Temporal Consistency in Video Generation

Follow this topic Ask about this topic

Momentum

30 papers in the last four weeks, up 275% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 224

Oct 8, 2026cs.CV

OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3D Gaussian Splatting scene into a 3D cinemagraph: a dynamic scene with vivid, diverse motion looping seamlessly from any viewpoint. A vision-language model infers plausible dynamics and guides a video model to synthesize a reference video, which we lift and complete into multi-view videos. To learn from this imperfect supervision, we propose Inconsistency-Robust Periodic 4DGS: a Fourier-series deformation field guarantees looping by construction, while a Grounded Drift Field anchored at the reference view absorbs cross-view inconsistency. Unlike prior Eulerian methods limited to fluid-like motion, we capture general deformation, object motion, and illumination change. We introduce a ground-truth-free evaluation covering vividness, naturalness, loop seam coherence, and scene quality. On 39 reconstructed and generated scenes, OuroWorld outperforms all baselines and wins 70.8%-99.0% of user-study comparisons. Project page: https://ouroworld.userwei.com

You-Zhe Xie, Ting-Wei Chou, Yu-Hsuan Li +3

National Yang Ming Chiao Tung University · Alaya Lab

Dynamic Scene Reconstruction 4D Scene Generation Temporal Consistency in Video Generation 3D Gaussian Splatting

Oct 8, 2026cs.CV

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/.

Jing He, Kaixin Ding, Xingye Tian +5

The Hong Kong University of Science and Technology (Guangzhou) · KlingAI · The University of Hong Kong +1

Video Generation Temporal Consistency in Video Generation Video Diffusion Models Physical Consistency in Video Generation RL for Video Generation

Oct 8, 2026cs.CV

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.

Dongbin Zhang, Chaoda Zheng, Kangjie Chen +13

XPeng · The Chinese University of Hong Kong · Tsinghua University

Autoregressive Video Generation Streaming Video Generation Long-Horizon Video Generation Temporal Consistency in Video Generation Backpropagation

Oct 8, 2026cs.CV

Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention

Real-time video super-resolution requires high spatio-temporal fidelity under strict latency constraints, challenging diffusion models due to their iterative sampling cost and limited temporal coordination. We propose a streaming-aware framework that adapts pretrained single-image latent diffusion models for efficient video super-resolution (VSR) by exploiting the sequential structure of video streams. Our Cross-Step Attention mechanism reuses intermediate denoising features across adjacent frames and diffusion steps, enabling temporal information exchange without explicit temporal modeling. We further introduce Trajectory-Coupled Diffusion Scheduling, which aligns adjacent diffusion states and provides cleaner intermediate representations for cross-step conditioning, improving temporal coherence. These components are integrated into a streaming inference pipeline that incrementally propagates latent states across frames, reducing the effective computational complexity from

O(N \cdot S)

to

O(N + S)

for

N

frames and

S

diffusion steps. Experiments on REDS4 and YouHQ40-Test demonstrate improved perceptual quality and temporal realism while maintaining frame-wise stability. Our method achieves over 40 FPS at

512 \times 512

resolution after cold start, enabling real-time VSR without explicit temporal modeling.

Harris Partaourides, Sotirios Chatzis

Ethical AI Novelties Limassol, Cyprus · Cyprus University of Technology Limassol, Cyprus

Video Super-Resolution Diffusion Model Inference Acceleration Temporal Consistency in Video Generation Diffusion Timestep Scheduling

Oct 8, 2026cs.CV

Learning to Retrieve: Internalizing Memory Retrieval for Video World Models

Video world models aim to generate explorable, 3D-consistent scene videos conditioned on camera trajectories. Existing approaches often rely on external memory systems that explicitly retrieve previously observed content to mitigate scene drift during long-horizon generation. However, these auxiliary memory pathways operate outside the model's internal generative dynamics, preventing the model from intrinsically learning when and what historical information should be retrieved. We propose to internalize memory retrieval into the generation process, allowing retrieval to emerge as an intrinsic behavior of the video world model rather than relying on an external memory system. Based on this principle, we introduce \textbf{Learning-to-Retrieve (L2R)}, which repurposes the model's persistent internal state as a memory for historical context. A camera-conditioned retrieval gate selectively accesses relevant historical information from this state, determining \textit{what to retrieve}, while a retrieval trigger determines \textit{when to retrieve}. We further supervise the trigger with a 3D re-visibility signal, activating retrieval when previously observed content re-enters the current view while otherwise preserving the existing context. Together, these components enable the model to intrinsically acquire memory retrieval behavior and incorporate relevant historical observations into generation without a separate retrieval pathway. Across multiple base models and camera-revisit benchmarks, L2R improves long-term scene consistency while eliminating the need for an external memory bank or 3D conditions. https://jkhu29.github.io/l2r

