sign language datasets and translation · 9 citations (OpenAlex)

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
train with shuffled multi-reference strategy instead of Sample One (ablation)DivSLT stage 1 · PHOENIX14T-Div testBLEU-BM: 18.43 -> 24.20Improved
add stage 2 RL training (ablation)DivSLT · PHOENIX14T-Div testBLEU-BM: 24.20 -> 25.29Improved
add stage 2 RL training (ablation)DivSLT · PHOENIX14T-Div testpwb: 22.26 -> 26.30Hurt
use mixed XE+RL loss in stage 1 instead of XE only (ablation)DivSLT stage 1 · PHOENIX14T-Div testrfb-BM: 20.74 -> 19.18Hurt
use RL loss only in stage 2 instead of mixed loss 0.5/0.5 (ablation)DivSLT stage 2 · PHOENIX14T-Div testrfb-BM: 21.37 -> 22.12Improved
use diverse beam search instead of beam search (ablation)DivSLT · PHOENIX14T-Div testpwb: 57.14 -> 26.30Improved
use diverse beam search instead of beam search (ablation)DivSLT · PHOENIX14T-Div testrfb-BM: 23.35 -> 22.12Hurt
apply two-stage multi-reference paradigmGFSLT · PHOENIX14T-Div testBLEU-BM: 19.76 -> 25.29Improved
apply two-stage multi-reference paradigmRNN · PHOENIX14T-Div testBLEU-BM: 12.77 -> 13.97Improved
apply two-stage multi-reference paradigmTransformer · PHOENIX14T-Div testBLEU-BM: 10.49 -> 12.31Improved
apply two-stage multi-reference paradigmGASLT · PHOENIX14T-Div testBLEURT-BM: 49.07 -> 55.37Improved
add DivSLT-tailored vision-language pre-training (ablation)DivSLT · PHOENIX14T-Div testBLEU-BM: 25.29 -> 25.79Improved

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