RVLF: A Reinforcing Vision-Language Framework for Gloss-Free Sign Language Translation

• URL: http://arxiv.org/abs/2512.07273v1
• Date: Mon, 08 Dec 2025 08:11:53 GMT
• Title: RVLF: A Reinforcing Vision-Language Framework for Gloss-Free Sign Language Translation
• Authors: Zhi Rao, Yucheng Zhou, Benjia Zhou, Yiqing Huang, Sergio Escalera, Jun Wan,
• Abstract summary: We build a large vision-language model (LVLM) specifically designed for sign language.<n>For a sufficient representation of sign language, RVLF introduces an effective semantic representation learning mechanism.<n>Then, to improve sentence-level semantic misalignment, we introduce a GRPO-based optimization strategy.
• Score: 44.39679803351263
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gloss-free sign language translation (SLT) is hindered by two key challenges: **inadequate sign representation** that fails to capture nuanced visual cues, and **sentence-level semantic misalignment** in current LLM-based methods, which limits translation quality. To address these issues, we propose a three-stage **r**einforcing **v**ision-**l**anguage **f**ramework (**RVLF**). We build a large vision-language model (LVLM) specifically designed for sign language, and then combine it with reinforcement learning (RL) to adaptively enhance translation performance. First, for a sufficient representation of sign language, RVLF introduces an effective semantic representation learning mechanism that fuses skeleton-based motion cues with semantically rich visual features extracted via DINOv2, followed by instruction tuning to obtain a strong SLT-SFT baseline. Then, to improve sentence-level semantic misalignment, we introduce a GRPO-based optimization strategy that fine-tunes the SLT-SFT model with a reward function combining translation fidelity (BLEU) and sentence completeness (ROUGE), yielding the optimized model termed SLT-GRPO. Our conceptually simple framework yields substantial gains under the gloss-free SLT setting without pre-training on any external large-scale sign language datasets, improving BLEU-4 scores by +5.1, +1.11, +1.4, and +1.61 on the CSL-Daily, PHOENIX-2014T, How2Sign, and OpenASL datasets, respectively. To the best of our knowledge, this is the first work to incorporate GRPO into SLT. Extensive experiments and ablation studies validate the effectiveness of GRPO-based optimization in enhancing both translation quality and semantic consistency.

Related papers

• DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning [53.36809572236361]
  Few-shot learning aims to generalize to novel categories with only a few samples.<n>Recent approaches incorporate large language models to enrich visual representations with semantic embeddings derived from class names.<n>We propose Dual-level Vision-Language Alignment with Reinforcement Learning gating (DVLA-RL)
  arXiv  Detail & Related papers  (2026-01-31T16:09:37Z)
• Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment [84.39962912136525]
  We develop a model for sign language understanding that performs sign language translation (SLT) and sign-subtitle alignment (SSA)<n>Our approach is built upon three components: (i) a lightweight visual backbone that captures manual and non-manual cues from human keypoints and lip-region images; (ii) a Sliding Perceiver mapping network that aggregates consecutive visual features into word-level embeddings; and (iii) a multi-task scalable training strategy that jointly optimises SLT and SSA.
  arXiv  Detail & Related papers  (2025-12-08T21:05:46Z)
• Uni-Sign: Toward Unified Sign Language Understanding at Scale [90.76641997060513]
  We propose a unified pre-training framework that eliminates the gap between pre-training and downstream SLU tasks.<n>Uni-Sign achieves state-of-the-art performance across multiple downstream SLU tasks.
  arXiv  Detail & Related papers  (2025-01-25T11:51:23Z)
• LLaVA-SLT: Visual Language Tuning for Sign Language Translation [42.20090162339927]
  Recent advancements in Sign Language Translation (SLT) have shown promise, yet they often largely lag behind gloss-based approaches in terms of accuracy.<n>We introduce LLaVA-SLT, a pioneering Large Multimodal Model (LMM) framework designed to leverage the power of Large Language Models (LLMs) through effectively learned visual language embeddings.<n>Our comprehensive experiments demonstrate that LLaVA-SLT outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-12-21T08:01:08Z)
• VladVA: Discriminative Fine-tuning of LVLMs [67.14293827774827]
  Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning.<n>We propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs.
  arXiv  Detail & Related papers  (2024-12-05T17:54:27Z)
• DiffSLT: Enhancing Diversity in Sign Language Translation via Diffusion Model [9.452839238264286]
  We propose DiffSLT, a novel gloss-free sign language translation framework. DiffSLT transforms random noise into the target latent representation conditioned on the visual features of input video. We also introduce DiffSLT-P, a DiffSLT variant that conditions on pseudo-glosses visual features, providing key textual guidance and reducing the modality gap.
  arXiv  Detail & Related papers  (2024-11-26T09:26:36Z)
• LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation [72.02635550088546]
  This work explores how large language models (LLMs) can enhance CLIP's capability, especially for processing longer and more complex image captions.<n>We introduce a caption-to-caption contrastive fine-tuning framework, significantly enhancing the discriminative quality of LLM outputs.<n>Our approach outperforms LoRA-based methods, achieving nearly fourfold faster training with superior performance.
  arXiv  Detail & Related papers  (2024-11-07T18:59:16Z)
• Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation [28.648494997132925]
  We propose Factorized Learning assisted with Large Language Model (FLa-LLM) for gloss-free Sign Language Translation (SLT) We factorize the training process into two stages. In the visual initialing stage, we employ a lightweight translation model after the visual encoder to pre-train the visual encoder. In the LLM fine-tuning stage, we freeze the acquired knowledge in the visual encoder and integrate it with a pre-trained LLM to inspire the LLM's translation potential.
  arXiv  Detail & Related papers  (2024-03-19T09:00:23Z)
• Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining [56.26550923909137]
  Gloss-Free Sign Language Translation (SLT) is a challenging task due to its cross-domain nature. We propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-) Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual and Text Decoder from
  arXiv  Detail & Related papers  (2023-07-27T10:59:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.