JiaKui Hu, Tailai Chen, Yuqi Pan +8

Peking University · Xiaomi EV · CASIA +2

Memory-Augmented Video Generation Video World Models Long-Horizon Video Generation Temporal Consistency in Video Generation Camera-Conditioned Video Generation

Oct 8, 2026cs.CV

MATE4D: Matrix-Guided Editable 4D Generation from a Single Image

Generative models have rapidly pushed content creation be-yond 2D imagery toward dynamic 3D and 4D scene synthesis. Yet pro-ducing realistic and temporally stable 4D content from a single image is still difficult because one view provides limited structural cues and weak motion evidence. We introduce MATE4D, a framework that converts one input image into editable dynamic 4D content. Our method constructs a spatio-temporal multi-view image matrix with text-guided background manipulation, delivering coherent supervision over viewpoint, appear-ance, and motion. These synthesized observations are used to optimize 3D Gaussian primitives, which are then animated through a lightweight deformation module to form a 4D representation. The resulting scenes preserve geometry more faithfully, maintain smoother temporal behavior, and keep background edits more consistent, reducing context ambiguity and motion artifacts. Experiments on Objaverse-XL and Diffusion4D show that MATE4D outperforms strong baselines in visual quality, effi-ciency, and controllability, supporting practical AR/VR content creation.

Xiaotian Chen, Dongfu Yin

Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) · Shenzhen University

4D Scene Generation Temporal Consistency in Video Generation

Oct 8, 2026cs.CV

Transforming Image Editors into Video Editors

Recent image editing systems have achieved impressive semantic understanding, visual fidelity, and instruction-following ability, while video editing remains substantially more difficult and costly. In this paper, we present a simple alternative to end-to-end video editing: instead of training a monolithic video editor, we transform a strong image editor into a video editor through anchor-based generation. Our key insight is that video editing can be decomposed into two subproblems: editing a sparse set of keyframes and propagating those edits across time. Based on this observation, we propose Anchor-based Video Editing (AVE), a two-stage framework in which a powerful image editor first performs composed editing on selected keyframes, and a motion-guided image-to-video diffusion model then generates the final video by treating the edited keyframes as fixed anchors. This design directly inherits the strengths of modern image editors while avoiding expensive end-to-end video editing training. Experiments on IVEBench and VIE-Bench show that AVE achieves strong performance in instruction following, temporal consistency, and content fidelity. Further ablations reveal that final video editing quality is strongly correlated with the quality of the image editor, suggesting that future progress in video editing may come from stronger image editing foundations and lightweight transfer to video. Code is available at https://github.com/wangf3014/AVE.

Feng Wang, Zijie Li, Ceyuan Yang +2

ByteDance Seed · Johns Hopkins University

Video Editing Instruction-Based Video Editing Temporal Consistency in Video Generation

Oct 7, 2026cs.CV

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.

Zihan Su, Junhao Zhuang, Yaowei Li +10

Tsinghua University · Joy Future Academy, JD · The Chinese University of Hong Kong

Autoregressive Video Generation Long-Horizon Video Generation Temporal Consistency in Video Generation Gradient Interference

Oct 7, 2026cs.CV

Self-correction Optimization for Interleaved Multimodal Generation

Multimodal large language models (MLLMs) have made significant progress in visual understanding and generation. However, generating interleaved image--text content remains challenging, as it requires tightly integrated multimodal understanding and generation capabilities. Although existing MLLMs provide promising solutions, most rely on additional training with augmented data, which is computationally expensive and remains limited in preserving visual subjects, temporal consistency, and physical plausibility. In this work, we propose self-correction optimization (SCO), an effective training-free method for consistent interleaved generation. SCO treats the classifier-free guidance update as a reference and performs minimal self-correction under two complementary constraints, including new-event and state-preserving constraints. Specifically, the new-event constraint promotes temporal consistency across image--text sequences, while the state-preserving constraint maintains the coherence of visual subjects throughout subsequent generation steps. Experiments on challenging interleaved multimodal generation benchmarks demonstrate significant improvements in temporal coherence and visual-subject preservation. Furthermore, SCO can be extended to video generation and improves the modeling of physically grounded processes, including robot manipulation and long-horizon handcrafting.

