# RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robots

arXiv: https://arxiv.org/abs/2609.32250 · HTML: https://mlsanity.com/paper/2609.32250/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis](https://mlsanity.com/paper/2412.04431/) (2024)
- [How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language](https://mlsanity.com/paper/2008.08143/) (2020)
- [WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild](https://mlsanity.com/paper/2409.12259/) (2024)
- [Progressive Transformers for End-to-End Sign Language Production](https://mlsanity.com/paper/2004.14874/) (2020)
- [Adversarial Training for Multi-Channel Sign Language Production](https://mlsanity.com/paper/2008.12405/) (2020)
- [Neural Sign Actors: A diffusion model for 3D sign language production from text](https://mlsanity.com/paper/2312.02702/) (2023)
- [InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation](https://mlsanity.com/paper/2511.04675/) (2025)
- [WHAC: World-grounded Humans and Cameras](https://mlsanity.com/paper/2403.12959/) (2024)
- [T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text](https://mlsanity.com/paper/2406.07119/) (2024)
- [SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark](https://mlsanity.com/paper/2310.20436/) (2023)
- [SignDiff: Diffusion Model for American Sign Language Production](https://mlsanity.com/paper/2308.16082/) (2023)
- [Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator](https://mlsanity.com/paper/2411.17799/) (2024)
- [SignBot: Learning Human-to-Humanoid Sign Language Interaction](https://mlsanity.com/paper/2505.24266/) (2025)
- [Next-Scale Autoregressive Models for Text-to-Motion Generation](https://mlsanity.com/paper/2604.03799/) (2026)
- [SignVLA: A Gloss-Free Vision-Language-Action Framework for Real-Time Sign Language-Guided Robotic Manipulation](https://mlsanity.com/paper/2602.22514/) (2026)
- [Stable Signer: Hierarchical Sign Language Generative Model](https://mlsanity.com/paper/2512.04048/) (2025)
- [M3T: Discrete Multi-Modal Motion Tokens for Sign Language Production](https://mlsanity.com/paper/2603.23617/) (2026)

## Abstract (arXiv)

Sign-language interpretation in public communication relies on qualified professional interpreters and can be difficult to scale, motivating robotic signing as a complementary accessibility interface. We present RoBoSTAR, a text-conditioned sign language production (SLP) framework for generating human-centric sign motion that can be retargeted for robotic execution, with speech supported optionally through an external ASR front end. Conventional autoregressive approaches flatten motion into a single full-resolution token sequence, forcing long-range and local dependencies to be modeled at a uniform temporal granularity. RoBoSTAR instead combines part-wise Finite Scalar Quantization with next-scale autoregression, generating motion over progressively finer temporal resolutions while predicting synchronized body and hand tokens in parallel within each step. This coarse-to-fine formulation provides compact long-range context before progressively refining motion details, while self-conditioning and context corruption improve robustness to cross-scale prediction errors. The generated motion is subsequently retargeted for physical humanoid execution. Extensive qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of RoBoSTAR.