Autoregressive Video Generation

Ask about this topic

Overview

Autoregressive video generation studies how to produce a sequence of frames or video chunks conditioned on earlier content, enabling streaming output and interactive control. Common approaches use causal diffusion transformers, often distilled from bidirectional models to reduce denoising steps, and add action, camera, audio, or text conditioning for world models and editing. To extend generation beyond short clips, methods train on model-generated histories and use retrieval, compressed KV caches, or structured memory to preserve identities, scenes, and motion. The central challenge is balancing speed and bounded memory with visual quality, diverse motion, and consistency over long rollouts, which benchmarks such as VBench-Long and task-specific interaction tests attempt to measure.

Latest papers

CardsList

211 papers46 papers in the last four weeks, up 207% on the four weeks before. 0.3% of all new papers.

Apr 3, 2026

Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation

Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking intermediate cases where direct reuse is too coarse yet full recomputation is unnecessary. Moreover, asynchronous AR schedules assign different noise levels to co-generated frames, yet existing methods process the entire valid interval uniformly. To address these AR-specific inefficiencies, we present SCOPE, a training-free framework for efficient AR video diffusion. SCOPE introduces a tri-modal scheduler over cache, predict, and recompute, where prediction via noise-level Taylor extrapolation fills the gap between reuse and recomputation with explicit stability controls backed by error propagation analysis. It further introduces selective computation that restricts execution to the active frame interval. On MAGI-1 and SkyReels-V2, SCOPE achieves up to 4.73x speedup while maintaining quality comparable to the original output, outperforming all training-free baselines.

Hanshuai Cui, Zhiqing Tang, Zhi Yao +3

School of Artificial Intelligence, Beijing Normal University, Beijing, China · Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China · Shenzhen University of Advanced Technology, Shenzhen, China

Autoregressive Video GenerationDiffusion Model Inference AccelerationVideo Diffusion Models
AskPDF
Apr 3, 2026

Generative AI for Video Trailer Synthesis: From Extractive Heuristics to Autoregressive Creativity

The domain of automatic video trailer generation is currently undergoing a profound paradigm shift, transitioning from heuristic-based extraction methods to deep generative synthesis. While early methodologies relied heavily on low-level feature engineering, visual saliency, and rule-based heuristics to select representative shots, recent advancements in Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), and diffusion-based video synthesis have enabled systems that not only identify key moments but also construct coherent, emotionally resonant narratives. This survey provides a comprehensive technical review of this evolution, with a specific focus on generative techniques including autoregressive Transformers, LLM-orchestrated pipelines, and text-to-video foundation models like OpenAI's Sora and Google's Veo. We analyze the architectural progression from Graph Convolutional Networks (GCNs) to Trailer Generation Transformers (TGT), evaluate the economic implications of automated content velocity on User-Generated Content (UGC) platforms, and discuss the ethical challenges posed by high-fidelity neural synthesis. By synthesizing insights from recent literature, this report establishes a new taxonomy for AI-driven trailer generation in the era of foundation models, suggesting that future promotional video systems will move beyond extractive selection toward controllable generative editing and semantic reconstruction of trailers.

Abhishek Dharmaratnakar, Srivaths Ranganathan, Debanshu Das +1

Video GenerationT2V GenerationControllable Video GenerationAutoregressive Video GenerationVideo Diffusion Models
AskPDF
Mar 26, 2026

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables interactive storytelling and efficient on-the-fly frame generation. By reformulating the task as next-shot generation conditioned on historical context, ShotStream allows users to dynamically instruct ongoing narratives via streaming prompts. We achieve this by first fine-tuning a text-to-video model into a bidirectional next-shot generator, which is then distilled into a causal student via Distribution Matching Distillation. To overcome the challenges of inter-shot consistency and error accumulation inherent in autoregressive generation, we introduce two key innovations. First, a dual-cache memory mechanism preserves visual coherence: a global context cache retains conditional frames for inter-shot consistency, while a local context cache holds generated frames within the current shot for intra-shot consistency. And a RoPE discontinuity indicator is employed to explicitly distinguish the two caches to eliminate ambiguity. Second, to mitigate error accumulation, we propose a two-stage distillation strategy. This begins with intra-shot self-forcing conditioned on ground-truth historical shots and progressively extends to inter-shot self-forcing using self-generated histories, effectively bridging the train-test gap. Extensive experiments demonstrate that ShotStream generates coherent multi-shot videos with sub-second latency, achieving 16 FPS on a single GPU. It matches or exceeds the quality of slower bidirectional models, paving the way for real-time interactive storytelling. Training and inference code, as well as the models, are available on our

Yawen Luo, Xiaoyu Shi, Junhao Zhuang +5

MMLab, CUHK · Kuaishou Technology · CPII under InnoHK

Multi-Shot Video GenerationStreaming Video GenerationReal-Time Interactive Video GenerationAutoregressive Video GenerationMemory-Augmented Video Generation
AskPDF
Mar 26, 2026