Xin You, Zhiwei Ning, Zukai Chen +7

Shanghai Jiao Tong University · SenseTime Research · Technical University of Munich

Multimodal Generation Temporal Consistency in Video Generation

Oct 5, 2026cs.CV

S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation

Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-distribution data from procedural generators, continue to violate physical laws and simple symbolic rules. We introduce Serial-to-Parallel Diffusion (S2PD), which performs autoregressive diffusion at high noise before switching to parallel diffusion at low noise. The autoregressive phase provides the serial computation needed to coordinate interdependent events and produce valid state transitions while the parallel phase jointly refines the entire video and reduces sampling time relative to fully serial generation. We implement S2PD with two architectures: a pixel-space diffusion transformer trained from scratch and a pretrained video model adapted through LoRA fine-tuning with causal attention. Across games, physical simulations, and real video, S2PD follows rules more reliably than matched bidirectional baselines and generates videos with greater temporal stability and sampling efficiency than other serial methods.

Jeffrey Hu, Daniel Olmeda Reino, Ayush Tewari

University of Cambridge · Toyota Motor Europe

Physical Consistency in Video Generation Video Diffusion Models Autoregressive Diffusion Temporal Consistency in Video Generation

Oct 5, 2026cs.CV

ChronoWorld: Camera-Controlled Consistent 4D World Generation via Spatiotemporal Cues and Geometric Reflections

While existing camera-controllable video generation models can produce visually compelling sequences, preserving intrinsic 4D spatiotemporal coherence remains challenging. To address this limitation, we propose ChronoWorld, an "Observation--State--Reflection" framework that leverages spatiotemporal causal cues and reconstruction priors to generate globally consistent, free-view 4D scenes. Given a context video, we introduce a Spatiotemporal Epipolar Causal Attention mechanism that enforces multi-view epipolar constraints and temporal causality throughout the generation process. In addition, we develop a reconstruction-driven geometric reflection pipeline with a 4D retrieval strategy to enable dynamic self-assessment and correction of generated outputs, improving consistency and accuracy. Extensive experiments show that ChronoWorld achieves state-of-the-art performance in spatiotemporally consistent, cinematic-quality 4D scene generation, with strong generalization and high-fidelity geometry across diverse scenarios.

Xiaoyu Zhou, Dingwei Xian, Zhenyu Wang +3

Wangxuan Institute of Computer Technology, Peking University · VGI Labs Co., Ltd. · University of California, Merced

Camera-Controlled Video Generation Multi-View Video Generation Temporal Consistency in Video Generation 4D Scene Generation

Oct 5, 2026cs.CV

HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models

Long-horizon video world models require persistent memory to preserve scene consistency over extended rollouts. Softmax attention retains the full generation history through a growing KV cache, whereas recurrent linear attention compresses history into fixed-size states with substantially lower memory cost. However, we identify severe long-range forgetting in Gated DeltaNet (GDN), where information from distant but relevant scenes is progressively attenuated by subsequent state updates. To address this limitation, we propose HLA-WM, a training-free hybrid linear-attention framework that combines coarse-grained geometry-guided retrieval with fine-grained recurrent linear-state computation. HLA-WM exploits the affine structure of GDN to cache compact chunk-wise transition summaries, retrieve scene-relevant historical chunks using camera geometry, and recompose them into query-specific recurrent states. On the

60

-second SANA-WM-Bench, HLA-WM improves all six aggregate revisit-consistency and camera-control metrics of the base autoregressive generator without additional training, including a

0.74

dB PSNR gain and a

28.5\%

reduction in rotation error. The improvements persist after downstream refinement and generalize to MBench-A, where HLA-WM consistently improves all three revisit-consistency metrics across all four subsets and all evaluated inference modes over

