# GestureFAR: Streaming Co-Speech Gesture Generation with Flow Autoregression

arXiv: https://arxiv.org/abs/2609.21576 · HTML: https://mlsanity.com/paper/2609.21576/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [One Step Diffusion via Shortcut Models](https://mlsanity.com/paper/2410.12557/) (2024)
- [Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity](https://mlsanity.com/paper/2009.02119/) (2020)
- [Autoregressive Video Generation without Vector Quantization](https://mlsanity.com/paper/2412.14169/) (2024)
- [Generating Holistic 3D Human Motion from Speech](https://mlsanity.com/paper/2212.04420/) (2022)
- [Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation](https://mlsanity.com/paper/2203.13161/) (2022)
- [From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations](https://mlsanity.com/paper/2401.01885/) (2024)
- [DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation](https://mlsanity.com/paper/2401.04747/) (2024)
- [GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling](https://mlsanity.com/paper/2501.18898/) (2025)
- [Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation](https://mlsanity.com/paper/2410.00464/) (2024)
- [TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation](https://mlsanity.com/paper/2410.04221/) (2024)
- [SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning](https://mlsanity.com/paper/2507.19359/) (2025)
- [Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation](https://mlsanity.com/paper/2502.07239/) (2025)
- [MIBURI: Towards Expressive Interactive Gesture Synthesis](https://mlsanity.com/paper/2603.03282/) (2026)
- [Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion](https://mlsanity.com/paper/2503.10488/) (2025)

## Built on by (most cited first, 1 of 1)

- [Sonic-AMG: Streaming Human Motion Generation from Spatial Audio](https://mlsanity.com/paper/2610.13300/) (2026)

## Abstract (arXiv)

Generating natural co-speech gestures from streaming speech is essential for embodied conversational agents, where motion must be produced while a user is still speaking. Recent streaming gesture systems make online generation possible by autoregressing over discrete motion tokens, but this design compresses high-dimensional continuous motion into finite codebooks and can limit the realism and diversity of generated gestures. To preserve both causality and continuous expressiveness, we propose GestureFAR, a flow-autoregressive framework for streaming co-speech gesture generation. First, GestureFAR autoregresses over causal continuous motion latents, using a transformer to model streaming audio-motion context and a per-token flow-matching head to sample the next latent from a continuous distribution. Second, we introduce a head-only flow distillation strategy that freezes the causal backbone and distills the multi-step per-token flow head into a single network evaluation using consistency and distribution-matching objectives. This keeps the model token-causal while removing the main latency bottleneck for live interaction. Experiments on BEAT2 show that GestureFAR significantly improves the quality--latency trade-off among streaming-capable methods, preserving strong gesture quality while enabling real-time token-causal generation. Project Page: https://andypinxinliu.github.io/GestureFAR