# FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation

arXiv: https://arxiv.org/abs/2603.27915 · HTML: https://mlsanity.com/paper/2603.27915/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 45 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 30 of 33)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)
- [Sparse Sinkhorn Attention](https://mlsanity.com/paper/2002.11296/) (2020)
- [Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison](https://mlsanity.com/paper/1910.11006/) (2019)
- [Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity](https://mlsanity.com/paper/2502.01776/) (2025)
- [Flex Attention: A Programming Model for Generating Optimized Attention Kernels](https://mlsanity.com/paper/2412.05496/) (2024)
- [How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language](https://mlsanity.com/paper/2008.08143/) (2020)
- [SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration](https://mlsanity.com/paper/2410.02367/) (2024)
- [UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining](https://mlsanity.com/paper/2304.09151/) (2023)
- [Fast Video Generation with Sliding Tile Attention](https://mlsanity.com/paper/2502.04507/) (2025)
- [Progressive Transformers for End-to-End Sign Language Production](https://mlsanity.com/paper/2004.14874/) (2020)
- [Loong: Generating Minute-level Long Videos with Autoregressive Language Models](https://mlsanity.com/paper/2410.02757/) (2024)
- [Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent](https://mlsanity.com/paper/2411.02265/) (2024)
- [Training-free and Adaptive Sparse Attention for Efficient Long Video Generation](https://mlsanity.com/paper/2502.21079/) (2025)
- [Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production](https://mlsanity.com/paper/2203.15354/) (2022)
- [ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification](https://mlsanity.com/paper/2410.08584/) (2024)
- [T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching](https://mlsanity.com/paper/2402.14167/) (2024)
- [LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models](https://mlsanity.com/paper/2603.07145/) (2026)
- [Improving Continuous Sign Language Recognition with Cross-Lingual Signs](https://mlsanity.com/paper/2308.10809/) (2023)
- [Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile](https://mlsanity.com/paper/2502.06155/) (2025)
- [A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights](https://mlsanity.com/paper/2407.08428/) (2024)
- [PresentAgent: Multimodal Agent for Presentation Video Generation](https://mlsanity.com/paper/2507.04036/) (2025)
- [FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion](https://mlsanity.com/paper/2506.04648/) (2025)
- [UniVid: The Open-Source Unified Video Model](https://mlsanity.com/paper/2509.24200/) (2025)
- [DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion](https://mlsanity.com/paper/2510.15264/) (2025)
- [Towards AI-driven Sign Language Generation with Non-manual Markers](https://mlsanity.com/paper/2502.05661/) (2025)
- [ChaLearn LAP Large Scale Signer Independent Isolated Sign Language Recognition Challenge: Design, Results and Future Research](https://mlsanity.com/paper/2105.05066/) (2021)

## Abstract (arXiv)

Sign language plays a crucial role in bridging communication gaps between the deaf and hard-of-hearing communities. However, existing sign language video generation models often rely on complex intermediate representations, which limits their flexibility and efficiency. In this work, we propose a novel pose-free framework for real-time sign language video generation. Our method eliminates the need for intermediate pose representations by directly mapping natural language text to sign language videos using a diffusion-based approach. We introduce two key innovations: (1) a pose-free generative model based on the a state-of-the-art diffusion backbone, which learns implicit text-to-gesture alignments without pose estimation, and (2) a Trainable Sliding Tile Attention (T-STA) mechanism that accelerates inference by exploiting spatio-temporal locality patterns. Unlike previous training-free sparsity approaches, T-STA integrates trainable sparsity into both training and inference, ensuring consistency and eliminating the train-test gap. This approach significantly reduces computational overhead while maintaining high generation quality, making real-time deployment feasible. Our method increases video generation speed by 3.07x without compromising video quality. Our contributions open new avenues for real-time, high-quality, pose-free sign language synthesis, with potential applications in inclusive communication tools for diverse communities. Code: https://github.com/AIGeeksGroup/FlashSign.