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
TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models
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/
Forward citations
Cited by 16 Pith papers
-
Efficient Video Diffusion Models: Advancements and Challenges
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.
-
OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars
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.
-
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
Wan-Streamer is a unified end-to-end Transformer for low-latency streaming audio-visual interaction using block-causal attention on interleaved multimodal tokens.
-
InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars
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.
-
InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars
InteractiveAvatar uses autoregressive distillation, Long-Short Visual Memory, and a Reasoning-Reaction Module to enable real-time, consistent, intent-aware avatar video streaming.
-
Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs
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.
-
LPM 1.0: Video-based Character Performance Model
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.
-
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
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.
-
Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation
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.
-
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
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.
-
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
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.
-
Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.
-
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
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.
-
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
Wan-Streamer presents a unified end-to-end Transformer for low-latency multimodal streaming interaction without external modules.
-
PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment
PortraitDirector uses hierarchical disentanglement of spatial physical motions and semantic emotions to deliver controllable, high-fidelity real-time facial reenactment at 20 FPS.
-
Image-to-Video Diffusion: From Foundations to Open Frontiers
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.