547

samples. At a

60

-second context, HLA-WM reduces historical-state memory by

12\times

relative to full KV caching while incurring at most a

1.6\%

reduction in inference throughput. These results demonstrate that selectively addressable recurrent memory can improve long-range scene recall while preserving the efficiency advantages of GDN. Project page: https://caesarhhh.github.io/hla-wm/

Zhuokun Chen, Feng Chen, Xi Lin +4

Monash University · The University of Adelaide · Zhejiang University

World Model Learning Long-Horizon Video Generation Memory-Augmented Video Generation Linear Attention Hybrid Attention Temporal Consistency in Video Generation

Oct 2, 2026cs.CV

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.

Jeongwoo Shin, Youngyoon Choi, Sangwoo Jo +5

Seoul National University · Korea University · Sungkyunkwan University +1

Long Video Generation Video Diffusion Models Autoregressive Video Generation Temporal Consistency in Video Generation Diffusion Model Caching

Oct 1, 2026cs.CV

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.

Yiwen Zhang, Haocheng Xi, Michael Tian-Yue Liu +4

Cornell University · Impossible, Inc. · University of California, Berkeley +1

Image-to-Video Generation Long-Horizon Video Generation Memory-Augmented Video Generation Autoregressive Video Generation Temporal Consistency in Video Generation

Oct 1, 2026cs.CV

Towards Subject Consistency over Dynamic Subject Sets in Video Generation

We argue that as video generation extends to longer durations, subject consistency should be evaluated over \textit{dynamic subject sets}. We therefore introduce \textbf{DynSC-Eval}, an evaluation framework that dynamically tracks eligible subjects throughout their visible lifespans and measures local continuity and global identity preservation using six complementary object-level metrics, with explicit detection of inconsistency events. To validate its effectiveness, we design synthetic experiments that actively inject inconsistency events, demonstrating both the sensitivity of DynSC-Eval and the limitations of existing metrics. Evaluations of diverse models on 5s, 15s, and 60s video generation further reveal substantial subject consistency differences that are obscured by conventional metrics. Beyond evaluation, we construct rewards from DynSC-Eval and apply DiffusionNFT post-training in an autonomous-driving testbed. On 5s generation, our approach reduces the six inconsistency metrics by an average of 13.82% for Wan-2.1-1.3B and 5.66% for SANA-2B, with improvements also observed on the I2V model ReSim. Qualitative comparisons further demonstrate the effectiveness of our method. We then extend generation to 10s and 30s through curriculum learning and show that consistency optimization remains effective while largely preserving other capabilities.

Tongcheng Zhang, Jun Zhu, Jianfei Chen

Dept. of Comp. Sci. and Tech., Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University

Long Video Generation Identity-Preserving Video Generation Video Generation Temporal Consistency in Video Generation Video Generation Evaluation

Sep 30, 2026cs.CV

ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing

Recent video generation is increasingly realistic and controllable, yet video editing remains less developed, particularly for precise local edits that must preserve the original scene dynamics. Video scene text editing replaces text on scene surfaces, such as storefront signs, whiteboards, and product labels, while preserving the surrounding content, motion, and camera dynamics. Although scene text editing is well studied for images, video scene text editing that achieves high visual quality, temporal consistency, and edit locality remains underexplored. Existing resources offer limited paired real-video data, and general video-editing metrics do not directly measure whether the requested text remains correct over time. We introduce ViTeX-Bench, a benchmark suite comprising ViTeX-Dataset and a three-axis evaluation protocol. The dataset contains 387 real-world 720p videos with text-region masks and editing instructions: 230 provide reviewed, pipeline-generated paired edits for training, and 157 form a frozen evaluation split. The protocol evaluates text correctness, visual and temporal quality, and edit locality through 13 metrics, with one primary metric per axis and a Pareto comparison of their trade-offs. OCR calibration, human evaluation, and annotation-sensitivity analyses support the interpretation of these scores. Across eight baselines from four editing families, accurate text, temporal stability, and scene preservation remain difficult to achieve together. We also release ViTeX-Edit-14B, an open-source reference editor fine-tuned on the paired training split with motion-aligned glyph-video conditioning. It achieves CharAcc 0.688, the highest mean among the evaluated video-native editors, and the lowest comparable text-crop Warp among raw editor outputs. ViTeX-Bench provides a reproducible foundation for studying these trade-offs in video scene text editing.

