AI Paper Atlas

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

BoostSLT: Boosting Sign Language Translation via a Plug-and-Play Diffusion-Based Semantic Enhancer

Changzhou Han, Wanlun Ma, Xi Tang, Kun Hu, Sheng Wen, Yang Xiang

CVPR 2026 · Large language models › Language, safety and interpretability · approach: Controlled text generation

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
add BoostSLT (EAT-Seg + DSR) to CV-SLTCV-SLT · PHOENIX-2014T DevBLEU-4: 29.10 -> 33.48Improved
add BoostSLT to TwoStreamNetworkTwoStreamNetwork · PHOENIX-2014T TestBLEU-4: 28.95 -> 30.12Improved
add BoostSLT to GASLTGASLT · PHOENIX-2014T TestBLEU-4: 15.62 -> 21.95Improved
add BoostSLT to MMTLBMMTLB · Auslan-Daily NewsBLEU-4: 2.31 -> 12.46Improved
add BoostSLT to LLM-based Sign2GPT and LiTFiCSign2GPT, LiTFiC · PHOENIX-2014T TestBLEU-4: Sign2GPT 15.23 -> 18.61; LiTFiC 23.62 -> 25.83Improved
add BoostSLT to CV-SLT on CSL-DailyCV-SLT · CSL-Daily TestBLEU-4: 28.94 -> 32.49Improved
add BoostSLT to TwoStreamNetwork on CSL-DailyTwoStreamNetwork · CSL-Daily TestBLEU-4: 25.79 -> 28.96Improved
add DSR diffusion reconstruction on top of EAT-Seg (ablation)GASLT pipeline · PHOENIX-2014T TestBLEU-4: 17.44 (EAT-Seg + GPT) -> 21.95 (EAT-Seg + DSR)Improved
replace random segmentation with EAT-Seg in the DSR pipeline (ablation)GASLT pipeline with DSR · PHOENIX-2014T TestBLEU-4: 16.30 -> 21.95Improved
use random segmentation alone without post-editing (ablation)GASLT pipeline · PHOENIX-2014T TestBLEU-4: 15.62 -> 8.03Hurt
add GPT autoregressive post-editing to direct concatenation (ablation)GASLT pipeline · PHOENIX-2014T TestBLEU-4: 15.62 -> 14.71Hurt
add fine-tuned LLaMA post-editing to direct concatenation (ablation)GASLT pipeline · PHOENIX-2014T TestBLEU-4: 15.62 -> 15.36No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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