GestureFAR: Streaming Co-Speech Gesture Generation with Flow Autoregression

arXiv:2609.21576 · cs.CV, cs.GR, cs.HC · Submitted 2026-09-18 · Read on arXiv

cs.CV, cs.GR, cs.HC

Submitted: 2026-09-18

Updated: 2026-09-18

Project page: https://andypinxinliu.github.io/GestureFAR

Terminology

• Distillation — 31× in this paper · explained in 2 episodes
• Transformer — 21× in this paper · explained in 2 episodes
• Consistency — 10× in this paper · explained in 3 episodes
• Distribution Matching — 10× in this paper · explained in 2 episodes
• Flow Matching — 6× in this paper · explained in 8 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Ablation Studies — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Quantization — 3× in this paper · explained in 12 episodes
• Beat Consistency — 2× in this paper
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Alternation — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Mean Opinion Score — 1× in this paper
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
• DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation
• One Step Diffusion via Shortcut Models
• Autoregressive Image Generation without Vector Quantization
• Flow Matching for Generative Modeling
• TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation
• EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
• BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis
• SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning
• Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• Towards Variable and Coordinated Holistic Co-Speech Motion Generation
• Consistency Models
• MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models