Xinghao Chen, Xiangbo Gao, Jiongze Yu +2

Texas A&M University

Video Editing Benchmarks Video Editing Temporal Consistency in Video Generation

Sep 30, 2026cs.CV

TexTailor: Texture-Preserving Video Virtual Try-On via Adaptive Garment Conditioning

Video virtual try-on has attracted increasing attention due to its broad potential in digital fashion and intelligent e-commerce. However, existing methods primarily focus on low-resolution settings and still face substantial challenges when extended to high-resolution scenarios. These limitations can be attributed to two main factors: (1) the insufficient utilization of rich garment reference information, and (2) the lack of explicit positional modeling between garment and video representations during cross-modal interaction, which weakens fine-grained local correspondence. To address these issues, we propose TexTailor, a high-fidelity video virtual try-on framework built upon a pretrained video Diffusion Transformer. Specifically, we introduce a timestep-adaptive modulation mechanism to dynamically adjust garment visual representations throughout denoising. We further develop a frame-aligned positional encoding strategy to strengthen garment-to-video correspondence, together with a multi-source injection design that reduces interference among heterogeneous conditions. Extensive experiments on multiple video virtual try-on benchmarks, including the high-resolution Eevee dataset, demonstrate that TexTailor achieves competitive performance in garment detail preservation, temporal consistency, and overall video quality.

Zijing Qin, Jun Zhou, Ruicheng Zhang +5

Tsinghua University, China · Mohamed bin Zayed University of Artificial Intelligence, UAE

Virtual Try-On Video Diffusion Models Controllable Video Generation Temporal Consistency in Video Generation

Sep 30, 2026cs.CV

TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation

Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generate, the model must infer and reconstruct a highly specific occluded background entirely from the surrounding context. Existing training-free methods struggle with this because their editing mechanisms act primarily as localized erasers. They fail to actively synthesize the missing background details and often leave behind ghosting artifacts. To solve this, we propose TripleFlow, a training-free framework that tightly couples erasure and generation. It coordinates a source flow, a residual flow, and a synthesis flow throughout the entire process. By reusing a single target prediction, the residual flow isolates and suppresses the object, while the synthesis flow independently reconstructs the occluded background. Crucially, TripleFlow injects this newly synthesized background back into the editing trajectory at every step. This continuous feedback loop ensures that the generated structures actively guide the removal process, achieving seamless completion that is spatiotemporally consistent with the unedited scene. Extensive evaluations across five challenging benchmarks demonstrate that TripleFlow establishes a new state-of-the-art, significantly outperforming existing baselines in both reconstruction fidelity and temporal consistency.

Songhe Wang, Lifu Wei, Shuolin Xu +2

CSE Department, Penn State University · Department of Computer Science, The University of British Columbia, Canada · Department of Computing, Bournemouth University, United Kingdom +2

Video Editing Image Inpainting Temporal Consistency in Video Generation

Sep 30, 2026cs.CV

FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation

Long-horizon video generation requires models to effectively leverage an increasingly long generation history. As the generated history grows, retaining all previous content becomes increasingly expensive and redundant, making effective historical selection essential. Existing approaches often determine historical relevance based on the current content. However, information relevant to the present is not necessarily useful for future generation, while seemingly less relevant history may become important later. Our key insight is that historical information should be selected according to its relevance to future information needs. Capturing these needs does not require generating the full future; instead, a compact representation of what becomes important next is sufficient to guide historical selection. Building on this insight, we propose FrameMorrow, a prospective frame selector that predicts a small set of prospective tokens representing future information needs and uses them to identify relevant information from history. FrameMorrow selects explicit historical frames rather than model-specific internal states, enabling plug-and-play integration across diverse generators, including closed-source models, with little additional inference cost. We evaluate FrameMorrow across five benchmarks and 11 generative models spanning long-video generation, interactive generation, and action-conditioned world models. Extensive experiments demonstrate consistent improvements in long-range consistency, visual quality, and action alignment across diverse generation settings.