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these challenges, we present PackForcing, a unified framework that efficiently manages the generation history through a novel three-partition KV-cache strategy. Specifically, we categorize the historical context into three distinct types: (1) Sink tokens, which preserve early anchor frames at full resolution to maintain global semantics; (2) Mid tokens, which achieve a massive spatiotemporal compression (32x token reduction) via a dual-branch network fusing progressive 3D convolutions with low-resolution VAE re-encoding; and (3) Recent tokens, kept at full resolution to ensure local temporal coherence. To strictly bound the memory footprint without sacrificing quality, we introduce a dynamic top-kk context selection mechanism for the mid tokens, coupled with a continuous Temporal RoPE Adjustment that seamlessly re-aligns position gaps caused by dropped tokens with negligible overhead. Empowered by this principled hierarchical context compression, PackForcing can generate coherent 2-minute, 832x480 videos at 16 FPS on a single H200 GPU. It achieves a bounded KV cache of just 4 GB and enables a remarkable 24x temporal extrapolation (5s to 120s), operating effectively either zero-shot or trained on merely 5-second clips. Extensive results on VBench demonstrate state-of-the-art temporal consistency (26.07) and dynamic degree (56.25), proving that short-video supervision is sufficient for high-quality, long-video synthesis. https://github.com/ShandaAI/PackForcing

Xiaofeng Mao, Shaohao Rui, Kaining Ying +4

Alaya Studio, Shanda AI Research Tokyo · Fudan University · Shanghai Innovation Institute

Long Video GenerationVideo Diffusion ModelsAutoregressive Video GenerationKV-Cache CompressionTemporal Consistency in Video Generation
AskPDF
Mar 25, 2026

DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation

Long-trajectory video generation is a crucial yet challenging task for world modeling primarily due to the limited scalability of existing video diffusion models (VDMs). Autoregressive models, while offering infinite rollout, suffer from visual drift and poor controllability. To address these issues, we propose DCARL, a novel divide-and-conquer, autoregressive framework that effectively combines the structural stability of the divide-and-conquer scheme with the high-fidelity generation of VDMs. Our approach first employs a dedicated Keyframe Generator trained without temporal compression to establish long-range, globally consistent structural anchors. Subsequently, an Interpolation Generator synthesizes the dense frames in an autoregressive manner with overlapping segments, utilizing the keyframes for global context and a single clean preceding frame for local coherence. Trained on a large-scale internet long trajectory video dataset, our method achieves superior performance in both visual quality (lower FID and FVD) and camera adherence (lower ATE and ARE) compared to state-of-the-art autoregressive and divide-and-conquer baselines, demonstrating stable and high-fidelity generation for long trajectory videos up to 32 seconds in length.

Junyi Ouyang, Wenbin Teng, Gonglin Chen +2

Institute for Creative Technologies · University of Southern California

Long-Horizon Video GenerationAutoregressive Video GenerationControllable Video GenerationVideo Diffusion Models
AskPDF
Mar 22, 2026

Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation

Autoregressive video diffusion has recently emerged as a promising paradigm for long-video generation, enabling causal synthesis beyond the temporal limits of bidirectional models. Existing forcing-based training strategies reduce exposure bias by conditioning models on their own predictions during rollout, yet minute-scale generation remains challenging due to progressive temporal degradation and constrained motion evolution. In this work, we study the role of temporal KV memory during long-horizon autoregressive inference. Our analysis shows that simply retaining more historical frames does not consistently improve generation quality; instead, both the quantity and temporal placement of memory strongly affect motion dynamics. These findings suggest that temporal memory should be treated as structured context rather than a homogeneous chronological buffer. Motivated by this observation, we introduce Relax Forcing, a training-free memory mechanism for autoregressive video diffusion. Relax Forcing decomposes temporal context into three functional components: Sink frames that provide global stability, Tail frames that preserve short-term continuity, and dynamically selected History frames that supply mid-range motion structure. History frames are selected using a relaxation-based criterion that encourages alignment with global anchors while suppressing redundancy with recent context. This role-aware sparse memory design mitigates error accumulation during long-horizon rollout while preserving motion evolution and reducing attention overhead. Experiments on VBench-Long show that Relax Forcing improves long-video generation, achieving stronger motion dynamics and higher overall scores than existing autoregressive baselines. These results indicate that structured temporal memory is an effective and complementary direction for scalable long-video generation.

Zengqun Zhao, Yanzuo Lu, Ziquan Liu +3

Queen Mary University of London · Imperial College London · Huawei R&D UK

Long-Horizon Video GenerationAutoregressive Video GenerationMemory-Augmented Video GenerationTemporal Consistency in Video GenerationKV-Cache Management
AskPDF
Mar 19, 2026

EARTalking: End-to-end GPT-style Autoregressive Talking Head Synthesis with Frame-wise Control

Audio-driven talking head generation aims to create vivid and realistic videos from a static portrait and speech. Existing AR-based methods rely on intermediate facial representations, which limit their expressiveness and realism. Meanwhile, diffusion-based methods generate clip-by-clip, lacking fine-grained control and causing inherent latency due to overall denoising across the window. To address these limitations, we propose EARTalking, a novel end-to-end, GPT-style autoregressive model for interactive audio-driven talking head generation. Our method introduces a novel frame-by-frame, in-context, audio-driven streaming generation paradigm. For inherently supporting variable-length video generation with identity consistency, we propose the Sink Frame Window Attention (SFA) mechanism. Furthermore, to avoid the complex, separate networks that prior works required for diverse control signals, we propose a streaming Frame Condition In-Context (FCIC) scheme. This scheme efficiently injects diverse control signals in a streaming, in-context manner, enabling interactive control at every frame and at arbitrary moments. Experiments demonstrate that EARTalking outperforms existing autoregressive methods and achieves performance comparable to diffusion-based methods. Our work demonstrates the feasibility of in-context streaming autoregressive control, unlocking a scalable direction for flexible, efficient generation. The code will be released for reproducibility.

