Autoregressive Video Generation

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

226 papers26 papers in the last four weeks, down 38% on the four weeks before. 0.2% of all new papers.

Oct 13, 2026

CineMem: Attention-Aligned Fine-grained Memory Retrieval for Multi-Shot Long Video Generation

Autoregressive video generation relies on memory retrieval to model long-range dependencies. This capability becomes particularly critical for multi-shot generation, where models must reconcile substantial visual changes across shot transitions with persistent semantic continuity. Existing methods tend to perform memory retrieval at the frame level and share the same historical context across all query tokens, overlooking the heterogeneous information needs and leading to redundant retrieval and inefficient use of historical memory. To bridge this gap, we introduce CineMem, an attention-aligned fine-grained memory retrieval framework that combines online memory organization with query-adaptive retrieval for autoregressive multi-shot video generation. Specifically, guided by intrinsic memory-access patterns revealed through attention analysis, we propose an online-clustered KV cache as a memory organization strategy over all historical tokens, enabling semantic-aware memory grouping and more precise retrieval. In addition, we introduce a query-level retrieval mechanism that provides broader access to historical information under a fixed retrieval budget, thereby improving long-term memory utilization. Together, these designs enable the multi-shot video generator to preserve long-range consistency across shot transitions, particularly in revisitation scenarios, while approximating full-memory access under a constrained memory budget. To facilitate evaluation, we further introduce a suite of task-specific, VLM-assisted metrics for faithful inter-shot consistency assessment. Extensive experiments demonstrate the effectiveness of our framework.
Oct 11, 2026

Frequency-Step Cache: Separating Synchronization and Repair for Efficient Autoregressive Video Diffusion

Autoregressive (AR) video generation enables long-horizon synthesis but requires repeated forward passes through large diffusion transformers. Training-free caching reduces this cost by reusing intermediate computation, yet existing controllers often couple two decisions: when to synchronize the cache exactly and how much computation to repair between synchronizations. We introduce Frequency-Step Cache (FSC), which separates these roles. FSC schedules exact full-computation anchors on a dense-to-sparse trajectory, while a lightweight latent-space risk based on frequency-resolved drift and token age controls inter-anchor repair through whole-step replay, selective token recomputation, or full repair. On SkyReels-V2, whole-step reuse provides most of the acceleration, while selective token computation is most effective as fidelity repair. A controlled ablation shows that using one reactive signal for both synchronization and repair reduces fidelity at matched latency, with the same separation advantage observed on FramePack and Matrix-Game. Across multiple autoregressive video backbones, FSC improves speed-quality trade-offs. On SkyReels-V2, FSC-Speed reaches 2.36x speedup versus MotionCache's 2.275x while improving SSIM by 0.019 and PSNR by 0.5 dB. At MotionCache-matched speed, FSC-Quality improves SSIM by 0.031 and PSNR by 1.0 dB and lowers LPIPS by 0.024. Without retuning, FSC-Quality transfers to SkyReels-V2 14B at 2.12x speedup versus 1.79x for MotionCache.
Oct 11, 2026

TempoKV: Predictive KV Cache Quantization for Autoregressive Video Generation

Autoregressive (AR) video diffusion models enable streaming generation of long videos but suffer from significant memory overhead due to the rapidly growing KV cache. Existing KV cache quantization methods are primarily designed for LLMs and transfer poorly to video models, where activations exhibit different statistics and strong spatiotemporal redundancy. We observe that the video KV cache is largely predictable over time, with a clear asymmetry. Keys are highly predictable from their temporal history, while values depend primarily on the current key and need a short history of preceding values. Based on these observations, we propose \method, a training-free predictive KV cache quantization framework for AR video generation. \method predicts keys and values according to their distinct dependencies and stores only the residuals at low precision. Both predictors are lightweight, calibrated once offline by linear regression on a small set of BF16 samples, and remain fixed across prompts and generation runs. Experiments on Self-Forcing, Causal Forcing, and LongCat-Video-13B show that \method consistently achieves higher generation quality than existing KV cache quantization methods at comparable or higher compression ratios, reaching up to 6.71×6.71\times KV cache compression with the best overall quality--efficiency tradeoff. Our code will be released on GitHub.
Oct 10, 2026