Bo Yin, Xiaobin Hu, Jiaqi Zhao +1

National University of Singapore · Harbin Institute of Technology (Shenzhen)

Long-Horizon Video Generation Memory-Augmented Video Generation Temporal Consistency in Video Generation

Sep 29, 2026cs.CV

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.

Byoungwoo Park, Jaemoo Choi, Juho Lee +1

KAIST · Georgia Tech

Video Diffusion Models Long-Horizon Video Generation Video Generation Autoregressive Video Generation Distribution Matching Distillation Temporal Consistency in Video Generation

Sep 29, 2026cs.CV

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/.

Weiqiang Wang, Zhuokun Chen, Yusheng Dai +5

Monash University · Vivix AI · Lancaster University

Long-Horizon Video Generation Streaming Video Generation Autoregressive Video Generation Temporal Consistency in Video Generation

Sep 29, 2026cs.CV

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

Chenjian Gao, Zhihao Hu, Jianqi Ma +3

MMLab, The Chinese University of Hong Kong · Tencent AIPD

Autoregressive Diffusion Long-Horizon Video Generation Diffusion Model Distillation Autoregressive Video Generation Temporal Consistency in Video Generation

Sep 29, 2026cs.CV

Honeycomb: Constant-Size Scene Memory Representation for Video World Models

Video world models require persistent scene memory to maintain consistency during long-horizon video generation. Existing spatial memories accumulate RGB observations or latent features, increasing storage requirements as generation proceeds. We introduce Honeycomb, a video world model built on HexMemory, our proposed low-rank representation for storing scene features in a fixed-size memory with a total of six spatial and spatiotemporal planes. A feed-forward writer maps each generated chunk into new plane features. As the spatial coverage or temporal range expands, we warp the previous planes while preserving their dimensions, then fuse them with the new features through confidence-weighted pooling and a learned residual correction. A reader retrieves latents from HexMemory to condition subsequent video generation. The writer processes only observations from the new chunk, avoiding per-scene optimization and repeated processing of the full history. Experiments on WorldScore and RealEstate10K demonstrate strong video generation quality and robust revisit consistency while keeping HexMemory feature storage constant throughout generation. Code and additional visualizations are available on our project page at https://jackswl.github.io/honeycomb/.

Jack Wei Lun Shi, Kaichen Zhou, Haoyu Chen +6

National University of Singapore · Harvard University · MIT +1

Long-Horizon Video Generation Memory-Augmented Video Generation Temporal Consistency in Video Generation Video World Models

Sep 29, 2026cs.CV

Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation

While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a major bottleneck lies in conditioning independently generated shots to preserve consistent characters, scenes, and objects throughout a story. Existing training-free approaches typically condition target shots using retrieved historical visuals. However, these references often suffer from severe informational mismatch, either introducing irrelevant contextual redundancy or failing to provide the full combination of required elements for the target shot. To resolve this, we present Complementary Retrieval-Augmented Prompting, an agentic framework that strategically aggregates a compact set of mutually supportive historical references to achieve complete and targeted conditioning for long-form video generation without retraining or modifying the underlying generator. Specifically, our framework explicitly models the visual elements required by each target shot by parsing the narrative script into a text-grounded visual element registry that tracks characters, objects, scenes, and their shot-level states. A VLM-annotated keyframe library further maps these elements to past visual observations. Guided by the required elements, our agent retrieves complementary references that maximize target-element coverage while minimizing historical noise. Finally, the retrieved references, structured element states, and grounding instructions are assembled into a unified prompt for the frozen video generator. This element-aware process provides comprehensive conditioning while remaining fully interpretable. Quantitative and qualitative evaluations on multi-shot story generation demonstrate that our method consistently outperforms recent-frame, memory-based, and entity-level retrieval baselines in cross-shot consistency and text-controllability.

