Pith. sign in

REVIEW 16 cited by

TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.03099 v1 pith:AVTJUZDD submitted 2025-06-03 cs.SD cs.AIcs.GR

TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models

classification cs.SD cs.AIcs.GR
keywords modeltalkingmachinesvideoaudio-drivengenerationautoregressiveefficientmodels
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this paper, we present TalkingMachines -- an efficient framework that transforms pretrained video generation models into real-time, audio-driven character animators. TalkingMachines enables natural conversational experiences by integrating an audio large language model (LLM) with our video generation foundation model. Our primary contributions include: (1) We adapt a pretrained SOTA image-to-video DiT into an audio-driven avatar generation model of 18 billion parameters; (2) We enable infinite video streaming without error accumulation through asymmetric knowledge distillation from a bidirectional teacher model into a sparse causal, autoregressive student model; (3) We design a high-throughput, low-latency inference pipeline incorporating several key engineering optimizations such as: (a) disaggregation of the DiT and VAE decoder across separate devices, (b) efficient overlap of inter-device communication and computation using CUDA streams, (c) elimination of redundant recomputations to maximize frame-generation throughput. Please see demo videos here - https://aaxwaz.github.io/TalkingMachines/

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Efficient Video Diffusion Models: Advancements and Challenges

    cs.CV 2026-04 unverdicted novelty 7.0

    A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.

  2. OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars

    cs.CV 2026-07 conditional novelty 6.0

    OmniMate generates real-time streaming video, speech, and sound effects for interactive avatars while preserving the same face and voice across long multi-turn conversations.

  3. Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

    cs.CV 2026-06 unverdicted novelty 6.0

    Wan-Streamer is a unified end-to-end Transformer for low-latency streaming audio-visual interaction using block-causal attention on interleaved multimodal tokens.

  4. InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars

    cs.CV 2026-06 unverdicted novelty 6.0

    InteractiveAvatar is a real-time infinite-streaming avatar video generation system using autoregressive distillation, Long-Short Visual Memory for consistency, and a Reasoning-Reaction Module for intent-aware interactions.

  5. InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars

    cs.CV 2026-06 unverdicted novelty 6.0

    InteractiveAvatar uses autoregressive distillation, Long-Short Visual Memory, and a Reasoning-Reaction Module to enable real-time, consistent, intent-aware avatar video streaming.

  6. Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs

    cs.CV 2026-06 unverdicted novelty 6.0

    A causal VAE with variable reference guidance and a Rectified Flow Transformer enables real-time streamable high-quality talking portrait video generation from audio and images.

  7. LPM 1.0: Video-based Character Performance Model

    cs.CV 2026-04 unverdicted novelty 6.0

    LPM 1.0 generates infinite-length, identity-stable, real-time audio-visual conversational performances for single characters using a distilled causal diffusion transformer and a new benchmark.

  8. Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

    cs.CV 2026-02 unverdicted novelty 6.0

    Rolling Sink is a training-free cache adjustment technique that maintains visual consistency in autoregressive video diffusion models for ultra-long open-ended generation beyond training horizons.

  9. Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

    cs.LG 2026-01 conditional novelty 6.0

    A causal diffusion-forcing model generates interactive head-avatar motion with 500ms motion-generation latency and learns expressive reactions via DPO with synthetic negative samples.

  10. Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

    cs.CV 2025-12 conditional novelty 6.0

    Live Avatar reports real-time streamable generation from a 14B audio-driven diffusion model at ~20 FPS on 5 H800s with stable identity over 10,000 seconds.

  11. Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

    cs.CV 2025-12 conditional novelty 6.0

    Live Avatar enables 45 FPS real-time streaming infinite-length audio-driven avatar generation from a 14B diffusion model via distillation and timestep-forcing pipeline parallelism.

  12. Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation

    cs.MM 2025-09 unverdicted novelty 6.0

    A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.

  13. Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

    cs.CV 2026-06 unverdicted novelty 5.0

    Wan-Streamer is a unified Transformer model for low-latency streaming audio-visual interaction that jointly handles perception, reasoning, generation, and timing without external modules.

  14. Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

    cs.CV 2026-06 unverdicted novelty 5.0

    Wan-Streamer presents a unified end-to-end Transformer for low-latency multimodal streaming interaction without external modules.

  15. PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment

    cs.CV 2026-04 unverdicted novelty 5.0

    PortraitDirector uses hierarchical disentanglement of spatial physical motions and semantic emotions to deliver controllable, high-fidelity real-time facial reenactment at 20 FPS.

  16. Image-to-Video Diffusion: From Foundations to Open Frontiers

    cs.CV 2026-05 unverdicted novelty 3.0

    A survey that organizes diffusion image-to-video methods into a taxonomy, distills core designs in condition encoding, temporal modeling, noise prior, and upsampling, and discusses applications plus challenges.