Demiurge: Forging Navigable 4D Worlds via Autoregressive Video Rerendering

Recent advances in video diffusion enable novel-view video synthesis from a single input video, supporting world modeling, embodied intelligence, and robotic simulation. However, existing methods process camera trajectories independently, lacking the cross-trajectory consistency needed for coherent, navigable 4D worlds. We introduce Demiurge, an autoregressive video rerendering pipeline built on a dynamic 4D point-cloud memory cache. It promotes cross-trajectory consistency through four components: (1) an appearance video diffusion model that synthesizes photorealistic novel-view videos conditioned on the 4D memory; (2) a memory-consistent video depth completion model that aligns known-region depths with cached geometry and completes missing regions, mitigating scale ambiguity and discontinuities during memory updates; (3) memory-aware dual-stream warping that provides high-fidelity visual guidance and occlusion cues for novel-view synthesis; and (4) geometry-aware video refinement that enhances perceptual quality. Extensive experiments demonstrate state-of-the-art performance and three key capabilities: coherent spatiotemporal lattice construction over dense multi-view trajectories; large-parallax video rerendering under challenging camera motions, including 180-degree rotations with no input-view overlap; and geometry-faithful outputs that can be directly optimized into high-quality 3D Gaussian Splatting representations with minimal artifacts. Project page: https://hanxinzhu-lab.github.io/demiurge_project_page/.
Oct 10, 2026

TGuide: Faster Autoregressive Video Diffusion via Historical Trajectory Guidance

Can autoregressive video diffusion be accelerated further when only four denoising steps remain? Existing feature caching approaches struggle in this regime, as large feature changes between denoising timesteps undermine both direct reuse and lightweight predictors. We observe that features across video chunks remain strongly correlated at matching denoising timesteps, offering a complementary source of guidance. Building on this insight, we introduce TGuide, a framework that accelerates autoregressive video diffusion through a lightweight Anchor-Transport-Correct (ATC) predictor guided by historical sampling trajectories. Our ATC combines two complementary references: the current chunk's preceding-step features preserve its spatial structure, while the previous chunk's same-timestep features provide information at the target denoising stage. By integrating these references through spatial retrieval and adaptive correction, ATC improves velocity prediction accuracy despite the large gaps between denoising steps. To mitigate error accumulation across both denoising steps and video chunks, we train the predictor on its own autoregressive rollouts, allowing it to adapt to states shaped by its own earlier predictions. An optional confidence-aware scheduler further adjusts the quality-efficiency trade-off. Experiments on Self Forcing, Causal Forcing, and HY-WorldPlay show that TGuide preserves generation quality while achieving denoising speedups of up to 1.89×1.89\times over the original 4-step generators. On Self Forcing, TGuide generalizes from 81-frame training videos to 333-frame generation, approximately four times the training length, while exceeding the original model's VBench score.
Oct 10, 2026

Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion

Autoregressive video generators synthesize long videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate future. This limited prediction horizon makes it challenging to maintain video quality over extended rollouts. To address this problem, we introduce Prospective Forcing, a multi-head prediction framework that injects long-range predictive signals into autoregressive video representations. Built on a rolling-window generator, Prospective Forcing attaches lightweight, offset-specific heads that share the same conditioning information and independently predict chunks at different future temporal offsets. By extending supervision beyond the next chunk, these heads encourage the shared history representation to retain information useful for longer-horizon prediction, supporting temporally consistent generation. At inference time, we accelerate sampling by using accepted future-chunk predictions to skip full-window backbone executions. We equip the head with learnable embeddings to generate multiple candidates for the next chunk, and a learned verifier either selects a candidate or rejects all and falls back to standard autoregressive generation.
Oct 10, 2026

FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation

In autoregressive video generation, retaining all historical key-value (KV) states increases memory usage and per-step attention costs as videos grow longer. A fixed cache budget bounds these costs but raises the challenge of preserving historical content that supports consistent, high-quality generation. Existing methods control cache size through history selection or consolidation, yet deciding what to retain and how to limit the loss of useful content remains a shared challenge. Our analysis shows that spatial queries depend on different historical content and that higher current attention coverage does not necessarily yield better long-video quality. We introduce FrameFold, a training-free KV cache consolidation method that compares the content retrieved by the same recent historical queries before and after merging to guide both representative construction and merge selection. Exploiting temporal redundancy between adjacent historical entries, FrameFold merges their KV states into shared representatives while retaining complete spatial grids. It fits value-merging coefficients in closed form by matching conditional attention responses, then selects the merge with the lowest remaining response distortion. Under matched KV cache budgets, experiments on Self Forcing and Causal Forcing at 30 and 60 seconds and on LongLive at 120 seconds demonstrate improved consistency and visual quality. Continuous eight-minute Self Forcing rollouts further show less quality degradation than the baselines.
Oct 10, 2026

Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation

Autoregressive video generation models generate videos sequentially, with each new block conditioned on previously generated blocks. By training on the model's own rollouts, Self Forcing and its follow-up methods substantially mitigate exposure bias caused by the mismatch between training- and inference-time history distributions. However, these models still suffer from error accumulation during long-horizon generation. We identify a key underlying limitation: the model remains highly sensitive to errors in its generated history, allowing small deviations to be amplified through subsequent generations. We refer to this underexplored problem as the local history robustness gap. To address this gap, we introduce Adversarial Gradient Forcing (AGF), a framework designed to improve the robustness of few-step autoregressive video models to perturbations and accumulated errors in their own generated histories. AGF uses distribution matching gradients from future block predictions to select adversarial perturbations of self-generated histories. It then jointly trains the generator on the original and perturbed histories to improve the robustness of future generation. Extensive experiments show that AGF achieves the highest VBench Total score on 60-second video generation and the best visual quality on four-minute video generation. Notably, AGF achieves such long-horizon robustness while requiring only 5-second rollouts for training.
Oct 9, 2026

Unified Generative Video Compression with Autoregressive and Bidirectional Video Diffusion

Video diffusion models can reconstruct visually compelling content from severely compressed representations at ultra-low bitrates, but they impose a rigid deployment trade-off. Bidirectional (BI) models achieve high quality through dense full-sequence attention, yet require the entire sequence before reconstruction and incur substantial latency. Autoregressive (AR) models enable low-delay streaming, but their restricted temporal context reduces compression efficiency. This tension is particularly relevant when a video stream must be decoded in real time yet is also stored for later, quality-oriented playback, making AR and BI models natural choices for the live and replay stages, respectively. To support both stages, we present UniGVC, a Unified Generative Video Codec that supports two decoding modes from a single bitstream. UniGVC-BI employs a BI-DiT with dense attention for quality-oriented random-access decoding, whereas UniGVC-AR uses windowed AR-DiT for low-delay streaming. Both paths share a hierarchical latent codec that recurrently produces the same conditions with ultra-low bitrates, allowing UniGVC-BI to serve as a conditional teacher for single-step distillation of UniGVC-AR. A tiny conditional video decoder further reduces streaming latency while preserving most of the reconstruction quality. On standard 1080p benchmarks, UniGVC-BI achieves the best overall rate-distortion-perception trade-off among the evaluated methods and produces temporally stable video at rates as low as 0.0005 bits per pixel. Meanwhile, UniGVC-AR remains competitive while decoding 1080p video at 36.85 FPS, over 250×250\times faster than UniGVC-BI. Code and models will be released later.
Oct 8, 2026

ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion

Autoregressive video diffusion models have become a leading approach to real-time interactive video generation and video world modeling. However, existing methods typically allocate computation uniformly across space when generating the next video chunk, updating all patches with the same denoising schedule and number of function evaluations. This ignores the spatial heterogeneity of video content: static, simple, or recurring regions are often easier to denoise, while other regions require further refinement or additional context. A uniform budget thus leads to redundant computation on easy patches, whereas reducing the fixed step count can leave difficult patches insufficiently refined. We introduce \methodname{}, a general framework that dynamically allocates denoising steps to individual patches: easy patches stop early to improve efficiency, while difficult patches receive more refinement steps. This design accelerates generation with negligible quality degradation. Our method is compatible with most existing few-step autoregressive diffusion models, requiring only a lightweight routing module with modest training. Experiments demonstrate that \methodname{} reduces the total number of denoising steps applied across video patches by about 50% while maintaining visual quality comparable to the four-step baseline.
Oct 8, 2026

Connected Self Forcing: Beyond Local Learning in Video Autoregression

To stream long videos while maintaining visual quality and temporal consistency, Self Forcing mitigates exposure bias through self-rollout training on self-generated histories with key-value (KV) caching. To keep memory manageable, it detaches historical caches, preserving forward dependencies between chunks but severing the backward gradient paths. We introduce Connected Self Forcing, a training framework that reconnects gradient paths across autoregressive chunks, allowing feedback from later predictions to guide how earlier context is generated. These connections go beyond historical KV-writing: gradients pass through generated latents into the computations that produced them, linking the generation of earlier context to its use in later predictions. To make this connected training memory-efficient, we develop shortcut gradient replay, which recovers cross-chunk gradients without retaining the full rollout computation graph. Integrated with distribution matching distillation, Connected Self Forcing trains historical chunks according to both their direct supervision and their contribution to subsequent generation. Experiments on autoregressive video generation show improvements in long-horizon visual quality and temporal consistency, without changing the inference procedure.
Oct 8, 2026