Xianghan Wei, Xiaoda Yang, Zhi Wang +7

Long Video Generation Agentic RAG Multi-Shot Video Generation Temporal Consistency in Video Generation

Sep 29, 2026cs.CV

MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos

Despite rapid progress in video generation models, they still exhibit obvious motion deficiencies, often manifested as incorrect object motion. However, most existing video quality evaluations focus on aesthetic quality or text-video alignment. To address this gap, we study object-centric motion fidelity assessment, evaluating target objects along object consistency, motion continuity, and physical plausibility. To achieve this, we first introduce VidMotion, a diagnostic dataset of 6,879 videos with designated moving objects and fine-grained annotations including dimension-wise scores and failure causes. We further propose MotionInsight, a diagnostic evaluator that shifts assessment from implicit RGB-frame observation to explicit motion-space diagnosis. By constructing motion-aware representations, MotionInsight makes subtle motion deficiencies more observable. We also introduce motion-specific rewards during GRPO to transform observed motion into a diagnostic assessment. Experiments demonstrate that MotionInsight provides an effective basis for diagnosing object motion deficiencies, producing human-aligned scores along three dimensions and grounded explanations.

Jiahao Zhan, Yongrui Ma, Qunliang Xing +6

Physical Consistency in Video Generation Video Quality Assessment Temporal Consistency in Video Generation Video Generation Evaluation

Sep 28, 2026cs.CV

Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation

Long-horizon camera-controlled video generation requires recovering previously observed content from an ever-growing visual history. Existing approaches either search historical context implicitly or reconstruct it into persistent 3D memory, facing inefficient memory access or accumulated geometric errors. Our key insight is that geometry need not explain the scene--it only needs to determine where visual memory should be read from, while attention decides what should be recovered. Based on this insight, we introduce GEAR, a Geometry-Enabled Attention Routing framework that uses geometry as an explicit token-level address for visual memory. Rather than fusing historical observations into a persistent global 3D representation, GEAR retains them as frame latents and uses per-frame geometry only to establish token-level correspondences with target views, thereby avoiding persistent error accumulation from global fusion. Guided by these correspondences, Geometric Correspondence Attention (GCA) selectively injects geometrically matched historical features into noisy target patches during denoising. We further introduce an Invisible Octree to accumulate visibility evidence and reject geometrically plausible but occluded correspondences. Extensive experiments demonstrate that GEAR achieves state-of-the-art visual quality, precise camera control, and revisit consistency, enabling minute-long video generation along challenging trajectories.

Zesong Yang, Weikai Chen, Liyuan Cui +10

State Key Laboratory of CAD&CG, Zhejiang University · LIGHTSPEED · HKUST(GZ)

Camera-Controlled Video Generation Long-Horizon Video Generation Memory-Augmented Video Generation Temporal Consistency in Video Generation

Sep 28, 2026cs.CV

SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling

We present SubjectAnchor, a Subject-Aware Memory-to-Video paradigm for multi-shot storytelling in which the current shot is generated by conditioning on explicit visual memories extracted from previous shots. The objective is to preserve subject identity and scene consistency across cuts while retaining the controllability of shot-wise prompting. Built on Wan2.2-I2V-A14B, SubjectAnchor contains three key components: subject-related memory construction, subject-aware temporal rotary position encoding, and memory-aware attention partition. For each target shot, the method constructs a compact memory bank by tracing each required subject to its historical appearance and retrieving the most relevant precomputed keyframes. These memory frames are encoded into the model input as explicit visual conditions, while different subjects are assigned to separated negative temporal slots to reduce identity interference. In addition, memory-aware attention partition regulates the interaction between memory tokens and generated content within a shared backbone. This formulation preserves the appearance anchoring of explicit visual memory while remaining compatible with script-driven shot-by-shot generation. Experiments show that SubjectAnchor improves cross-shot identity consistency over representative memory-based and holistic baselines while maintaining competitive visual quality.

Xinyu Wang, Huafeng Shi, Zian Li +4

Shenzhen International Graduate School, Tsinghua University · Kling Team · Peking University +1

Video Diffusion Models Memory-Augmented Video Generation Identity-Preserving Video Generation Multi-Shot Video Generation Temporal Consistency in Video Generation

Sep 28, 2026cs.CV

From Static to Dynamic: On-Policy Distillation from Image to Video Diffusion Models