Yuzhe Weng, Haotian Wang, Yuanhong Yu +4

University of Science and Technology of China · Zhejiang University · iFLYTEK

Talking Head GenerationControllable Video GenerationReal-Time Interactive Video GenerationAutoregressive Video GenerationStreaming Video Generation
AskPDF
Mar 18, 2026

AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization

Streaming autoregressive (AR) video generators combined with few-step distillation achieve low-latency, high-quality synthesis, yet remain difficult to align via reinforcement learning from human feedback (RLHF). Existing SDE-based GRPO methods face challenges in this setting: few-step ODEs and consistency model samplers deviate from standard flow-matching ODEs, and their short, low-stochasticity trajectories are highly sensitive to initialization noise, rendering intermediate SDE exploration ineffective. We propose AR-CoPO (AutoRegressive Contrastive Policy Optimization), a framework that adapts the Neighbor GRPO contrastive perspective to streaming AR generation. AR-CoPO introduces chunk-level alignment via a forking mechanism that constructs neighborhood candidates at a randomly selected chunk, assigns sequence-level rewards, and performs localized GRPO updates. We further propose a semi-on-policy training strategy that complements on-policy exploration with exploitation over a replay buffer of reference rollouts, improving generation quality across domains. Experiments on Self-Forcing demonstrate that AR-CoPO improves both out-of-domain generalization and in-domain human preference alignment over the baseline, providing evidence of genuine alignment rather than reward hacking.

Dailan He, Guanlin Feng, Xingtong Ge +5

CUHK MMLab, China · Vivix Group Limited, China · HKUST, China +1

RL for Video GenerationStreaming Video GenerationPolicy OptimizationRL for Generative ModelsAutoregressive Video Generation
AskPDF
Mar 17, 2026

Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures, typically requiring either expensive re-distillation or solver-coupled reverse-process optimization that introduces considerable memory and computational overhead. We present Astrolabe, an efficient online RL framework tailored for distilled AR models. To overcome existing bottlenecks, we introduce a forward-process RL formulation based on negative-aware fine-tuning. By contrasting positive and negative samples directly at inference endpoints, this approach establishes an implicit policy improvement direction without requiring reverse-process unrolling. To scale this alignment to long videos, we propose a streaming training scheme that generates sequences progressively via a rolling KV-cache, applying RL updates exclusively to local clip windows while conditioning on prior context to ensure long-range coherence. Finally, to mitigate reward hacking, we integrate a multi-reward objective stabilized by uncertainty-aware selective regularization and dynamic reference updates. Extensive experiments demonstrate that our method consistently enhances generation quality across multiple distilled AR video models, serving as a robust and scalable alignment solution.

Songchun Zhang, Zeyue Xue, Siming Fu +6

HKUST · JD Explore Academy · HKU

RL for Video GenerationAutoregressive Video GenerationAI Alignment
AskPDF
Mar 16, 2026

FAR-Drive: Frame-AutoRegressive Video Generation in Closed-Loop Autonomous Driving

Despite rapid progress in autonomous driving, reliable training and evaluation of driving systems remain fundamentally constrained by the lack of scalable and interactive simulation environments. Recent generative video models achieve remarkable visual fidelity, yet most operate in open-loop settings and fail to support fine-grained frame-level interaction between agent actions and environment evolution. Building a learning-based closed-loop simulator for autonomous driving poses three major challenges: maintaining long-horizon temporal and cross-view consistency, mitigating autoregressive degradation under iterative self-conditioning, and satisfying low-latency inference constraints. In this work, we propose FAR-Drive, a frame-level autoregressive video generation framework for autonomous driving. We introduce a multi-view diffusion transformer with fine-grained structured control, enabling geometrically consistent multi-camera generation. To address long-horizon consistency and iterative degradation, we design a two-stage training strategy consisting of adaptive reference horizon conditioning and blend-forcing autoregressive training, which progressively improves consistency and robustness under self-conditioning. To meet low-latency interaction requirements, we further integrate system-level efficiency optimizations for inference acceleration. Experiments on the nuScenes dataset demonstrate that our method achieves state-of-the-art performance among existing closed-loop autonomous driving simulation approaches, while maintaining sub-second latency on a single GPU.

Yaoru Li, Federico Landi, Marco Godi +6

Zhejiang University · Huawei

Autonomous Driving SimulationAutoregressive Video GenerationTemporal Consistency in Video GenerationMulti-View Video Generation
AskPDF
Mar 12, 2026

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation computational cost. Traditional video tokenizers apply a uniform token assignment across temporal blocks of different videos, often wasting tokens on simple, static, or repetitive segments while underserving dynamic or complex ones. To address this inefficiency, we introduce EVATok\textbf{EVATok}, a framework to produce E\textbf{E}fficient V\textbf{V}ideo A\textbf{A}daptive Tok\textbf{Tok}enizers. Our framework estimates optimal token assignments for each video to achieve the best quality-cost trade-off, develops lightweight routers for fast prediction of these optimal assignments, and trains adaptive tokenizers that encode videos based on the assignments predicted by routers. We demonstrate that EVATok delivers substantial improvements in efficiency and overall quality for video reconstruction and downstream AR generation. Enhanced by our advanced training recipe that integrates video semantic encoders, EVATok achieves superior reconstruction and state-of-the-art class-to-video generation on UCF-101, with at least 24.4% savings in average token usage compared to the prior state-of-the-art LARP and our fixed-length baseline.