Memory Forcing: Attendable Mid-Horizon History for Streaming Video Generation

Autoregressive video diffusion enables causal video streaming without a bidirectional pass over the full clip, but existing few-step systems usually retain only the opening and most recent frames in a fixed-size KV cache. Once an event leaves this window, later frames can no longer attend to it, a failure we term mid-horizon forgetting. We present Memory Forcing, a few-step streaming method that preserves this missing history without increasing the cache size. Its Archive & Working Banks partition the cache into sink, archive, and working regions, retaining diverse intermediate events alongside recent motion under fixed memory. Because absolute temporal indices drift outside the training range, Bank-aware RoPE reassigns indices at attention time so each bank remains distinguishable. At 1.3B, Memory Forcing leads on longer clips, shows the smallest drop from 5s to 60s among methods reporting all four lengths, and preserves subjects and scenes through leave-and-return. The same design scales to Wan2.2 5B, producing more physically plausible, realistic, and dynamic videos and, to our knowledge, the first public 5B model on this forcing line.
Oct 8, 2026

Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher

Causal video diffusion models generate video autoregressively, which suits streaming, interactive, and long-video generation. Under standard training, however, they often yield lower generation quality than bidirectional models of the same size. Many existing approaches address this gap by initializing from or distilling a pretrained bidirectional teacher. We instead train a causal model from an image-model initialization, with no bidirectional video model at any stage. Because this path requires neither a large bidirectional teacher nor a complex distillation pipeline, it is simpler and more scalable. On this path, we find that a causal model trained on ground-truth history becomes strongly dependent on it, so that at inference errors in its own generated history propagate forward. We hypothesize that much of this dependence is unnecessary, because the current input already determines much of what the history provides. We propose Conditional Residual Prediction (CRP), a simple recipe for reducing a model's reliance on a condition: the model first predicts the target without the condition, and the condition may only add a residual on top of this prediction. Applied to history, CRP makes the model predict each chunk from the present as far as it can and use the past only for what the present cannot supply. In controlled experiments, CRP nearly closes the 6.14-point gap to a bidirectional model trained under the same setup. Scaling this recipe, we train Optica, a 2B-parameter causal video model that autoregressively generates 5-second 480p videos and reaches 82.78 on VBench with only about 15M training videos.
Oct 7, 2026

CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches

Autoregressive video diffusion models maintain a growing attention key-value (KV) cache, making memory a key bottleneck for long video generation. Recently, clustering-based quantization has emerged as an effective method to compress video KV caches by grouping similar key and value vectors then quantizing residual errors. However, when later frames attend to the compressed history, small reconstruction errors can compound as the video grows. Beyond the within-layer similarity exploited by clustering, we find strong dependencies across cache layers in video models. This motivates Coral-KV - Calibrated Offline, Residual-coded, and Adapted Locally - a KV-cache compression framework that uses cache states in each layer to predict keys and values in subsequent layers, then quantizes the remaining prediction residuals. We construct compact block-diagonal-plus-low-rank (block-DPLR) predictors: block-diagonal components model channel relationships within each attention head, while a global low-rank term models dependencies between heads. Coral-KV exposes a flexible fidelity-memory trade-off: it can reuse its predictors across videos or refit lightweight block-diagonal predictors to the current video for higher fidelity. Across extensive evaluations on both HY-WorldPlay and MAGI-1, our reusable configuration improves PSNR over QVG-4 by 0.32 dB and 4.95 dB, respectively, while using 48% and 37% less cache memory. Against QVG-Pro, our video-adapted configuration improves MAGI-1 PSNR by 3.77 dB while using 33.7% less cache memory. Coral-KV also maintains higher reconstruction fidelity over extended generation and reduces temporal discontinuities while retaining comparable generation latency.
Oct 7, 2026

SGF+: Decoupling Gradient Flows for Autoregressive Video Generation

Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typically share parameters, and we find that their gradients exhibit distinct patterns and systematic negative alignment, hindering the joint optimization of visual quality and temporal consistency. We introduce Self Gradient Forcing Plus (SGF+), which assigns separate parameters to context writing and denoising while preserving their interaction through causal attention. Both roles are jointly optimized using the original generation objective without auxiliary losses, with context writing supervised through its contribution to future predictions. This simple change improves visual quality and long-horizon consistency over the evaluated baselines in both framewise and chunkwise generation, without additional video training data or a longer training horizon. Trained on only 5s rollouts, SGF+ supports continuous generation for up to 24 hours without long-video fine-tuning. These results highlight role-specific parameterization as an effective design principle for high-quality autoregressive video generation and native long-horizon extrapolation.
Oct 7, 2026

