# MaDiS: Taming Masked Diffusion Language Models for Sign Language Generation

arXiv: https://arxiv.org/abs/2601.19577 · HTML: https://mlsanity.com/paper/2601.19577/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Sign language production, one of 14 directions in Diffusion models.
- Builds on 92 of its 107 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Placed in

- Diffusion models / [Sign language production](https://mlsanity.com/diffusion/sign-language-production/)

## Builds on (most cited first, 30 of 92)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Simplified and Generalized Masked Diffusion for Discrete Data](https://mlsanity.com/paper/2406.04329/) (2024)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data](https://mlsanity.com/paper/2406.03736/) (2024)
- [ControlVideo: Training-free Controllable Text-to-Video Generation](https://mlsanity.com/paper/2305.13077/) (2023)
- [Scaling Diffusion Language Models via Adaptation from Autoregressive Models](https://mlsanity.com/paper/2410.17891/) (2024)
- [MMaDA: Multimodal Large Diffusion Language Models](https://mlsanity.com/paper/2505.15809/) (2025)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models](https://mlsanity.com/paper/2205.10770/) (2022)
- [Scaling up Masked Diffusion Models on Text](https://mlsanity.com/paper/2410.18514/) (2024)
- [TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis](https://mlsanity.com/paper/2305.00976/) (2023)

## Built on by (most cited first, 4 of 4)

- [M3T: Discrete Multi-Modal Motion Tokens for Sign Language Production](https://mlsanity.com/paper/2603.23617/) (2026)
- [BackTranslation2.0 -- A Linguistically Motivated Metric to Assess Sign Language Production](https://mlsanity.com/paper/2606.28673/) (2026)
- [SeRV: Semantic-Aligned Residual Vector Quantization for American Sign Language Generation](https://mlsanity.com/paper/2609.05742/) (2026)
- [Kinematics-Centric Continuous Sign Language Retrieval with Gloss-Guided Boundary-Aware Alignment](https://mlsanity.com/paper/2610.05306/) (2026)

## Abstract (arXiv)

Sign language generation (SLG) aims to translate written texts into expressive sign motions, bridging communication barriers for the Deaf and Hard-of-Hearing communities. Recent studies formulate SLG within the language modeling framework using autoregressive language models, which suffer from unidirectional context modeling and slow token-by-token inference. To address these limitations, we present MaDiS, a masked-diffusion-based language model for SLG that captures bidirectional dependencies and supports efficient parallel multi-token generation. We further introduce a tri-level cross-modal pretraining scheme that jointly learns from token-, latent-, and 3D physical-space objectives to leverage complementary, multi-level sign representations. To accelerate model convergence in the fine-tuning stage, we design a novel unmasking strategy with temporal checkpoints, which restructures generation in a coarse-to-fine manner and reduces the combinatorial complexity of unmasking orders by over 1041 times. In addition, a mixture-of-parts embedding layer is developed to effectively fuse information stored in different part-wise sign tokens through a learnable gate and well-optimized codebooks. Extensive experiments on CSL-Daily, Phoenix-2014T, and How2Sign demonstrate that MaDiS achieves superior performance across multiple metrics, including DTW error and two newly introduced metrics, SiBLEU and SiCLIP, while delivering a 40% higher throughput. Code and models will be publicly released.