On-policy distillation (OPD) specializes pretrained video diffusion models through teacher supervision along the student's own generation trajectory. Although large video models are natural teachers, developing specialized video experts can require costly video data and training, while querying them incurs substantially higher latency than querying image experts. More readily available and cheaper to query, image experts offer a cost-effective alternative, particularly for largely temporal-agnostic capabilities such as aesthetics and OCR that admit frame-level supervision. However, heterogeneous image and video latent spaces prevent direct supervision of intermediate student states, while image experts lack cross-frame motion supervision, making temporal consistency vulnerable to frame-level improvements. In this paper, we propose MILD, a Motion-Preserving Image-to-Video Latent Distillation framework that transfers specialized image expertise while preserving pretrained video dynamics. MILD uses a learnable linear connector that aligns student latent states and predicted updates with those of image experts, enabling supervision transfer across heterogeneous latent spaces. We further constrain image-guided corrections around the pretrained student's predictions to preserve video dynamics and incorporate an optical-flow-based motion reward to improve motion quality and temporal consistency. Across specialized image experts and multiple video-student backbones, our method consistently outperforms video-teacher OPD baselines, with further studies demonstrating effective transfer across connector designs and heterogeneous architectures. These results establish image-to-video distillation as an effective route to improving video generation by drawing on the diverse and evolving capabilities of the image-generation ecosystem.

Bingqing Jiang, Li Luo, Zichao Yu +3

The University of Hong Kong · Cornell University

Cross-Modal Knowledge Distillation Video Diffusion Models Diffusion Model Distillation On-Policy Distillation Temporal Consistency in Video Generation

Sep 28, 2026cs.CV

Enhanced Video Text Editing with Trajectory-Aligned Glyph Rendering

Video text editing aims to replace or add text in a video while keeping the rest of the video unchanged, which requires the edited text to be correct in every frame and to move coherently with the scene. Despite the remarkable progress of video diffusion models, they struggle to reproduce exact stroke structures and often produce garbled or wrong characters, especially for characters with complex strokes. To address this, we propose a trajectory-aligned glyph rendering reference that provides explicit per-frame glyph guidance following the position and perspective of the text, and a depth-normalized recognizer feature supervision that supervises the generated text on multi-depth features of a frozen text recognizer with per-depth normalized errors, targeting stroke errors overlooked by the diffusion loss. We further build VTEdit, a benchmark of 288 real-scene clips with 440 annotated text trajectories covering text replacement and text addition, which will be publicly released to facilitate future research. Experiments on VTEdit show that our method outperforms image text editing methods, video editing methods, and commercial models in text accuracy and background preservation, achieving a sentence accuracy of 0.9408, and receives the highest preference in a user study.

Shulian Zhang, Xiangyu Shu, Wenbo Li +2

South China University of Technology · The Chinese University of Hong Kong · Huawei

Video Diffusion Models Video Editing Temporal Consistency in Video Generation

Sep 27, 2026cs.CV

StoryEngine: A State-Grounded Agentic Framework for Video Storytelling

Despite recent progress in agentic multi-shot video generation, producing coherent and consistent long-form stories remains challenging. Existing agentic pipelines typically rely on textual shot plans or previously generated pixels, yet lack an explicit mechanism for propagating the consequences of story events and maintaining the video world state across shots. As a result, missing visual details may be reconstructed inaccurately, while visual drift may propagate across subsequent shots, undermining both narrative coherence and visual consistency. To address these challenges, we propose StoryEngine, a state-grounded agentic framework for video storytelling. StoryEngine establishes a separation between authoritative semantic plans and unreliable visual observations. Specifically, StoryEngine maintains a structured representation of entity placement and story-relevant states, and propagates event-induced changes to define the intended start and end states of each shot. To visually realize these states, StoryEngine constructs canonical references for recurring entities and environments, and compiles state and visual constraints into executable render plans. Meanwhile, to realize these states correctly, a bounded evaluation-guided repair loop further corrects local state inconsistencies. Together, these mechanisms preserve causal story progression and prevent local visual errors from propagating across shots. To comprehensively evaluate long-form storytelling, we construct a benchmark across diverse scenarios and visual styles, with metrics assessing storytelling quality, narrative coherence, and visual consistency. Experimental results demonstrate that StoryEngine consistently outperforms state-of-the-art methods across all evaluation dimensions, validating its effectiveness for coherent and consistent video storytelling.

Yingrui Wang, Zeqing Wang, Yeying Jin

Tencent · National University of Singapore

Long Video Generation Agentic Video Generation Multi-Shot Video Generation Causal Reasoning in Videos Temporal Consistency in Video Generation