Real-Time Joint Audio-Video Generation by Parallel Adapter Composition

Deploying a joint audio-video diffusion transformer for real-time, interactive generation normally requires two essential modifications: block-autoregressive attention, so frames can be emitted before the whole clip is finished, and few-step sampling, so each block is cheap. Conventionally, the streaming video literature obtains both capabilities from a chained pipeline. It first distills a bidirectional teacher into a causal student, then into a few-step one, or proceeds in reverse order. Each stage of such a chain fine-tunes the weights the previous one produced, so a later objective can undo an earlier capability. Following the idea of model merging, we show that on a packed audio-video backbone the two capabilities can be acquired in parallel. A causal adapter is trained against the frozen backbone, and an off-the-shelf few-step adapter provides the few-step capability. As the two edit different functional axes, we predict, and then verify, that their weight-update directions are near-orthogonal, without any explicit orthogonality constraint during training. Orthogonal updates should combine without interfering, so parallel composition is a direct sum. The two adapters are simply added at inference, with no joint training, yielding few-step, streaming audio-video whose image quality tracks the bidirectional teacher. Compared to the chained baselines, the composed model matches or beats them on most metrics, making parallel composition a practical approach. The resulting streaming system generates joint audio-video in real time, ≈\approx26 fps at 480×832480\times832 without quantization, and sustains 30 s of continuous generation with stable image quality. Demo Page: https://pac-demo-2027.github.io/demo/
Oct 2, 2026

ProAR: Learning Prospective Reasoning with Autoregressive Video Models

Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines them to a short-sighted, reactive paradigm. This limitation is particularly consequential for reasoning-oriented generation, where achieving a target outcome through valid intermediate states matters more than local visual plausibility. To address this challenge, we propose Learning Prospective Reasoning with Autoregressive Video Models (ProAR), a novel framework that transforms autoregressive video generation into a goal-oriented reasoning process. ProAR introduces two key components: (1) To anchor generation to the long-range outcome, we integrate goal-frame prediction into the autoregressive loop via an asymmetric attention mask, enabling the predicted goal frame to guide the generation of intermediate states without being disrupted by them. (2) To guide short-range transitions, we introduce future representation self-alignment to encourage current hidden states to anticipate upcoming temporal dynamics. By leveraging teacher-forcing in AR training, we extract clean future representations in a single forward pass and align current representations with them using a lightweight, training-only predictor. Together, these two mechanisms seamlessly combine explicit, sparse target supervision with implicit, dense step-wise guidance, promoting coherent, goal-directed reasoning progress with modest computational cost. Experiments show that ProAR's complementary components consistently improve performance across diverse visual reasoning benchmarks. The framework proves highly training-efficient, surpassing fully trained standard AR baselines using only 25% of the training steps. This paradigm also demonstrates promising applicability to embodied reasoning tasks.
Oct 2, 2026

In-Distribution Forcing for Long Video Generation at Test Time

Modern autoregressive (AR) video diffusion models excel at short-horizon video generation, yet generating long videos remains challenging due to drifting, where colors and textures shift, and motion dynamics decay. Existing works primarily rely on KV conditioning, which selects or modifies cached key-value (KV) entries to mitigate drifting. However, we observe that KV conditioning alone is insufficient as it assumes cached KV entries remain in-distribution. This assumption fails beyond the training horizon: nothing constrains the construction of KV entries during rollout, giving rise to the KV-provenance problem where cached entries themselves become out-of-distribution (OOD). To address this, we propose In-Distribution Forcing (ID-Forcing), a test-time framework that aligns both KV caching and KV conditioning with training configurations. Its key mechanism, self-caching, prevents OOD KV entries at their source. Each chunk is cached without attending to prior KV entry, keeping the rolling window exactly in-distribution. Consequently, ID-Forcing seamlessly extends short-horizon models to minute-scale video generation. Extensive evaluations show that our method remains competitive on standard video generation benchmark while substantially outperforming prior work in mitigating drifting, as validated by both our drift metrics and a user study.
Oct 2, 2026

Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation

Autoregressive video models can generate minute-long videos in real time, but they produce generic subjects from text rather than specific subjects from user-provided images. Existing customization methods either require costly per-subject optimization or use pretrained conditioning networks that jointly process all video frames with bidirectional attention. Neither approach is designed for causal streaming. We present Custom Forcing, a training-free method that stores reference-based anchor frames in the persistent KV cache of a frozen autoregressive video model. However, fixed anchors face two limitations: simple conditioning allows identity to drift, and the text prompt continues to favor a generic subject. To address these problems, drift-adaptive value amplification (DVA) scales reference influence with the degree of identity drift, while anchor contrast guidance (ACG) steers generation away from the generic class prior. Over two-minute rollouts, fixed anchors fall from 0.58 to 0.42 in DINO-I, while Custom Forcing keeps it between 0.58 and 0.62 without reducing motion. Custom Forcing also achieves higher subject similarity than bidirectional customization methods and better preserves identity over 30s than causal image-to-video and reference-to-video models, while generating each frame 9.5-28.5 times faster than these long-video baselines.
Oct 2, 2026

TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video Generation

Autoregressive (AR) video generation enables scalable long-video synthesis by sequentially generating fixed-length chunks, but incurs substantial computational cost from repeated denoising and attention over growing historical contexts. Recent cache reuse methods exploit temporal redundancy to reduce this cost, yet are mainly designed for single-trajectory generation, making them less suitable for sequentially coupled AR trajectories where approximation errors can accumulate and propagate across chunks. To address this challenge, we propose TRAC, a Trajectory-aware Reuse and Adaptive Correction framework for efficient and robust AR video generation. TRAC integrates three complementary components: (1) Robust Cumulative Scheduling (RCS), which selects cache reuse schedules by accounting for cumulative rollout errors and their variation across chunks and prompts; (2) Autoregressive Trajectory-aware Guidance Scheduling (ATGS), which coordinates classifier-free guidance refreshes along the global AR trajectory; and (3) Spectral Structure Correction (SSC), which adaptively restores low-frequency structural information to mitigate long-term error accumulation. By combining these innovations, TRAC substantially improves the efficiency-quality trade-off of AR video generation. For example, on VBench with SkyReels-V2, it achieves a 6.03x speedup over the vanilla model with only ~0.6% VBench score degradation, while consistently outperforming existing AR acceleration methods in both latency and generation quality. The code is publicly available at https://github.com/yolosjxhhhhhh/trac.
Oct 1, 2026

MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation

Long-horizon autoregressive video generation is limited by a finite context window. When an object or scene falls out of context, its fine-grained visual details may be lost and difficult to recover upon reappearance. To retain access to such visual details, we introduce MosaiChunk, a spatio-temporal memory mechanism that composes a mosaic of selected historical key-value (KV) entries across space and time. Our approach is motivated by the observation that a frozen video generator can directly consume such non-contiguous historical KV and recover the corresponding visual content. We therefore keep the generator fixed and learn only a lightweight router that determines which historical sections to include in the mosaic under a fixed active-memory budget. We further introduce RememBench, a benchmark of long-horizon revisits with prompt-driven text-to-video (T2V) and camera-driven image-to-video (I2V) splits. Our experiments show that MosaiChunk consistently improves revisit consistency over both sliding-window inference and whole-chunk retrieval under matched memory budgets, across both T2V and I2V settings.
Sep 30, 2026

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation

Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene tokenizer is paramount for the optimal performance of each of these, both in terms of fidelity and semantics. Flexible-length, coarse-to-fine tokenizers yield exactly that: the first coarse tokens carry the clip's global semantics while later tokens further specify details. Existing flexible tokenizers only apply a representation-alignment (REPA) loss on early decoder hidden states, a target the decoder can partly meet from its noised input instead. We introduce SemanTok, a flexible video tokenizer that feeds frozen DINO features into its encoder and adds lightweight heads that reconstruct them from each retained token prefix alone. SemanTok achieves high semantic alignment and video fidelity at every AR model size: a 201M SemanTok AR model matches or beats a VideoFlexTok AR model 3.4×3.4\times its size, and larger SemanTok AR models further improve fidelity. It keeps semantic alignment on out-of-distribution classes and gives the decoder higher semantic alignment at every noise level, including pure noise. It performs well in both reconstruction and generation, and its short token prefixes are cheaper to predict and give better generation fidelity, with pixel detail deferred to later tokens.
Sep 30, 2026

Enhancing Autoregressive Video Generation via Representation Adversarial Distillation

