Overview

Video diffusion models synthesize or transform frame sequences by denoising video latents, often in diffusion transformers, conditioned on text, images, reference clips, or structured controls. Researchers use temporal attention, autoregressive chunking, and pose, camera, depth, or physics cues to improve motion, identity, geometry, and interaction; related systems support editing, restoration, avatars, and world-model prediction. Evaluation spans prompt alignment and visual quality, using benchmarks such as VBench and FVD, as well as controllability, physical plausibility, and downstream action performance. A central challenge is balancing fidelity and precise control over long videos with the speed and memory needed for streaming, while limiting drift and physically implausible events.

Latest papers

812 papers72 papers in the last four weeks, down 36% on the four weeks before. 0.5% of all new papers.

Oct 12, 2026

Heuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration

Feature caching has become a mainstream training-free strategy for accelerating video diffusion models by reusing intermediate outputs across denoising steps. However, existing adaptive methods rely on heuristic difference measures misaligned with actual generation quality, employ a single global threshold that ignores heterogeneous phase dynamics, and never validate their budget estimates against true approximation error, allowing systematic bias to propagate uncorrected. We propose AlignCache, a closed-loop caching framework that directly aligns scheduling decisions with their true influence on the final generated video through three tightly coupled components: (1) phase-adaptive budget routing that partitions the denoising trajectory into structurally distinct phases, each governed by an independent threshold and a staleness-aware guard; (2) closed-loop threshold calibration that exploits counterfactual error measurement at the classifier-free guided output level to adjust decision boundaries online via an EMA feedback loop; and (3) momentum-augmented draft synthesis combining direction-magnitude gated residual extrapolation with anchor-guided unconditional correction. By transforming scheduling from a static risk accumulator into a feedback-driven, self-correcting controller, AlignCache consistently achieves superior acceleration-quality trade-offs across state-of-the-art video generation models. Our code is available at https://github.com/jiangjyjy/AlignCache.
Oct 12, 2026

MiMaAlign: Hierarchical Micro-Macro Alignment for Physically Plausible Video Generation

Text-to-video (T2V) diffusion models have made remarkable progress in generating high-fidelity visuals, yet their outputs still often exhibit physically implausible phenomena, including discontinuous dynamics and implausible event interactions. Existing representation alignment methods mainly transfer generic video features or short-range motion cues, treating physical plausibility as a single-level representation problem. To address this issue, we propose MiMaAlign, a hierarchical micro-macro alignment framework that transfers complementary dynamics-oriented and event-oriented knowledge into different abstraction depths of a pretrained video diffusion model. Specifically, micro-level continuous dynamics alignment imposes constraints by aligning diffusion features with a continuous-time motion representation learned by a Neural Ordinary Differential Equation (Neural ODE), while macro-level event-commonsense alignment provides representations of object interactions and event semantics through an instruction-prompted vision-language model (VLM). With training-only auxiliary objectives, we align the complementary supervision from the two teachers with shallower and deeper generator features, respectively, enabling the generator to internalize the corresponding physical priors. Empirical evaluations show that, on CogVideoX-2B, MiMaAlign achieves a relative improvement of up to 21.0% in the Physical Commonsense (PC) score on the VideoPhy benchmark over the baseline, and also delivers substantial gains on the highly challenging VideoPhy2 benchmark, while maintaining general video quality on VBench and being supported by blind user comparisons.
Oct 12, 2026

Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration

Diffusion models, particularly Diffusion Transformers, achieve strong image and video generation quality but remain expensive at inference time due to repeated denoiser evaluations. Feature caching offers a deployment-friendly acceleration strategy by reusing or predicting intermediate representations without retraining the generator or modifying the sampler. However, existing cache-then-forecast methods often rely on Taylor-style finite-difference extrapolation, which can become unstable over longer cache intervals, and typically predict local module outputs whose errors may accumulate through subsequent denoiser blocks. We propose BeziCast, a training-free diffusion acceleration framework that forecasts output-proximal denoising representations using low-order B'ezier trajectories. BeziCast estimates B'ezier control points via Tikhonov-stabilized fitting, providing a smooth, capacity-controlled temporal parameterization that avoids explicit high-order derivative estimation and decouples trajectory capacity from cache-query density. To moderate aggressive extrapolation, we further derive equivalent forecasting weights and introduce a convex-hull-inspired guardrail that detects high-risk predictions and softly pulls them toward a conservative simplex-projected estimate. Extensive evaluations across advanced image and video diffusion models demonstrate the effectiveness of BeziCast. In particular, BeziCast accelerates FLUX.1 by up to (4.79\times) and HunyuanVideo by up to (4.11\times), while preserving substantially better generation quality than competing acceleration baselines.
Oct 12, 2026