Tianwei Xiong, Jun Hao Liew, Zilong Huang +3

The University of Hong Kong · ByteDance Seed

Video Token CompressionVisual Token CompressionAutoregressive Video GenerationVisual Autoregressive Models
AskPDF
Mar 12, 2026

OmniForcing: Unleashing Real-time Joint Audio-Visual Generation

Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency due to their bidirectional attention dependencies, hindering real-time applications. We propose OmniForcing, the first framework to distill an offline, dual-stream bidirectional diffusion model into a high-fidelity streaming autoregressive generator. However, naively applying causal distillation to such dual-stream architectures triggers severe training instability, due to the extreme temporal asymmetry between modalities and the resulting token sparsity. We address the inherent information density gap by introducing an Asymmetric Block-Causal Alignment with a zero-truncation Global Prefix that prevents multi-modal synchronization drift. The gradient explosion caused by extreme audio token sparsity during the causal shift is further resolved through an Audio Sink Token mechanism equipped with an Identity RoPE constraint. Finally, a Joint Self-Forcing Distillation paradigm enables the model to dynamically self-correct cumulative cross-modal errors from exposure bias during long rollouts. Empowered by a modality-independent rolling KV-cache inference scheme, OmniForcing achieves state-of-the-art streaming generation at ∼\sim25 FPS on a single GPU, maintaining multi-modal synchronization and visual quality on par with the bidirectional teacher.Project Page: https://omniforcing.com

Yaofeng Su, Yuming Li, Zeyue Xue +7

JD Explore Academy · Fudan University · Peking University +1

Audio-Video GenerationStreaming Video GenerationDiffusion Model DistillationAutoregressive Video GenerationAudio-Visual Synchronization
AskPDF
Mar 10, 2026

Streaming Autoregressive Video Generation via Diagonal Distillation

Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but require heavy computation to achieve high fidelity. Diffusion distillation can compress these models into efficient few-step variants, but existing video distillation approaches largely adapt image-specific methods that neglect temporal dependencies. These techniques often excel in image generation but underperform in video synthesis, exhibiting reduced motion coherence, error accumulation over long sequences, and a latency-quality trade-off. We identify two factors that result in these limitations: insufficient utilization of temporal context during step reduction and implicit prediction of subsequent noise levels in next-chunk prediction (i.e., exposure bias). To address these issues, we propose Diagonal Distillation, which operates orthogonally to existing approaches and better exploits temporal information across both video chunks and denoising steps. Central to our approach is an asymmetric generation strategy: more steps early, fewer steps later. This design allows later chunks to inherit rich appearance information from thoroughly processed early chunks, while using partially denoised chunks as conditional inputs for subsequent synthesis. By aligning the implicit prediction of subsequent noise levels during chunk generation with the actual inference conditions, our approach mitigates error propagation and reduces oversaturation in long-range sequences. We further incorporate implicit optical flow modeling to preserve motion quality under strict step constraints. Our method generates a 5-second video in 2.61 seconds (up to 31 FPS), achieving a 277.3x speedup over the undistilled model.

Jinxiu Liu, Xuanming Liu, Kangfu Mei +3

South China University of Technology · Westlake University · Johns Hopkins University +2

Streaming Video GenerationAutoregressive Video GenerationDiffusion Model DistillationDiffusion Model AccelerationTemporal Consistency in Video Generation
AskPDF
Mar 9, 2026

HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising

Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity while preventing the progressive quality degradation caused by error accumulation. To ensure continuity, existing methods typically condition on highly denoised contexts; yet, this practice propagates prediction errors with high certainty, thereby exacerbating degradation. In this paper, we argue that a highly clean context is unnecessary. Drawing inspiration from bidirectional diffusion models, which denoise frames at a shared noise level while maintaining coherence, we propose that conditioning on context at the same noise level as the current block provides sufficient signal for temporal consistency while effectively mitigating error propagation. Building on this insight, we propose HiAR, a hierarchical denoising framework that reverses the conventional generation order: instead of completing each block sequentially, it performs causal generation across all blocks at every denoising step, so that each block is always conditioned on context at the same noise level. This hierarchy naturally admits pipelined parallel inference, yielding a 1.8 wall-clock speedup in our 4-step setting. We further observe that self-rollout distillation under this paradigm amplifies a low-motion shortcut inherent to the mode-seeking reverse-KL objective. To counteract this, we introduce a forward-KL regulariser in bidirectional-attention mode, which preserves motion diversity for causal inference without interfering with the distillation loss. On VBench (20s generation), HiAR achieves the best overall score and the lowest temporal drift among all compared methods.

