Vorch-Director is proposed, a noise-level-aware residual correction strategy that associates each residual with its originating noise level and injects residuals from matched noise regimes during training to produce more realistic autoregressive histories while retaining efficient teacher-forcing training.
Abstract
Autoregressive continuation provides a natural path toward minute-scale audio-visual generation by repeatedly extending a short-window generator conditioned on previously generated video and audio. However, models are trained on clean ground-truth histories, while inference relies on their own generated histories, where accumulated errors cause identity drift, over-smoothing, and audio-visual desynchronization. Recent methods reduce this mismatch by reusing prediction residuals as synthetic corruption, but we observe that the effectiveness of residual correction critically depends on the flow-matching noise level at which residuals are produced. We propose Vorch-Director, a noise-level-aware residual correction strategy that associates each residual with its originating noise level and injects residuals from matched noise regimes during training. By aligning injected errors with the denoising process, Vorch-Director produces more realistic autoregressive histories while retaining efficient teacher-forcing training. Built on the audio-visual LTX-2 diffusion transformer, Vorch-Director further introduces task embeddings to distinguish historical video, reference images, and target video, enabling unified conditioning for long-horizon generation. Together with a clean conditioning sink and mixed-task training, Vorch-Director supports multi-shot, multi-subject, reference-guided audio-visual long-video generation. We evaluate Vorch-Director on ST-Bench and introduce a new long-horizon audio-visual benchmark with metrics for quality drift and long-range consistency. Extensive experiments demonstrate improved stability and audio-visual fidelity over strong baselines.
Self Gradient Forcing (SGF), a two-pass training strategy that restores this missing memory-writing supervision within the native autoregressive training objective, using losses on future video latents to train the model to encode context into more effective causal memory.
Autoregressive (AR) video diffusion models have shown great potential in real-time video generation. Recent methods distill pretrained bidirectional video diffusion models into causal AR students through Distribution Matching Distillation (DMD), but the generated videos often suffer from over-saturation and over-smoothing issues, resulting in limited visual quality and realism. The key contributing factor is the mode-seeking behavior of the reverse KL objective in DMD, which can cause the student distribution to collapse onto only a few modes of the teacher distribution. To address this, we propose Mask Forcing, a Dual-Noise Masking Rollout strategy that perturbs the AR student self-rollout to mitigate mode collapse induced by reverse-KL mode seeking. The core idea is to inject cleaner signals into noisy rollout inputs via random masks along spatial and temporal axes during the self-rollout process of AR diffusion distillation. Such perturbations encourage the student rollouts to explore more regions of the teacher distribution, allowing DMD to provide learning signals beyond the modes already covered by the student. Moreover, the cleaner tokens act as denoising guidance for other noisier tokens, improving the intermediate rollout predictions and reducing error accumulation. Extensive experiments demonstrate that our method improves multiple AR video diffusion distillation methods with higher visual quality efficiently, without incorporating real video data or additional post-training stages.
Zhuo-Ran Zhao, Sheng-Ju Qian, Tong-Tong Liang et al.· 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
Terminal points Avoidance through Noise Guided Optimization (TANGO) is introduced, which uses the diffusion model as a critic of its own outputs, by predicting one step forward and requiring an isotropic Gaussian noise prediction.
Dimitrios Karageorgiou, Symeon Papadopoulos, Y. Kompatsiaris et al.· arXiv.org· 0 citations
This work establishes the first connection between autoregressive video drifting and model internal representations, adopts erank as a quantitative metric for error accumulation, reveals counterintuitive scaling limitations for video world models, and presents a simple yet effective regularization strategy to improve long video generation robustness.
The proposed FreqForcing is a training-free framework that addresses error accumulation in long-video generation via Spectral Self-Anchoring (SSA), which leverages the low-frequency components of anchor attention to maintain long-horizon visual stability, while preserving dynamic motion through the high-frequency components of local attention.
Jia-Tong Li, Leo Liang, Linghe Kong et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
