Temporal Consistency in Video Generation

Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generating chunk-by-chunk, each through a short sequence of denoising stages. To memorize chunks that are already generated, previous methods reconstruct a clean or less-noisy key--value (KV) cache by additional forwards to build the cache without advancing an output latent. However, every denoising forward itself already computes the in-flight KV of the current chunk. We introduce FlashForward, which directly reuses this cache to avoid the heavy cache-update-only model forwards. After the current chunk completes one denoising stage, its stage-specific cache is already available for the next chunk. Assigning one GPU to each stage therefore lets different chunks occupy different stages concurrently. This early availability has a quality cost: the resulting stage-matched history is noisy, causing appearance and motion drift among chunks. To complement it, FlashForward produces sparse auxiliary clean anchor latents before the corresponding region is generated so the generation trajectories can be stabilized by this two-sided conditioning. The two memories operate at different temporal scales: sparse clean anchor KV supplies coarse, long-range two-sided structural guidance, while dense stage-matched history preserves fine, recent evolution. With up to four GPUs, FlashForward runs $1.16$--$1.69\times$ faster than HiAR and $1.42$--$2.92\times$ faster than Self-Forcing for 16 FPS videos of 20 seconds or longer across 1.3B and 14B backbone scales at 480p and 720p. On VBench, for the 1.3B model at 480p, it achieves higher scores and remains stable at longer durations, demonstrating that FlashForward generates high-quality and temporally consistent videos across durations of 20s, 35s and 65s at a much faster generation speed.

Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environments. Autoregressive (AR) video generation extends visual sequences through causal rollouts. However, a fundamental bottleneck emerges: as the generated sequence expands, practical models must operate under strictly bounded context windows, storage, and computational limits. Consequently, critical historical information, e.g., entity identities, dynamic states, and intervention-induced causal changes, often leaves the active context long before its relevance diminishes. Overcoming this limitation and maintaining temporal persistence constitutes a fundamental memory problem. We present a systematic and comprehensive review of memory mechanisms in AR video generation. We formulate memory operationally as persistent historical information maintained across outer AR steps, capable of influencing future generation even after the originating evidence is no longer locally accessible. Building upon this unified framework, we organize the literature through five complementary perspectives: (I) Forms, the representational carriers of history; (II) Functions, the specific semantic and physical information requiring preservation; (III) Operations, the lifecycle of writing, reading, updating, managing, and integrating memory; (IV) Learning, the optimization of memory behaviors under closed-loop rollouts; and (V) Evaluation, the paradigms for diagnosing genuine memory capabilities. We conclude by synthesizing open challenges, including composable and resource-aware memory architectures, trustworthy state updating, self-rollout learning, and standardized evaluation. By bridging representations, mechanisms, and learning paradigms, this paper establishes a structured foundation for developing reliable, memory-conditioned video generation systems.

Recent advances in text-to-video generation have enabled high-fidelity visual synthesis, yet realistic motion remains challenging. Generated videos may exhibit temporal discontinuities, inconsistent action progression, and structural distortions during complex movements. Even when individual frames appear realistic, the underlying motion may evolve in inconsistent or implausible ways. Standard generative objectives provide limited motion-specific supervision, leaving motion evolution insufficiently constrained. In this paper, we propose MotionSpec, a motion supervision framework centered on Spectral Trajectory Consistency (STC). STC constructs dense anchor-relative motion trajectories and transforms them into motion spectral volumes via a temporal Fourier transform. By aligning the spectral amplitude and phase of predicted and target trajectories, STC constrains both motion strength across temporal frequencies and the temporal organization of motion. To complement this trajectory-level supervision, we introduce Local Flow Consistency (LFC), which aligns consecutive-frame optical flow between predicted and target videos to stabilize local motion transitions. Experiments demonstrate that MotionSpec consistently improves motion consistency, temporal coherence, and plausibility while preserving visual fidelity.

Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cache makes KV cache memory a major deployment bottleneck, which motivates low-bit quantization study for efficiency. Existing 2-bit KV cache quantization methods can achieve nearly lossless performance on VBench, however, when applied to video world models, we find they still cause severe temporal flickering and visual degradation. Meanwhile, deeper investigates show that Key quantization produces smaller reconstruction errors than Value, but surprisingly leads to larger output degradation. We trace this discrepancy to attention in video world models: Key perturbations can change the attention logits, and shift the temporal-spatial tokens selected by Queries. These observations motivate us to preserve attention logits and temporal-spatial token selection during KV cache quantization. To address this issue, we present QuantWM, a training-free 2-bit KV cache quantization framework for video world models. QuantWM introduces two complementary techniques to mitigate the attention shifts. Firstly, quantization-sensitivity-aware clustering (QSAC) jointly considers historical Query sensitivity and residual ranges to select INT2-friendly Key centroids, which reduces quantization errors in channels that are more critical to attention. In addition, principal-subspace attention compensation (PSAC) restores the remaining Key errors along the dominant Query subspace using low-rank projections, which provides a direct and efficient correction to stabilize attention logits. Experiments on LingBot-World-v2, HY-World 1.5, Matrix-Game-2, Longcat-Video and Causal-Forcing demonstrate that QuantWM significantly improves visual quality and temporal consistency, while outperforming existing methods across benchmarks with up to 6.20 KV cache memory compression and limited additional overhead.

Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world model that learns a camera-queryable implicit 3D-aware memory for this purpose. The key insight is to let the requested viewpoint shape how multi-view evidence is compressed into the video generator's limited token budget. Trained jointly with the video generator, a memory encoder and pose-conditioned readout module integrate historical observations into a fixed set of target view-specific tokens before denoising, without explicit depth-based correspondences. By combining this memory with recent temporal context and few-step distillation, WorldCrafter enables streaming scene exploration from a single input image or text prompt. Experiments across static and dynamic scenes show substantial gains in long-horizon consistency and camera-control accuracy while preserving visual quality during minute-scale exploration.

We present a compact geometry-native latent space as a shared foundation for perception and generation. Visual generators can produce photorealistic frames without preserving a consistent 3D scene. We argue that this is not only a modeling problem but also a representation problem: generators typically evolve appearance-centric latents, while perception models recover geometry in a semantically rich space that encodes cross-view structure. Rather than adding geometry as another output, we reparameterize a geometry foundation model's features into a compact latent space for generation. We realize this shift with the geometry-native autoencoder (GAE), whose latent is jointly decodable to appearance, depth, cameras, and point maps. With this state, a standard conditional flow supports diverse generation tasks. In controlled comparisons that hold the generator and training protocol fixed, replacing the latent with GAE improves both visual quality and independently measured 3D coherence: FVD falls by $12.7\%$ and $23.1\%$ on RealEstate10K and DL3DV, and camera-trajectory error is halved on RealEstate10K. Together, these results show that the latent space is central to geometry-consistent generation and can serve as a shared interface between perception and generation.

Autoregressive (AR) video generation degrades over long horizons due to an overlooked train-inference discrepancy we term KV eviction mismatch: models train on short clips where all context frames reside in the KV cache, but at inference, memory constraints force distant frames to be evicted from the KV cache - removing context the model was conditioned on. Rather than simulating eviction via context truncation - which discards temporal information the model still needs and degrades motion coherence - we keep the context but while progressively reducing the influence of distant frames, making their eventual eviction negligible. To guide this design, we introduce the positional response $R( Δ, \, t_{\text{denoise}})$, a perturbation-based sensitivity measure revealing that context influence decays steeply with temporal distance and varies systematically across denoising steps. Motivated by this analysis, we propose Recency Forcing, which applies a non-positive, timestep-dependent bias, termed Temporal Response Bias (TRB), on pre-softmax attention logits derived directly from $R$, closing the train-inference gap without modifying context length or training objectives. We further introduce Biased Attention Reparameterization (BAR), an exact reformulation that moves the bias outside the softmax, making TRB a standard FlashAttention call at zero overhead. Recency Forcing operates in both training-free mode and training-based mode. Experiments on VBench and VBench-Long demonstrate state-of-the-art long-horizon generation quality at no additional inference cost.

We study the challenge of sign language video mimicking: given a driving video and a single reference frame, synthesize a video where the target signer reproduces the source motion while preserving identity and linguistic form. Prior pipelines entangle rigid motion, non-rigid deformation, and view-dependent completion in a monolithic generator, causing handshape drift and spatio-temporal instability. We present SignMimic, which (i) applies a TNet-based model to study SE(3) rigid canonicalization to stabilize global pose, (ii) performs non-rigid adaptation in a canonical space to preserve fine-grained articulators (hands/face) and coarticulation via NIF2D, and (iii) uses Pose-MAE-style completion before conditional video diffusion. This factorization injects geometric and linguistic priors, yielding shape and spatio-temporal consistency. On several large-scale datasets (ASL 50K, How2Sign, CSL News), SignMimic achieves state-of-the-art-level performance on video quality, identity similarity, and frame continuity while also achieving minimal loss when performing back translation (SLT) on generated videos. Ablations confirm the role of rigid canonicalization, non-rigid adaptation, and completion. Code is available at https://anonymous.4open.science/r/UniSignMimicTurbo-6088; model checkpoints and video examples will be released.