Kai Zou, Dian Zheng, Hongbo Liu +3

University of Science and Technology of China · Anhui Province Key Laboratory of Digital Security, USTC · The Chinese University of Hong Kong +2

Autoregressive Video GenerationLong-Horizon Video GenerationTemporal Consistency in Video GenerationDiffusion Model Inference Acceleration
AskPDF
Mar 7, 2026

FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis

Visual Autoregressive modeling (VAR) has emerged as a highly efficient alternative to diffusion-based frameworks, achieving comparable synthesis quality. However, as this paradigm extends to Spacetime Autoregressive modeling (STAR) for video generation, scaling resolution and frame counts leads to a "token explosion" that creates a massive computational bottleneck in the final refinement stages. To address this, we propose FastSTAR, a training-free acceleration framework designed for high-quality video generation. Our core method, Spatiotemporal Token Pruning, identifies essential tokens by integrating two specialized terms: (1) Spatial similarity, which evaluates structural convergence across hierarchical scales to skip computations in regions where further refinement becomes redundant, and (2) Temporal similarity, which identifies active motion trajectories by assessing feature-level variations relative to the preceding clip. Combined with a Partial Update mechanism, FastSTAR ensures that only non-converged regions are refined, maintaining fluid motion while bypassing redundant computations. Experimental results on InfinityStar demonstrate that FastSTAR achieves up to a 2.01x speedup with a PSNR of 28.29 and less than 1% performance degradation, proving a superior efficiency-quality trade-off for STAR-based video synthesis.

Sungwoong Yune, Suheon Jeong, Joo-Young Kim

Korea Advanced Institute of Science and Technology

Video GenerationAutoregressive Video GenerationToken PruningVisual Token Pruning
AskPDF
Mar 4, 2026

Helios: Real Real-Time Long Video Generation Model

We introduce Helios, the first 14B video generation model that runs at 19.5 FPS on a single NVIDIA H100 GPU and supports minute-scale generation while matching the quality of a strong baseline. We make breakthroughs along three key dimensions: (1) robustness to long-video drifting without commonly used anti-drifting heuristics such as self-forcing, error-banks, or keyframe sampling; (2) real-time generation without standard acceleration techniques such as KV-cache, sparse/linear attention, or quantization; and (3) training without parallelism or sharding frameworks, enabling image-diffusion-scale batch sizes while fitting up to four 14B models within 80 GB of GPU memory. Specifically, Helios is a 14B autoregressive diffusion model with a unified input representation that natively supports T2V, I2V, and V2V tasks. To mitigate drifting in long-video generation, we characterize typical failure modes and propose simple yet effective training strategies that explicitly simulate drifting during training, while eliminating repetitive motion at its source. For efficiency, we heavily compress the historical and noisy context and reduce the number of sampling steps, yielding computational costs comparable to -- or lower than -- those of 1.3B video generative models. Moreover, we introduce infrastructure-level optimizations that accelerate both inference and training while reducing memory consumption. Extensive experiments demonstrate that Helios consistently outperforms prior methods on both short- and long-video generation. We plan to release the code, base model, and distilled model to support further development by the community.

Shenghai Yuan, Yuanyang Yin, Zongjian Li +3

Peking University · ByteDance China · Chengdu Anu Intelligence +1

Efficient Video GenerationLong-Horizon Video GenerationVideo Diffusion ModelsAutoregressive Video GenerationReal-Time Interactive Video GenerationTemporal Consistency in Video Generation+1
AskPDF
Mar 4, 2026

CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video

Generating high-quality 360° panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially important for immersive experience. Existing methods are constrained by computational limitations of vanilla diffusion models, only supporting ≤\leq 1K resolution native generation and relying on suboptimal post super-resolution to increase resolution. We introduce CubeComposer, a novel spatio-temporal autoregressive diffusion model that natively generates 4K-resolution 360° videos. By decomposing videos into cubemap representations with six faces, CubeComposer autoregressively synthesizes content in a well-planned spatio-temporal order, reducing memory demands while enabling high-resolution output. Specifically, to address challenges in multi-dimensional autoregression, we propose: (1) a spatio-temporal autoregressive strategy that orchestrates 360° video generation across cube faces and time windows for coherent synthesis; (2) a cube face context management mechanism, equipped with a sparse context attention design to improve efficiency; and (3) continuity-aware techniques, including cube-aware positional encoding, padding, and blending to eliminate boundary seams. Extensive experiments on benchmark datasets demonstrate that CubeComposer outperforms state-of-the-art methods in native resolution and visual quality, supporting practical VR application scenarios. Project page: https://lg-li.github.io/project/cubecomposer

Lingen Li, Guangzhi Wang, Xiaoyu Li +5

The Chinese University of Hong Kong · ARC Lab, Tencent PCG

High-Resolution Video GenerationVideo GenerationVideo Diffusion ModelsAutoregressive Video Generation
AskPDF
Mar 2, 2026

StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models

Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales predominantly refine high-frequency textures and exhibit substantial spatial redundancy, in contrast to earlier scales that determine the global structural layout. Existing pruning methods primarily focus on high-frequency detection for token selection, often overlooking structural coherence and consequently degrading global semantics. To address this limitation, we propose StepVAR, a training-free token pruning framework that accelerates VAR inference by jointly considering structural and textural importance. Specifically, we employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information. This dual-criterion design enables the model to retain tokens critical for both fine-grained fidelity and overall composition. To maintain valid next-scale prediction under sparse tokens, we further introduce a nearest neighbor feature propagation strategy to reconstruct dense feature maps from pruned representations. Extensive experiments on state-of-the-art text-to-image and text-to-video VAR models demonstrate that StepVAR achieves substantial inference speedups while maintaining generation quality. Quantitative and qualitative evaluations consistently show that our method outperforms existing acceleration approaches, validating its effectiveness and general applicability across diverse VAR architectures.

