# ViPo-MLLM: Visual-Pose Multimodal LLM for Gloss-Free Sign Language Translation

arXiv: https://arxiv.org/abs/2607.03657 · HTML: https://mlsanity.com/paper/2607.03657/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 24 of 24)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation](https://mlsanity.com/paper/2003.13830/) (2020)
- [Improving Sign Language Translation with Monolingual Data by Sign Back-Translation](https://mlsanity.com/paper/2105.12397/) (2021)
- [Two-Stream Network for Sign Language Recognition and Translation](https://mlsanity.com/paper/2211.01367/) (2022)
- [Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining](https://mlsanity.com/paper/2307.14768/) (2023)
- [LLMs are Good Sign Language Translators](https://mlsanity.com/paper/2404.00925/) (2024)
- [TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation](https://mlsanity.com/paper/2010.05468/) (2020)
- [Multi-channel Transformers for Multi-articulatory Sign Language Translation](https://mlsanity.com/paper/2009.00299/) (2020)
- [Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation](https://mlsanity.com/paper/2405.04164/) (2024)
- [Gloss Attention for Gloss-free Sign Language Translation](https://mlsanity.com/paper/2307.07361/) (2023)
- [Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation](https://mlsanity.com/paper/2109.13318/) (2021)
- [Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues](https://mlsanity.com/paper/2501.09754/) (2025)
- [Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation](https://mlsanity.com/paper/2403.12556/) (2024)
- [Cross-modality Data Augmentation for End-to-End Sign Language Translation](https://mlsanity.com/paper/2305.11096/) (2023)
- [Leveraging the Power of MLLMs for Gloss-Free Sign Language Translation](https://mlsanity.com/paper/2411.16789/) (2024)
- [A Token-level Contrastive Framework for Sign Language Translation](https://mlsanity.com/paper/2204.04916/) (2022)
- [An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs](https://mlsanity.com/paper/2408.10593/) (2024)
- [Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment](https://mlsanity.com/paper/2512.08040/) (2025)
- [AraReasoner: Evaluating Reasoning-Based LLMs for Arabic NLP](https://mlsanity.com/paper/2506.08768/) (2025)
- [USTM: Unified Spatial and Temporal Modeling for Continuous Sign Language Recognition](https://mlsanity.com/paper/2512.13415/) (2025)

## Abstract (arXiv)

Gloss-free Sign Language Translation (SLT) translates sign language videos into spoken-language sentences without gloss annotations, avoiding costly labeling but requiring fine-grained modeling of hands, body, and facial cues. Existing methods often use single-modality or weakly fused features, limiting performance. We propose ViPo-MLLM, a framework that integrates spatio-temporal RGB and human pose features. Dedicated encoders model intra-modal dynamics and cross-modal attention captures long-range dependencies. The fused representation is conditioned with a structured prompt and processed by an LLM trained with contrastive and language modeling objectives. The proposed model was evaluated on the PHOENIX14T and CSL-Daily datasets and achieved new state-of-the-art results on both datasets. Moreover, the ViPo-MLLM model attained competitive performance compared to gloss-based recognition approaches, confirming the effectiveness of the proposed pose cues and cross-modal attention mechanisms.