Few-step autoregressive video generation enables efficient streaming synthesis, but errors introduced in early temporal blocks are reused as context and can propagate through subsequent rollouts, leading to detail degradation, structural drift, and unstable motion. Existing distribution matching distillation (DMD) primarily aligns student and teacher distributions in diffusion latent space, but provides no direct supervision over the perceptual quality of decoded videos. We introduce Radian, a representation-space adversarial distillation framework that complements on-policy DMD with real-data adversarial supervision in the feature space defined by a frozen visual foundation model (VFM). During training, Radian sparsely decodes frames from autoregressive student rollouts, extracts multi-level visual representations, and applies lightweight discriminator heads to distinguish generated outputs from real video frames. The DMD objective anchors the student to the pretrained teacher, while the representation-space adversarial objective supplies complementary perceptual and semantic gradients that promote high-quality modes. These additional components are discarded after training, leaving the generator architecture and inference-time denoising budget unchanged. Experiments on Wan2.1-1.3B cover four-step chunk-wise, one-step frame-wise, and minute-long autoregressive generation. Our method achieves a VBench Total of 0.8444 and a VideoAlign Total of 0.8033 under four-step generation, and improves VBench-Long from 0.7805 to 0.8041 over Rolling Forcing while using fewer denoising steps. Controlled comparisons across image, video, and diffusion representations further indicate that the choice of representation spaces induces distinct adversarial signals, and external VFM gradients complement DMD more effectively than adversarial supervision derived from diffusion-internal features.
Sep 30, 2026

DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency

Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows continuously with the generated history. Existing compression strategies either discard history using fixed windows or select tokens through local attention and similarity signals, which do not directly measure whether the current chunk contributes information beyond the retained context. We introduce DeCoPrune, a training-free method that treats cache compression as a denoising-consistency problem. We find empirically that denoising difficulty provides a useful proxy for a token's value in long-term retention: tokens with larger step-to-final discrepancies tend to carry visual evidence that is less predictable from the retained context. DeCoPrune measures each current-chunk token's denoising difficulty using the discrepancy between its intermediate clean prediction and final denoised value, retaining high-discrepancy tokens in the long-term cache while pruning those with low discrepancy. To evaluate information retention, we introduce CMBench, comprising 58 approximately one-minute generated or real-world context episodes and 116 Reappear or Revisit continuation tasks that require recalling specific previously observed objects or scenes. Experiments with LingBot World v2 show that DeCoPrune preserves near-FullKV long-range recall while pruning over 85% of historical KV tokens and accelerating continuation generation by over 4×4\times, substantially outperforming the evaluated compression baselines at comparable budgets. These results indicate that denoising consistency can serve as a model-intrinsic signal for retaining long-range information while reducing autoregressive inference cost. Our project homepage is https://decoprune.github.io. The code is available at https://github.com/DeCoPrune/CMBench, and the benchmark at https://huggingface.co/datasets/Aoraku/CMBench.
Sep 30, 2026

Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video

Studying the alignment between the internal representations of vision models and the responses of the visual cortex to the same observed visual stimuli has enabled us to better understand human visual processing. However, studies so far have largely overlooked the fact that the human brain not only processes observed visual stimuli, but also predicts upcoming stimuli based on what has been observed. Accordingly, we hypothesize that internal representations for generating future video frames are better aligned with the predictive nature of human visual processing than representations of the observed video itself. To this end, we compare the alignment between human video-watching fMRI responses in the visual cortex and the internal representations from two types of video diffusion models, an autoregressive (AR) model and its non-AR base model. We first conduct a within-model analysis of the AR video diffusion model and show that the representations for future video generation align better with the visual cortex than the representations of the observed video. We then compare the internal representations of the AR model with those of its non-AR base model and again show that the representations for future video generation align better with the visual cortex than the representations for observed video reconstruction by the base model. Specifically, the alignment of observed video reconstruction is concentrated in lower-order visual cortex, whereas that of future video generation is concentrated in higher-order visual cortex. Finally, we show in a human behavioral experiment that humans prefer videos generated by amplifying the contributions of individual layers that align better with the visual cortex.
Sep 29, 2026

LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation

World models, game simulators, and long-take video creation require coherent scene evolution and sustained dynamics over extended durations. Autoregressive (AR) video diffusion provides a natural framework for long-horizon generation, yet extended rollouts often become near-static or lose visual quality. We hypothesize that these failures reflect the limited guidance provided by short-video supervision on how ongoing scene dynamics develops over longer durations. This motivates us to introduce LongTake, a two-stage training pipeline built around Long-Horizon Teacher Forcing (TF) on curated real long videos. Long-Horizon TF trains the AR model to predict later frames conditioned on long ground-truth video prefixes, extending direct supervision beyond the short training horizon. This supervision is designed to help the model sustain dynamics and preserve visual quality during long-horizon generation. Our central finding is that this training stage strengthens direct initialization for distribution matching distillation (DMD) under student self-rollout, without the intermediate few-step distillation stage used in standard pipelines. Under the same five-second DMD training setup, our initialization yields substantially higher dynamic degree than short horizon TF initialization on 30-second rollouts at comparable aesthetic quality, and surpasses the evaluated baselines in both measures. Hybrid DMD further reuses this teacher to extend supervision to later frames of the self-rollout while retaining bidirectional joint supervision over the initial window. On long-horizon self-rollouts, LongTake lies on the Pareto front of dynamic degree and aesthetic quality, and Hybrid DMD attains the highest dynamic degree among evaluated methods at both 30s and 60s.
Sep 29, 2026

Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History

Autoregressive video diffusion enables interactive streaming generation, but suffers from error accumulation over long rollouts. Self-rollout training reduces exposure bias, yet finite rollouts leave long-range drift unresolved. We observe that the noise level of the history key-value (K/V) representations trades visual quality against motion, and that restoring gradients through the history aligns causal training far more closely with bidirectional training. Motivated by these observations, we introduce Self-Aligned Forcing (SAF), a training scheme that aligns the history of each block with the noise level of the block being denoised. Specifically, the history is the K/V produced by preceding blocks at the same denoising stage, so all blocks at a stage can be denoised in a single forward pass under a causal mask. This keeps the noisy history differentiable, allowing future losses to optimize how it is encoded. SAF therefore avoids a separate no-gradient rollout and per-block timestep-zero recaching, training up to 1.8x faster than prior methods with lower memory. At inference, SAF achieves the highest single-GPU throughput among existing methods and keeps one history bank per stage for a multi-GPU pipeline, reaching 49.1 FPS on 4 GPUs. Experiments show superior long-horizon generation with a better balance between visual quality and motion. Project page: https://anonymous.4open.science/w/self-aligned-forcing/.
Sep 29, 2026

Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation

Autoregressive (AR) video diffusion enables low-latency, streamable video generation, but prediction errors often accumulate over long rollouts. Training the generator on its own rollouts exposes it to these imperfect histories. However, existing video-level distribution matching distillation (DMD) scores the whole rollout jointly. Because a chunk is evaluated together with its past and future, its correction can favor matching artifacts in the surrounding context merely to preserve temporal consistency. To provide a clearer visual-quality signal, we introduce Rollout-Marginal Distillation (RMD). RMD retains the generated history for AR prediction but scores each chunk independently against a chunk teacher, ensuring its quality correction is not compromised by an imperfect temporal context. To compensate for the lack of temporal context in independent chunk scoring, RMD subsequently applies video-level DMD to restore temporal coherence. Extensive experiments demonstrate that RMD maintains high visual quality far beyond its training horizon and outperforms video-level DMD baselines. Code and video results are available at https://cjeen.github.io/RMD
Sep 29, 2026

Scaling Video Generation for Reasoning: At What Cost?

We study whether scaling video generation enables models to reason about hidden information from the past frames, and at what computational cost. Our controlled benchmark requires predicting nine prescribed moves of an initially solved 2x2x2 Rubik's Cube from a fixed view of three faces. Correct predictions require inferring how actions change hidden states, and the simulator provides exact ground truth for evaluation. Models learn plausible cube geometry early, while correct sticker configurations require substantially more training. Although validation MSE follows approximate power-law scaling, lower MSE loss does not reliably indicate downstream reasoning capabilities. Smaller autoregressive models achieve higher state accuracy with limited compute, while larger models reach higher accuracy after more training. At roughly 0.1 PF-days, the 70M-parameter model correctly predicts the visible sticker configuration in 44.6% of post-action frames, compared with 0.3% for the 1B model, which reaches 83.7% at 3.14 PF-days. Symbolic state supervision raises the 20M model's frame accuracy from 31.1% to 67.3% at the same training-data budget, suggesting that learning representations of state changes can complement scaling.
Sep 28, 2026

From Scores to Samples: Elastic Forcing for Autoregressive Video Generation

Few-step autoregressive video generation commonly relies on Distribution Matching Distillation (DMD), requiring a bidirectional diffusion teacher and an online fake-score model. We instead learn the rollout distribution directly from reference videos, eliminating both score models during post-training. Our framework minimizes maximum mean discrepancy (MMD) in frozen self-supervised video representation spaces, using a hybrid Nyström--Monte Carlo estimator to balance approximation bias and sampling variance. Memory-efficient replay and gradient subsampling make this objective practical. Using the same architecture and initialization as Self-Forcing, our 1.3B model improves the VBench Total score from 83.80 to 84.64 while retaining 17 FPS. Removing auxiliary score models also enables 14B post-training on eight H200 GPUs. Beyond distillation, learning from reference videos enables the acquisition of new visual styles, semantic concepts, and spatial priors without a target-specific diffusion teacher.