Keli Liu, Zhendong Wang, Wengang Zhou +1

University of Science and Technology of China

Inference AccelerationVisual Autoregressive ModelsVisual Token PruningAutoregressive Image GenerationAutoregressive Video Generation
AskPDF
Mar 2, 2026

Accelerating Video Generation Inference with Sequential-Parallel 3D Positional Encoding Using a Global Time Index

Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism leads to explosive O(N^2) memory consumption and high first-frame latency. To address these issues, we implement system-level inference optimizations for a causal autoregressive video generation pipeline. We adapt the Self-Forcing causal autoregressive framework to sequence parallel inference and implement a sequence-parallel variant of the causal rotary position embedding which we refer to as Causal-RoPE SP. This adaptation enables localized computation and reduces cross-rank communication in sequence parallel execution. In addition, computation and communication pipelines are optimized through operator fusion and RoPE precomputation. Experiments conducted on an eight GPU A800 cluster show that the optimized system achieves comparable generation quality, sub-second first-frame latency, and near real-time inference speed. For generating five second 480P videos, a 1.58x speedup is achieved, thereby providing effective support for real-time interactive applications.

Chao Yuan, Pan Li

Diffusion Model Inference AccelerationAutoregressive Video GenerationDiffusion TransformerRotary Positional Embeddings
AskPDF
Feb 28, 2026

ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models

Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-observed areas. Methods that leverage generative priors to correct artifacts in these areas hold promise but currently suffer from two shortcomings. The first is scalability, as existing methods use image diffusion models or bidirectional video models that are limited in the number of views they can generate in a single pass (and thus require a costly iterative distillation process for consistency). The second is quality itself, as generators used in prior work tend to produce outputs that are inconsistent with existing scene content and fail entirely in completely unobserved regions. To solve these, we propose a two-stage pipeline that leverages two key insights. First, we train a powerful bidirectional generative model with a novel opacity mixing strategy that encourages consistency with existing observations while retaining the model's ability to extrapolate novel content in unseen areas. Second, we distill it into a causal auto-regressive model that generates hundreds of frames in a single pass. This model can directly produce novel views or serve as pseudo-supervision to improve the underlying 3D representation in a simple and highly efficient manner. We evaluate our method extensively and demonstrate that it can generate plausible reconstructions in scenarios where existing approaches fail completely. When measured on commonly benchmarked datasets, we outperform all existing baselines by a wide margin, exceeding prior state-of-the-art methods by 1-3 dB PSNR.

Riccardo de Lutio, Tobias Fischer, Yen-Yu Chang +7

NVIDIA, USA · NVIDIA, Switzerland · ETHZ, Switzerland +4

3D ReconstructionNovel View Synthesis3D Scene Completion3D Gaussian SplattingAutoregressive Video Generation
AskPDF
Feb 25, 2026

FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video Generation

Generating realistic talking-head videos remains challenging due to persistent issues such as imperfect lip synchronization, unnatural motion, and evaluation metrics that correlate poorly with human perception. We propose FlowPortrait, a reinforcement-learning framework for audio-driven portrait animation built on a multimodal backbone for autoregressive audio-to-video generation. FlowPortrait introduces a human-aligned evaluation system based on Multimodal Large Language Models (MLLMs) to assess lip-sync accuracy, expressiveness, and motion quality. These signals are combined with perceptual and temporal consistency regularizers to form a stable composite reward, which is used to post-train the generator via Group Relative Policy Optimization (GRPO). Extensive experiments, including both automatic evaluations and human preference studies, demonstrate that FlowPortrait consistently produces higher-quality talking-head videos, highlighting the effectiveness of reinforcement learning for portrait animation.

Weiting Tan, Andy T. Liu, Ming Tu +3

ByteDance Seed · Johns Hopkins University

Audio-Driven Facial AnimationAudio-Video GenerationRL for Video GenerationAutoregressive Video GenerationVideo Generation Evaluation
AskPDF
Feb 25, 2026

Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context

Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory for consistency, or iterative 3D reconstruction and inpainting, which accumulate errors during inference due to incorrect intermediary outputs, non-differentiable processes, and separate models. To overcome these limitations, we introduce ``geometry-as-context". It iteratively completes the following steps using an autoregressive camera-controlled video generation model: (1) estimates the geometry of the current view necessary for 3D reconstruction, and (2) simulates and restores novel view images rendered by the 3D scene. Under this multi-task framework, we develop the camera gated attention module to enhance the model's capability to effectively leverage camera poses. During the training phase, text contexts are utilized to ascertain whether geometric or RGB images should be generated. To ensure that the model can generate RGB-only outputs during inference, the geometry context is randomly dropped from the interleaved text-image-geometry training sequence. The method has been tested on scene video generation with one-direction and forth-and-back trajectories. The results show its superiority over previous approaches in maintaining scene consistency and camera control.