World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models

Video world models must generate physically plausible futures, not just realistic frames. Existing approaches typically use semantic, physical, or predictive information to guide the visual generation stream, leaving a fundamental question: where inside the generator should predictions of scene evolution live? Standard video tokens jointly encode appearance and dynamics, but provide no distinct state for learning and reading predictive dynamics. We answer this question with the Physical Registry: temporally grounded registry slots inside a video DiT that are initialized from an observation-conditioned forecast, co-evolve with video tokens, and receive future-representation supervision, making predictive dynamics an explicit, readable state of the generator. In a controlled comparison of predictive-state interfaces on Physics-IQ Verified, Physical Registry improves vanilla fine-tuning by 9.9/8.7 points on I2V/V2V, the largest gain among the interfaces we compare. Across all Cosmos and WAN backbones, Physical Registry improves Physics-IQ Verified scores. With only 0.45% additional parameters, it enables Cosmos 3 Nano 16B to surpass the published I2V score of Cosmos 3 Super 64B (43.56 vs. 42.7). On WorldModelBench, it also improves physical adherence and the total score for all four evaluated backbones. Because the registry becomes candidate-specific while remaining readable, the Physical Registry Selector (PRS) ranks emerging futures by how far their intermediate registry readouts depart from the shared forecast before full denoising is complete. Across four backbones, this selection improves I2V scores by 5.6-15.9% without completed-video external scoring. Together, these results support a broader principle: dynamics prediction should live as an explicit model state that co-evolves with the video representation. Project page: https://grainsack.github.io/physical-registry/
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

AcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation

Explicit point correspondence is attractive for adapting video generators: it describes how visible surfaces move, but can overwrite the appearance prior learned by a large pretrained model. We study this tension in a 5.01B-parameter text-to-video diffusion transformer. ACROSSVAM2.0 combines a confidence-weighted track-and-visibility head, zero-initialized residual feedback, and asymmetric PCGrad that removes only the auxiliary component opposing the primary flow-matching gradient on shared LoRA parameters. The design preserves the generator exactly at initialization and protects its primary update during adaptation. In a four-way ablation trained for 1,000 steps with three independent seeds, the full method lowers KLT forward-backward cycle error in all three seeds relative to a matched flow-only continuation (mean seed-level difference -0.00711, SD 0.00505), while robust sharpness remains positive in all three. An expanded 24-prompt evaluation (216 videos) yields 9.7% lower aggregate CoTracker3 cycle error than the matched control and near-matched performance on six VBench dimensions; however, the seed-level tracking effect is heterogeneous and I3D-FVD regresses from 0.1824 to 0.2022. These results support a bounded claim: conflict-aware adaptation improves correspondence consistency without broad perceptual degradation, but does not uniformly improve video quality. We release equations, pseudocode, matched outputs, source tables, and artifact provenance.
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

Competition Domains Matter: Selective Head Globalization for Training-Free Sparse Attention in Video Diffusion Transformers

Training-free sparse attention is a practical route to efficient video diffusion transformer inference, yet existing methods typically fix the competition domain at each query row for every attention head. Prior work primarily addresses how to estimate token-level importance within this fixed domain; whether the domain itself should adapt to head heterogeneity remains under-specified. We introduce EG-Sparse, a training-free framework that routes low-entropy heads to a grouped cross-head pool while retaining per-row local selection for high-entropy heads, using only scores already materialized by the sparse pipeline. A controlled diagnostic fixes the ranking score and varies only the competition rule: grouped cross-head selection reduces low-entropy-head reconstruction error by 9.8%, whereas forcing high-entropy heads into an all-head global pool increases it by 7.9%. Across four configurations, EG-Sparse achieves higher video quality while reducing attention density and GPU denoising latency compared with strong training-free sparse-attention baselines. Mechanism ablations further show that selective domain adaptation outperforms uniform, random, and fixed domain-assignment policies. These results support competition-domain adaptation as a distinct design axis within centroid-guided training-free sparse attention.
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

