Results show that \method preserves stable appearance across prompt-conditioned segments and strong audio-visual synchronization under autoregressive generation, accelerating autoregressive inference without pipeline-specific retraining.
Abstract
Real-time long-form digital-human generation relies on causal models to extend audio-visual content while preserving subject appearance and audio-video synchronization across successive segments. A bounded cache retains local motion and phonetic context but discards older evidence, whereas attending to the complete generated history is computationally expensive and can propagate accumulated errors. We present \method, an anchor-guided persistent-memory framework for few-step joint audio-video generation. The framework preserves an immutable visual anchor, compresses completed video and audio blocks into fixed-capacity dynamic states, and retrieves those states through modality-specific residual attention without extending the active cache. A reference-aware modulation method additionally conditions video features on dynamic and anchor appearance statistics. Anchor-preserving causal-context distillation varies rollout horizon, prefix provenance, and cache-history reliability while keeping the immutable visual anchor unperturbed. By separating persistent memory from stage-local denoising dependencies, \method further admits stage-parallel execution across blocks, accelerating autoregressive inference without pipeline-specific retraining. We evaluate long-form video continuations with appearance, temporal, synchronization, facial, and speech diagnostics. Results show that \method preserves stable appearance across prompt-conditioned segments and strong audio-visual synchronization under autoregressive generation. Our project page is https://taoliveaigc.github.io/TaoMate.
LiveVVT is introduced, a rolling streaming diffusion framework that preserves bounded bidirectional modeling within causal recurrent generation, and a progressive distillation framework integrating bidirectional VVT learning, teacher-trajectory regression for causal few-step adaptation, and Collaborative Matching Distillation, which couples teacher-distribution matching with rolling flow matching on real videos to align optimization with recurrent inference.
Yushe Cao, Shikun Feng, Ru-Xiang Duan et al.· 0 citations
StreamFlow is introduced, an efficient visual memory framework that enables dynamic, on-demand access to historical visual information and improves the visual attention score while reducing end-to-end latency and peak memory, enabling more visually grounded and efficient reasoning.
Muxin Fu, Yifan Zhang, Wentao Zhang et al.· 0 citations
Ripple is a real-time joint audio-video generation system with a cross-modal recurrent memory mechanism that combines a fixed-length sliding-window attention with modality-specific memory states that continuously summarize audio and video context.
Yanbo Ding, Zhizhi Guo, Quanyue Song et al.· arXiv.org· 0 citations
Real-time long-form avatar audio-video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consistency. Adapting a pretrained bidirectional model to this setting presents two key dilemmas. First, autoregressively reusing generated blocks as context creates exposure bias, causing errors and visual drift to accumulate over long rollouts. Second, a global speech utterance does not indicates a causal generator which portion should be spoken next when only limited local audio-video context is available. We present Vorch-Streamer, a post-training framework that addresses these challenges and enables real-time long-form Text-to-Audio-Video (T2AV) streaming. We construct a synthetic corpus of 80K avatar clips spanning 12-21 seconds and first train a causal generator with mixed Teacher Forcing and Diffusion Forcing. We then apply long-horizon Self Forcing with DMD distillation, exposing the model to its own rollout distribution while preserving the quality of the pretrained bidirectional teacher. To explicitly control speech progression, an external language model predicts discrete 25-Hz speech-planning tokens, whose continuous features condition the audio diffusion branch and align each causal block with the content it should speak. With bounded causal context and four-step denoising, Vorch-Streamer jointly generates audio and video from text at 27.12 FPS, exceeding the 24-FPS real-time playback rate while maintaining competitive audio-lip synchronization and strong identity preservation over long-form generation.
Menglin Han, Yang Ding, Yulei Lu et al.· 0 citations
Autoregressive video diffusion enables scalable long-video generation by producing chunks from a bounded recent context. While recency-based caching preserves local continuity, it evicts historical cues needed when subjects, objects, scenes, or attributes reappear. Existing memory mechanisms expose models to nonlocal history, but access alone does not ensure effective use. Our analysis reveals that video DiT layers exhibit distinct preferences for current, recent, and distant context, suggesting that long-range memory requires deciding both what to retrieve and where to use it. We introduce LayerRecall, a current-conditioned, layer-selective memory router that retrieves relevant historical K/V states and injects them only into backbone-specific memory-sensitive layers while preserving local attention elsewhere. To reduce reliance on scarce high-quality long-horizon videos and explicit memory-allocation labels, we further propose Cross-Horizon Prediction Matching (CHPM), which uses a privileged long-context reference to supervise the bounded-memory router in prediction space. Across 100 multi-shot evaluation prompts, LayerRecall achieves the best overall results on MemoBench and MovieBench while matching its backbone on VBench-Long, demonstrating stronger long-range recovery without sacrificing local continuity. Qualitative analyses further reveal memory-guided self-correction, whereby initially mismatched local attributes return to their historical appearance without resetting ongoing motion or scene structure. Additional analyses show cross-backbone portability and negligible inference overhead.
Yixuan Ding, Jia-Hao Kong, Wei Huang et al.· 0 citations
This work proposes to decouple the frequencies of memory updates and Memory Caching, and introduces two critical mechanisms: an auxiliary Memory Loss that forces persistent internalization of the scene, and a Memory Caching strategy that regularizes active weights against catastrophic drift.
Baback Elmieh, Lynn Tsai, Zeman Li et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