JiaKui Hu, Jialun Liu, Liying Yang +7

Institute of Medical Technology, Peking University · TeleAI · MUST

3D-Aware Video GenerationCamera-Controlled Video GenerationGeometric Consistency in Video GenerationCamera-Conditioned Video GenerationTemporal Consistency in Video GenerationAutoregressive Video Generation
AskPDF
Feb 24, 2026

RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space

World foundation models aim to simulate the evolution of the real world with physically plausible behavior. Unlike prior methods that handle spatial and temporal correlations separately, we propose RAYNOVA, a geometry-agonistic multiview world model for driving scenarios that employs a dual-causal autoregressive framework. It follows both scale-wise and temporal topological orders in the autoregressive process, and leverages global attention for unified 4D spatio-temporal reasoning. Different from existing works that impose strong 3D geometric priors, RAYNOVA constructs an isotropic spatio-temporal representation across views, frames, and scales based on relative Plücker-ray positional encoding, enabling robust generalization to diverse camera setups and ego motions. We further introduce a recurrent training paradigm to alleviate distribution drift in long-horizon video generation. RAYNOVA achieves state-of-the-art multi-view video generation results on nuScenes, while offering higher throughput and strong controllability under diverse input conditions, generalizing to novel views and camera configurations without explicit 3D scene representation. Our code will be released at https://raynova-ai.github.io/.

Yichen Xie, Chensheng Peng, Mazen Abdelfattah +6

Applied Intuition · UC Berkeley

Multi-View Video GenerationWorld ModelsWorld Models for Autonomous DrivingVideo World ModelsAutoregressive Video GenerationLong-Horizon Video Generation
AskPDF
Feb 16, 2026

Adapting VACE for Real-Time Autoregressive Video Diffusion

We describe an adaptation of VACE (Video All-in-one Creation and Editing) for real-time autoregressive video generation. VACE provides unified video control (reference guidance, structural conditioning, inpainting, and temporal extension) but assumes bidirectional attention over full sequences, making it incompatible with streaming pipelines that require fixed chunk sizes and causal attention. The key modification moves reference frames from the diffusion latent space into a parallel conditioning pathway, preserving the fixed chunk sizes and KV caching that autoregressive models require. This adaptation reuses existing pretrained VACE weights without additional training. Across 1.3B and 14B model scales, VACE adds 20-30% latency overhead for structural control and inpainting, with negligible VRAM cost relative to the base model. Reference-to-video fidelity is severely degraded compared to batch VACE due to causal attention constraints. A reference implementation is available at https://github.com/daydreamlive/scope.

Ryan Fosdick

Daydream

Video Diffusion ModelsControllable Video GenerationAutoregressive Video GenerationStreaming Video GenerationDiffusion-Based Video Editing
AskPDF
Feb 8, 2026

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

Autoregressive (AR) video diffusion models in the Self Forcing family generate a video chunk by chunk, each conditioned on the ones before it, so they can keep rolling out with no preset length. In practice they are trained on short, fixed clips (e.g., 5s). Once a rollout passes this training horizon, the cache fills with self-generated chunks the model never saw in training, and quality degrades: colors oversaturate, identities drift, structures collapse, and motion fades. We frame this failure as a cache-behavior mismatch, a domain shift between the within-horizon caches seen in training and those produced by open-ended testing, and address it with Rolling Sink, a training-free inference-time cache policy. Within the base model's fixed cache budget, Rolling Sink holds the cache close to its stable within-horizon behavior: it restores low-drift content, sliding temporal indices, and evolving semantics, and keeps a small recent context. Attention sink and temporal re-indexing are existing mechanisms. Our contribution is the mismatch formulation, the joint bounded-cache policy, and the Rolling Semantics schedule. On two 5s-trained bases, Self Forcing and Causal Forcing, Rolling Sink attains the best averaged rank on VBench-Long at both 1- and 5-minute rollouts under the same inference setting, at about 0.56% throughput change, and holds GPU memory constant. It also sustains a 30-minute qualitative rollout, 360 times its training horizon. We validate at 1- and 5-minute rollouts and do not claim guaranteed quality at arbitrary duration. Project page: https://rolling-sink.github.io/

Haodong Li, Shaoteng Liu, Zhe Lin +1

UC San Diego · Adobe Research

Autoregressive DiffusionLong-Horizon Video GenerationDiffusion Model CachingAutoregressive Video GenerationTemporal Consistency in Video Generation
AskPDF
Dec 18, 2025

CustomX: Unified Character, Action, and Scene Customization in Video World Models

Recent advances in world models have greatly enhanced interactive environment simulation. Existing methods mainly fall into two categories: (1) static world generation models, which construct 3D environments without active agents, and (2) controllable-entity models, which allow a single entity to perform limited actions in an otherwise uncontrollable environment. In this work, we introduce CustomX, leveraging the realism and structural grounding of static world generation while extending controllable-entity models to support user-specified characters capable of performing open-ended actions. Users can provide a 3DGS scene and a character, then use natural language to direct the character to perform diverse behaviors, ranging from basic locomotion to object-centric interactions, while freely exploring the environment. CustomX synthesizes temporally coherent video clips that preserve visual fidelity with the provided scene and character, formulated as a conditional autoregressive video generation problem. Built upon a pre-trained video generator, our training strategy significantly enhances motion dynamics while maintaining generalization across actions and characters. Our evaluation covers a broad range of aspects, including visual quality, character consistency, action controllability, and long-horizon coherence.