FreeCHROMA: Generative Chroma Keying from Unaligned Background References

In film production, chroma keying composites an approved foreground performance into a new environment, but conventional workflows require coordinated background plates and dedicated harmonization. Recent generative methods often require pre-aligned backgrounds, focus on background-conditioned foreground relighting, or represent the environment only through an edited first frame. These restrictions limit background selection, scene composition, and camera motion while adding preparation or editing effort. We present FreeCHROMA, which adapts a pretrained video diffusion model in a parameter-efficient manner for generative video compositing from one to three unaligned background references. The model integrates the foreground into the referenced environment, preserving foreground identity, motion, and fine visual details while generating a spatiotemporally coherent background. Foreground-background harmonization occurs within the same generation process, without a separate relighting stage. Optional text instructions help disambiguate complex spatial relationships and camera behavior. To train the model, we construct pseudo-paired data from readily available real monocular videos through foreground-background separation and augmentation with existing foundation models. The original videos serve as training targets, while automated processing and quality verification enable scalable data construction. Across reference fidelity, foreground preservation, scene integration, harmonization, and overall video quality, FreeCHROMA consistently outperforms recent compositing and conditional video-generation baselines, with particularly clear gains under camera motion. FreeCHROMA relaxes the constraints of existing tools to enable end-to-end generative chroma keying from unaligned inputs, with exploratory experiments demonstrating its potential in robotics.
Oct 9, 2026

GeoFix: Geometry Fixing for 4D Consistent Generation

Video diffusion models increasingly serve as priors for 4D generation, but the generated videos often lack geometric consistency. Recent approaches address this through post-training by designing geometric rewards, yet this can degrade texture and fine detail, requiring auxiliary appearance rewards and careful reward balancing. To address this challenge, we propose GeoFix, a unified framework that improves geometric consistency and visual quality with a single geometric reward, applicable to both training and inference-time reward alignment. Our reward measures cross-view depth consistency in static scene regions, targeting structural inconsistencies without directly constraining appearance or penalizing valid object motion. Crucially, depth agreement increases with camera field-of-view overlap even in real videos and 4D datasets, allowing a smaller camera movement to be mistaken for better geometry. We account for this effect by calibrating the reward against the overlap-dependent trend. GeoFix achieves a 39% improvement in WorldScore 3D consistency and a 4% increase in VBench Quality Score.
Oct 9, 2026

TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback

Classifier-free guidance (CFG) typically applies a shared scale to all latent tokens, although their velocity predictions evolve differently during sampling. We introduce Trajectory-Adaptive Classifier-Free Guidance (TrajCFG), a training-free method for flow-matching models that adapts token-wise guidance using historical changes in guided velocity direction. TrajCFG maps this feedback to bounded scales, assigning stronger guidance to larger directional changes and weaker guidance to more consistent directions. It combines adjacent-step and interval-normalized longer-span feedback, reusing standard CFG predictions without additional model evaluations. Controlled diagnostics and ablations examine the roles of directional feedback, token-wise allocation, and history-span fusion. Experiments on text-to-video, image-to-video, text-to-audio-video, text-to-image, and image-to-3D generation show improvements over base samplers across multiple backbones. For text-to-video generation, TrajCFG improves VBench Total scores by 0.30-0.75 points over the strongest evaluated baseline on each of three backbones. These results support historical directional feedback as a broadly applicable signal for fine-grained guidance allocation. The project page is available at https://jyliu-98.github.io/trajcfg-project-page/.
Oct 9, 2026

LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse

Image-to-video (I2V) diffusion models can animate a single reference image into high-quality, subject-consistent videos, posing threats of misuse as anyone can turn personal photos into fabricated videos without consent. A promising solution is to proactively add an adversarial perturbation to the image before release, such that videos generated from it would be unfaithful or visually corrupted. However, due to an insufficient understanding of what governs how subsequent frames read the reference image in modern I2V models, existing protections struggle to offer strong protection under common perturbation budgets. In this paper, we approach the problem by exploring this underlying reading mechanism. Through a convex geometric analysis, we theoretically identify the spread of the reference value vectors as a key factor governing this reading process, and empirically find that even a mild contraction of this spread can severely degrade the generated video, making it an efficient lever for protection. Guided by this insight, we propose LETHE, a novel protection method that directly disrupts this reading process. LETHE pairs two complementary objectives, where a value collapse objective drives the reference value vectors toward uniformity, while an attention attraction objective draws subsequent frames toward these collapsed tokens to amplify corruption. We further construct two human-centric I2V protection benchmarks and conduct extensive experiments with multiple modern I2V models, which demonstrate the state-of-the-art protection performance and versatility of LETHE.
Oct 9, 2026

PAGE: Parts-Aware Guidance for Co-Speech Gesture Portrait Video Generation

Co-speech gesture video generation aims to synthesize realistic, audio-driven portrait videos from a single reference image and a speech signal. Despite advances in visual quality, diffusion-based approaches still suffer from degraded local details and imperfect audio-visual alignment. We present PAGE (Parts-Aware GuidancE), a general, backbone-agnostic optimization framework for diffusion-based generation that enhances local spatial fidelity and global audio-visual consistency at both the training-objective and denoising-trajectory levels. During training, we propose Parts-Specific Reweighting (PSR), which adaptively increases supervision in semantically important regions such as lips, eyes, and hands, improving visual fidelity in perceptually critical areas. During inference, we introduce Consistency Classifier Guidance (CCG), an audio-conditioned latent classifier that identifies and corrects audio-visual inconsistencies in the generated video. We further design Differential Guidance (DG), an efficient inference strategy that refines facial and body motion separately while avoiding cross-region interference. To enable large-scale evaluation, we construct the Chinese Announcer Speech (CAS) dataset, the first comprehensive Chinese benchmark for co-speech gesture portrait video generation. Compared with the widely used PATS dataset, CAS includes substantially more identities, video clips, and scene diversity. Extensive experiments on both PATS and CAS demonstrate that PAGE achieves state-of-the-art performance in perceptual quality, gesture diversity, and audio-visual alignment. Project page: https://aigc-explorer.github.io/PAGE/.
Oct 9, 2026

Destination-Conditioned Adaptation with Semantic-Geometric Alignment for Generative Inbetweening

Generative inbetweening aims to synthesize temporally coherent intermediate frames between a start frame and a target frame. Although pretrained image-to-video diffusion models provide strong priors for large-motion inbetweening, they are not explicitly designed to reach a specified target frame. They may therefore generate realistic individual frames while drifting from the target or producing unstable motion under large displacements and non-rigid dynamics. We propose DSG-GI, a framework that adapts pretrained latent video diffusion models through Destination-Conditioned Adaptation and Semantic-Geometric Alignment. Destination-Conditioned Adaptation treats the target frame as the destination of the sequence and provides temporally progressive guidance along the generated trajectory. Semantic-Geometric Alignment aligns the token-wise spatio-temporal relational geometry of backbone features with that of a frozen video foundation encoder and applies a flow-matching-aware latent flow constraint to samples near the data endpoint of the probability path. Together, these components strengthen destination guidance and preserve coherent semantic-geometric motion structure. Extensive experiments on standard and large-motion inbetweening benchmarks demonstrate improvements in temporal stability, target-frame faithfulness, and perceptual quality. Our code will be made publicly available.
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

LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation

Generating an egocentric video from a single exocentric recording is a challenging case of novel view synthesis, as the two cameras share little overlap and much of the target view is unobserved. Current state-of-the-art methods reconstruct the scene explicitly by estimating depth, lifting the video into a point cloud, and re-rendering it from the egocentric camera to condition a video diffusion model. This deterministic mapping assigns each pixel to a single reprojected location, which preserves texture but translates depth errors into misplaced content. We ask what a video diffusion model should receive as its condition and propose a lifting-free answer: a learned view synthesizer, an LVSM-style transformer fine-tuned to render the egocentric view directly without depth, point clouds, or reprojection, resolving cross-view correspondence internally. In contrast, its probabilistic mapping averages each region over candidate source locations according to a learned correspondence distribution, preserving structure while fine texture is averaged away. We argue that this trade-off suits a diffusion generator, whose denoising training excels at restoring detail, so an effective condition should prioritize structural alignment over sharpness. This distribution's concentration also yields a per-region confidence, used both to mask low-confidence regions and to guide the generator toward high-confidence areas during early layout-forming denoising steps. Our approach consistently outperforms the state-of-the-art explicit pipeline and generalizes to other datasets without retraining. The synthesizer thus supplies view structure, and the diffusion model its detail.
Oct 8, 2026

WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation

Faithful visual world simulation requires generated videos to maintain 4D world consistency, encompassing both static and dynamic consistency. Static consistency requires coherent 3D structure in static environments across viewpoints, while dynamic consistency requires plausible subject motion and consistent appearance over time. Geometry-aware post-training offers a promising way to improve world consistency. However, existing methods often rely on a static-scene assumption. Even those that accommodate dynamic scenes struggle to provide reliable static-consistency feedback, while dynamic consistency is often overlooked or inadequately assessed. To address these limitations, we introduce WorldAlign, a decoupled 4D reward framework that semantically separates static regions and dynamic subjects and provides feedback by aligning each with a world prior suited to its assumptions. For static regions, WorldAlign aligns static geometry with a geometric world prior through semantically guided masked reprojection, enabling more reliable static-consistency evaluation; an auxiliary camera-motion reward discourages nearly static solutions. For dynamic subjects, WorldAlign uses a strong vision-language model (VLM) as a dynamic world prior and constructs a VLM-as-a-judge reward based on sample-specific checklists that assess dynamicity, physical plausibility, shape, and texture consistency. This decoupled design enables more effective online post-training without requiring human preference annotations. Across two pretrained image-to-video generators, Wan2.1 and Wan2.2, WorldAlign jointly improves static and dynamic consistency over existing methods without suppressing overall or subject motion. These results support decoupled world-prior alignment for more faithful visual world simulation. Project page: https://worldalign.github.io/.
Oct 8, 2026

VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling

Building a capable video editor remains significantly harder than a video generator: editing requires (source, instruction, edited) triplets that are prohibitively expensive to annotate and difficult to synthesize at scale, whereas image editing has already reached maturity with millions of such pairs readily available. In this work, we introduce VINCIE-NExT, a unified framework that transfers editing capability from images to videos through in-context visual demonstrations, alleviating the need for large-scale paired video editing data. VINCIE-NExT decomposes video editing into a structured chain of composable sub-tasks (Video -> Image -> Image -> Video), routing editing intent through the image domain and enabling scalable joint training from heterogeneous image and video corpora under a unified diffusion objective. An image editing pair, synthesized by the model or supplied by the user, is prepended as an in-context visual demonstration that serves as a spatial appearance blueprint for every output frame. To ground appearance edits across the interleaved context, we introduce a novel position encoding that links image demonstrations and video frames in a shared spatial coordinate system, enabling pixel-faithful propagation of appearance changes to every output frame. Chain-of-Editing further provides principled test-time scaling: by executing the sub-task chain as progressive diffusion stages, editing quality can be improved by investing additional compute without retraining. Comprehensive experiments on OpenVE-Bench demonstrate the state-of-the-art performance across diverse editing categories, with ablations confirming the effectiveness of each component.
Oct 8, 2026

