# Vorch-Director: Interactive World Story Model via Noise-Aware Error Rectification arXiv: https://arxiv.org/abs/2608.05776 ยท HTML: https://mlsanity.com/paper/2608.05776/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Placed in Video generation, one of 14 directions in Diffusion models. - Builds on 29 of its 31 references that are in the map. - First posted on arXiv 6 Aug 2026. ## Placed in - Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/) ## Builds on (most cited first, 29 of 29) - [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022) - [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025) - [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024) - [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024) - [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024) - [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025) - [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024) - [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024) - [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025) - [Seedance 2.0: Advancing Video Generation for World Complexity](https://mlsanity.com/paper/2604.14148/) (2026) - [Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory](https://mlsanity.com/paper/2604.08995/) (2026) - [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025) - [HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives](https://mlsanity.com/paper/2510.20822/) (2025) - [StoryMem: Multi-shot Long Video Storytelling with Memory](https://mlsanity.com/paper/2512.19539/) (2025) - [VideoMemory: Toward Consistent Video Generation via Memory Integration](https://mlsanity.com/paper/2601.03655/) (2026) - [Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models](https://mlsanity.com/paper/2606.25473/) (2026) - [Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework](https://mlsanity.com/paper/2503.10704/) (2025) - [DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation](https://mlsanity.com/paper/2602.12160/) (2026) - [FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion](https://mlsanity.com/paper/2512.11274/) (2025) - [TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment](https://mlsanity.com/paper/2606.13035/) (2026) - [VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction](https://mlsanity.com/paper/2601.05966/) (2026) - [AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising](https://mlsanity.com/paper/2603.14331/) (2026) - [CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation](https://mlsanity.com/paper/2606.09639/) (2026) - [UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating](https://mlsanity.com/paper/2606.21661/) (2026) - [Memento: Reconstruct to Remember for Consistent Long Video Generation](https://mlsanity.com/paper/2606.14667/) (2026) - [Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling](https://mlsanity.com/paper/2604.23586/) (2026) - [Towards Error-Free Long Video Generation](https://mlsanity.com/paper/2606.22370/) (2026) - [Corruption-Aware Training of Latent Video Diffusion Models for Robust Text-to-Video Generation](https://mlsanity.com/paper/2505.21545/) (2025) - [FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching](https://mlsanity.com/paper/2605.20910/) (2026) ## Built on by (most cited first, 1 of 1) - [RECAP-Forcing: Retaining Content Appearances for Long Video Generation](https://mlsanity.com/paper/2608.26671/) (2026) ## Abstract (arXiv) 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.