Yitong Wang, Fangyun Wei, Hongyang Zhang +2

Fudan University · Microsoft Research · University of Waterloo +1

HOI GenerationAction-Conditioned Video GenerationVideo GenerationAutoregressive Video GenerationControllable Video GenerationVideo World Models
AskPDF
Dec 17, 2025

End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional teacher model or discriminator. To achieve an end-to-end solution, we introduce Resampling Forcing, a teacher-free framework that enables training autoregressive video models from scratch and at scale. Central to our approach is a self-resampling scheme that simulates inference-time model errors on history frames during training. Conditioned on these degraded histories, a sparse causal mask enforces temporal causality while enabling parallel training with frame-level diffusion loss. To facilitate efficient long-horizon generation, we further introduce history routing, a parameter-free mechanism that dynamically retrieves the top-k most relevant history frames for each query. Experiments demonstrate that our approach achieves performance comparable to distillation-based baselines while exhibiting superior temporal consistency on longer videos owing to native-length training.

Yuwei Guo, Ceyuan Yang, Hao He +5

The Chinese University of Hong Kong, Hong Kong, China · ByteDance Seed, China · ByteDance, China

Video Diffusion ModelsAutoregressive DiffusionLong-Horizon Video GenerationAutoregressive GenerationAutoregressive Video GenerationTemporal Consistency in Video Generation
AskPDF
Nov 28, 2025

BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation

Long video generation is a critical step toward building realistic world models, requiring both high visual fidelity and long-range interaction consistency. Recent autoregressive diffusion models enable long-horizon generation through KV cache reuse, yet suffer from two fundamental challenges: failure to preserve long-range interactions due to sliding-window KV cache and error accumulation that progressively degrades generation quality over time. To address these issues, we propose BIFE, a framework that introduces a semantic sparse KV cache for retrieval-based long-range conditioning and a Block Forcing training strategy to enforce cross-block consistency. Together, these designs preserve historical interactions while mitigating drift, enabling stable and coherent minute-long video generation. We also introduce InterVBench, a minute-long video benchmark with fine-grained block-level annotations and Video Drift Error metrics. Extensive experiments on InterVBench and VBench-Long demonstrate that BIFE achieves state-of-the-art performance, including a 22.2% improvement on VDE-Subject and a 19.4% improvement on VDE-Clarity over baselines. Website: https://alibaba-damo-academy.github.io/BIFE. Code: https://github.com/alibaba-damo-academy/BIFE.

Zeyu Zhang, Jinyuan Mao, Shuning Chang +5

DAMO Academy, Alibaba Group · Zhejiang University · Hupan Lab

Long-Horizon Video GenerationAutoregressive Video GenerationTemporal Consistency in Video GenerationRetrieval-Augmented Video GenerationVideo Generation Evaluation
AskPDF
Aug 18, 2025

Matrix-game 2.0: An open-source, real-time, and streaming interactive world model

Recent advances in interactive video generations have demonstrated diffusion model's potential as world models by capturing complex physical dynamics and interactive behaviors. However, existing interactive world models depend on bidirectional attention and lengthy inference steps, severely limiting real-time performance. Consequently, they are hard to simulate real-world dynamics, where outcomes must update instantaneously based on historical context and current actions. To address this, we present Matrix-Game 2.0, an interactive world model generates long videos on-the-fly via few-step auto-regressive diffusion. Our framework consists of three key components: (1) A scalable data production pipeline for Unreal Engine and GTA5 environments to effectively produce massive amounts (about 1200 hours) of video data with diverse interaction annotations; (2) An action injection module that enables frame-level mouse and keyboard inputs as interactive conditions; (3) A few-step distillation based on the casual architecture for real-time and streaming video generation. Matrix Game 2.0 can generate high-quality minute-level videos across diverse scenes at an ultra-fast speed of 25 FPS. We open-source our model weights and codebase to advance research in interactive world modeling.

Xianglong He, Chunli Peng, Zexiang Liu +16

Skywork AI

Action-Conditioned Video GenerationReal-Time Interactive Video GenerationAction-Conditioned World ModelsStreaming Video GenerationAutoregressive Video GenerationInteractive World Models
AskPDF
Dec 4, 2024

Auto-Regressive Models Need Structural Registers: Semantic Foresight Improves Coherent Driving Video Continuation

Front-view driving video continuation is a critical component for constructing sophisticated world models. However, maintaining long-term coherence faces the fundamental challenge of mitigating ''generative degeneration'' during the auto-regressive process. This phenomenon arises when the limited attention capacity of world models becomes saturated with high-entropy pixel details over extended sequences, leading to a collapse of global scene structure and motion intensity. To address this, we introduce STRIDE (STructural RegIsters for Decoupled Extrapolation), a large vision model architecture with an enforced semantic foresight mechanism. STRIDE decouples video continuation into two sub-tasks via interleaved generation of semantic and RGB tokens: forecasting low-entropy semantic maps, and subsequently generating high-frequency visual appearance conditioned on this structure. The semantic tokens explicitly function as ''structural registers'' -- dedicated memory slots that robustly retain the scene's long-term context and world dynamics. Furthermore, we employ an architecturally decoupled flow matching-based super-resolution module to enhance the final visual fidelity. Extensive experiments in autonomous driving scenarios demonstrate that STRIDE effectively mitigates generative degeneration, achieving minute-level, temporally consistent driving video continuation with strong generalization ability.

Ruibo Ming, Jingwei Wu, Zhewei Huang +4

Tsinghua University · Megvii Technology · University of the Chinese Academy of Sciences +2

Video PredictionAutoregressive Video GenerationWorld Models for Autonomous DrivingTemporal Consistency in Video Generation
AskPDF