Parametric Trajectory Distillation for Few-Step Video Generation

Video diffusion and flow models require many sequential evaluations, making generation computationally expensive. Few-step distillation reduces this cost but poses a capacity allocation problem: a student must match the teacher's iterative generation with far less sequential computation. Existing trajectory methods ask the student to reproduce teacher transitions that are highly curved at high noise, which can exceed its capacity and degrade fine detail. We introduce Parametric Trajectory Distillation (PTD), which lets the student parameterize teacher trajectory segments as polynomials and learn from teacher guidance along its own predicted path. PTD is designed to let the learned curvature adapt to the backbone's predictive capacity, preserving motion and diversity. The curvature head is used only in training; inference keeps the original backbone architecture. On Wan2.1-14B, four-step PTD sets a new state of the art for trajectory distillation, significantly improving dynamic quality and naturalness over PDD, the best-performing trajectory-only method on this model, under the same training setting. On the 33B audio-video MiniMax-H3, LoRA-trained PTD significantly improves diversity and naturalness over the state-of-the-art LightX2V Turbo. Blinded human votes give PTD 55.1% and 63.4% preference shares against PDD and LightX2V Turbo. Project page: https://alan-lanfeng.github.io/PTD/.
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 8, 2026

iCATS: Fast Video Generation via Interaction-Aware Sparse Attention and Timestep-Adaptive Sparsity

Training-free sparse attention offers a practical acceleration solution to Diffusion Transformers (DiTs) via reducing computations without fine-tuning. It typically involves estimating the importance of query-key regions and deriving sparse masks to compute only the important candidates, which inevitably introduces approximation errors that may degrade generation quality. To better balance the efficiency-quality trade-off, we propose iCATS, integrating improved importance estimation and sparse mask construction with an efficient hardware execution strategy. Specifically, for importance estimation, unlike previous works that perform independent clustering over query and key tokens based on feature similarity to estimate attention scores, iCATS demonstrates that clustering based on query-key dot-product interactions is more accurate and further reformulates this objective as a simple quadratic form for low-cost computation. For sparse mask construction, instead of using a fixed top-p rule, we observe that tolerance to sparse approximation errors varies across denoising timesteps and therefore introduce an SNR-guided sparsity schedule to adjust sparsity dynamically, leading to higher accuracy. Finally, for hardware execution, we devise a tail-merging strategy to reduce padding overhead caused by irregular cluster sizes, improving GPU kernel utilization. Extensive experiments show that iCATS achieves 2.03×2.03\times acceleration with 31.017 dB PSNR on HunyuanVideo-T2V-13B and 1.55×1.55\times acceleration with 29.301 dB PSNR on Wan2.1-T2V-14B, delivering a state-of-the-art efficiency-quality trade-off.
Oct 8, 2026

IntactWorld: Joint World Modeling with Intact Features

While recent video generation models synthesize highly realistic visuals, they lack a genuine understanding of intrinsic real-world logic. Existing methods attempt to understand the world by internalizing diverse world knowledge, yet constrained by computational overhead or dimensionality alignment, their learning processes inevitably compress features, causing a severe loss of structural information. To address this, we propose IntactWorld, a Joint World Modeling Architecture utilizing uncompressed Intact Features. Since data naturally reside on a low-dimensional manifold within a high-dimensional space, predicting the flow velocity vv within this uncompressed high-dimensional space induces a severe manifold gap. To successfully eliminate this optimization bottleneck, our framework instead predicts the clean feature x0x_0 at intermediate layers. Furthermore, to mitigate the computational overhead of incorporating complete world knowledge, we introduce a Full-to-Compact Training Paradigm. By replacing raw full features with highly refined CLS tokens, this paradigm enables efficient single-branch guidance, reducing spatial memory consumption by 11.4% and cutting inference latency by 43.8%. Extensive evaluations demonstrate the effectiveness of IntactWorld, outperforming established baselines by 2.46 points on the VBench 2.0 benchmark.
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

GRACE: Generation-aware latent compression for efficient video generation

Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fewer tokens. However, such autoencoders are challenging to train, since a higher compression ratio degrades reconstruction quality and recovering it requires more channels, which is known to slow the convergence of the DiT. The compressed latent also differs from the one the DiT was trained on, so the pretrained DiT must be either retrained from scratch or adapted at considerable cost. Compressing the autoencoder the DiT was trained with appears to preserve compatibility, yet optimizing it for reconstruction alone still shifts the latent away from the distribution the DiT has learned. To address this, we propose Generation-Aware Latent Compression for Efficient Video Generation (GRACE), a two-stage framework that compresses a pretrained video autoencoder while keeping it compatible with the pretrained DiT. Specifically, we keep a frozen base latent from the pretrained encoder and learn a residual latent for the information lost under stronger compression, while aligning the compressed latent with the pretrained latent in the feature space of the frozen DiT so that the autoencoder is optimized for generation. We then adapt the DiT with lightweight fine-tuning and asymmetric denoising, where the base is denoised ahead of the residual. GRACE reduces the token count of Wan2.1-I2V-14B by 8x and its latency by 11.1x at 480x832x81, while matching the generation quality of the pretrained pipeline before compression on VBench.
Oct 7, 2026

MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration

Diffusion Transformers (DiTs) achieve remarkable performance in video synthesis, but their iterative denoising process suffers from high inference latency. To address this, caching has emerged as an effective acceleration strategy by capitalizing on inter-step redundancy during denoising. Existing dynamic caching methods typically estimate the error that cache reuse would introduce at each denoising step (step error) to guide cache decisions, whereas our concern is how much quality loss cache reuse would cause in the final generated video (terminal error). We show that step error does not directly correspond to terminal error and that latent information helps capture their relationship, thereby informing cache decisions. Moreover, existing threshold-based methods cannot provide precise speedup control, making it difficult to meet practical requirements for user-specified acceleration targets. To address these limitations, we introduce MORCA, a cache scheduling framework trained through offline-to-online reinforcement learning to make latent-aware reuse/recompute decisions under user-specified acceleration targets. Extensive experiments on different video generation models across multiple target acceleration ratios demonstrate that MORCA achieves better generation fidelity than state-of-the-art caching methods under comparable computational budgets. Code is available at https://github.com/x10ngyx/MORCA.
Oct 7, 2026

Kuration SDK: Addressing the Virtual2Real Gap via Data Curation

Benchmarks for measuring the quality of action-conditioned world models are still evolving and shifting away from visual similarity-based metrics to action-semantic and physically-grounded metrics. However, for domain and task-agnostic action-conditioned world model training, existing benchmarks provide a limited signal. By training and evaluating diffusion world models on CounterStrike gameplay data, we confirm that qualitative playability does not correspond with metrics such as FVD, LPIPS, and JEDi. We term this the Virtual2Real gap. We posit that, in lieu of reliable benchmarks, curating raw gameplay data and measuring a variety of diagnostic properties provides a more robust signal to bridge the gap, before the training even begins. We present several curation strategies and a general-purpose kit for physical AI data curation called Kuration SDK, which is being open-sourced with this paper. The SDK was instrumental in uncovering the root cause of the virtual2real gap in a specific case: why two world models trained on identical gameplay map, action and state distribution, behaved very differently when played in spite of having very similar LPIPS and FVD scores. Thus, Kuration SDK has the potential to uncover the root causes of Virtual2Real gap in specific datasets and accelerate development of sample-efficient training datasets.
Oct 6, 2026

Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation

Diffusion Transformers (DiTs) have achieved strong performance in image and video generation, but the quadratic complexity of full attention makes high-resolution generation computationally expensive. Window attention offers an efficient alternative, yet existing methods face a practical trade-off: partitioned window attention typically achieves computational efficiency consistent with its theoretical complexity. However, isolated windows block cross-window interaction, often introducing visible grid-like artifacts in the generated results. Fine-grained sliding-window attention effectively restores interactions across neighboring windows and improves visual quality. However, its irregular computation patterns create a substantial gap between theoretical and practical speedups and require specialized kernels tailored to each hardware backend. To tackle these challenges, we propose BASA, a backend-agnostic sparse attention, which brings the best of both worlds: visual quality and practical acceleration. Specifically, BASA replaces visual self-attention with shifted local-window attention. By introducing a structured window-shifting scheme across DiT blocks, we allow tokens divided by window boundaries in one layer to communicate in the following layers, thereby achieving global information exchange and eliminating window-induced visual artifacts. Notably, our design introduces no additional irregular operators or customized kernels, making it readily deployable on existing attention backends and closing the gap between theoretical sparsity and practical acceleration. Experiments demonstrate that BASA achieves measured speedups exceeding 90% of the theoretical estimates on FLUX and delivers a 4.52×\times attention speedup on Wan while maintaining competitive generation quality. Codes are publicly available at: https://github.com/lama0110/BASA.