SARAH: Spatially Aware Real-time Agentic Humans

TL;DR

The first real-time, fully causal method for spatially-aware conversational motion, deployable on a streaming VR headset, and validated on a live VR system, bringing spatially-aware conversational agents to real-time deployment.

Abstract

As embodied agents become central to VR, telepresence, and digital human applications, their motion must go beyond speech-aligned gestures: agents should turn toward users, respond to their movement, and maintain natural gaze. Current methods lack this spatial awareness. We close this gap with the first real-time, fully causal method for spatially-aware conversational motion, deployable on a streaming VR headset. Given a user's position and dyadic audio, our approach produces full-body motion that aligns gestures with speech while orienting the agent according to the user. Our architecture combines a causal transformer-based VAE with interleaved latent tokens for streaming inference and a flow matching model conditioned on user trajectory and audio. To support varying gaze preferences, we introduce a gaze scoring mechanism with classifier-free guidance to decouple learning from control: the model captures natural spatial alignment from data, while users can adjust eye contact intensity at inference time. On the Embody 3D dataset, our method achieves state-of-the-art motion quality at over 300 FPS -- 3x faster than non-causal baselines -- while capturing the subtle spatial dynamics of natural conversation. We validate our approach on a live VR system, bringing spatially-aware conversational agents to real-time deployment. Please see https://evonneng.github.io/sarah/ for details.

Figures (5)

• Figure 1: Given the user's 3D position and dyadic conversational audio, our model generates 3D motion that is conversationally and spatially aware (left). We use a fully causal transformer-based VAE with interleaved latent tokens at a fixed temporal stride; both encoder and decoder employ causal attention, where each $\mu/\sigma$ token attends only to preceding frames and earlier latents (center). These latents are passed to a transformer-based flow matching model that also uses causal masking and optionally accepts a gaze score for controlling the agent's eye contact (right). Our lightweight architecture enables real-time, autoregressive streaming without distillation.
• Figure 2: We represent each joint $j$ as a 3D icosahedron. The centroid of the vertices yields the global position $\boldsymbol{\Pi}_j$, and we recover the global orientation $\boldsymbol{\Omega}_j$ via SVD against a reference icosahedron.
• Figure 3: Our training data spans a wide range of gaze behaviors, from sustained eye contact to complete gaze aversion (left). To enable controllable gaze at inference, we compute a gaze score $g$, where $\mathbf{d}_x$ is the agent's facing direction and $\mathbf{d}_y$ points toward the user (right). The score approaches $1$ when facing the user directly and $-1$ when facing away.
• Figure 4: We visualize the agent’s facing direction via projected lines (agent: yellow $\rightarrow$ red; user: blue $\rightarrow$ green). With no alignment $g=\emptyset$, the agent’s gaze is more diverse; as we increase $g$, the agent increasingly turns towards the user.
• Figure 5: Sequences from our real-time demo system, rendered with a photorealistic avatar. The top row visualizes the user's headset location as a silver sphere. The bottom row shows the generated avatar from the user's (headset) viewpoint. Our method generates realistic conversational motion that is responsive to the user's spatial motion. Full videos are available on our https://evonneng.github.io/sarah/.