Autoregressive video world models enable interactive, long-horizon exploration, but flexible control remains challenging. Exploring a source video from new viewpoints requires the generated rollout to remain synchronised with the recorded event, place observed content in the requested view, plausibly complete newly exposed regions, and recover previously generated appearance on revisits. Existing methods typically address these requirements through task-specific modules or additional training. We present World in World, a training-free inference-time interface that converts heterogeneous control evidence into camera- and time-labelled clean visual states, which are read through the native self attention of a frozen causal video model. The evidence comprises source-video observations, target-view scene projections, geometry renderings that guide completion of newly exposed subject regions, and retrieved generated states beyond the rolling cache. Each evidence source carries token-level support and its own availability schedule. A correspondence router combines persistent point identities with geometry to establish token correspondences, guiding supported queries towards matching source-video tokens. Evidence-wise attention CFG (EWA) then independently regulates each auxiliary channel's additional contribution using attention responses from the same denoising forward pass. The shared interface supports camera-controlled rerendering, long-horizon revisiting, and human-motion transfer with the same frozen backbone. We evaluate World in World on camera-controlled video rerendering under diverse viewpoint changes, assessing perceptual quality, temporal consistency, and camera-following accuracy.

Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual attributes such as identity, scene layout, motion, and fine details across time. Existing training-free methods mainly strengthen cross-frame attention or analyze local attention entropy, but these views do not reveal whether temporal interactions stay in a healthy transport regime. In this work, we study video generation through the perspective of Temporal State Transport. We introduce Spectral Tension, a signed diagnostic that compares local attention diffuseness with global spectral diversity, and use it to identify two opposite temporal failures: fragmented transport and over-mixing hotspots. Based on this diagnosis, we propose Spectral Transport Homeostasis, a training-free regulator that softly corrects pathological temporal states while largely preserving balanced ones. Experiments on pretrained video generation models show that the original model often occupies imbalanced temporal regimes, whereas our method selectively applies larger corrections to the worst temporal hotspots and improves temporal consistency and visual quality without finetuning. Code: https://github.com/lytang63/temporal-state-transport

Chunk-autoregressive video world models typically condition each generated chunk on one action. An action received during sampling must therefore wait for the next chunk, condition future solver evaluations on a state produced under the previous action, or trigger rollback that repeats completed evaluations. We introduce ActionSplice, an inference framework that formulates this problem as Counterfactual State Transport (CST). A lightweight corrector transports the interrupted backbone-native representation toward the matched state induced by the revised action at the same solver step. The world model and sampler remain frozen, and sampling resumes without replaying completed evaluations. The retargeting variant $\mathrm{CST}*{R}$ updates the entire active chunk, while the temporal-splicing variant $\mathrm{CST}*{T}$ preserves a temporal prefix and updates only the suffix. Across minWM-Wan Action2V and HY-WM1.5, $\mathrm{CST}*{R}$ reduces rollback-relative LPIPS by 61.5% and 75.9% relative to direct condition swapping. $\mathrm{CST}*{T}$ reduces suffix LPIPS by 56.1% and 77.5%, respectively, while providing $2.73\times$ and $1.69\times$ pixel-ready speedups over waiting. Under the HY-WorldPlay protocol, $\mathrm{CST}_{R}$ obtains a PSNR of 25.66 dB, an SSIM of 0.6902, and an LPIPS of 0.1337 against the original rollout.

Long-form narrative-to-film generation requires shot-level controllability and cross-clip consistency in both visual identity and character behavior-requirements that remain difficult to satisfy with current prompt-based workflows. A core reason existing workflows remain brittle is the lack of a structured intermediate layer between scripts and video models, especially when screenplays are underspecified at key cinematic decision points. We introduce a structured orchestration layer for film-oriented script-to-video generation, implemented as a multi-agent framework that operates between scripts and off-the-shelf video generators. The layer is centered on FilmDSL, a film-oriented domain-specific language that makes cinematic constraints explicit, including shot and camera directives, asset and continuity requirements, and persona cues, so that agents coordinate through a shared structured specification for planning, generation, critique, and repair. Specifically, a generation agent constructs asset packs and storyboard keyframes that anchor composition before clip-by-clip synthesis, while a critic agent produces structured QA signals and triggers targeted refinement without retraining the base model. Experiments on TV-style segments show improved controllability and consistency over text-only and reference-only baselines.

Video virtual try-on (VVT) aims to generate realistic videos of a person wearing a target garment. Recent methods leverage a keyframe-driven video generation paradigm to improve in-the-wild performance, yet they still rely on masks to localize try-on regions, making them vulnerable to large motions and severe occlusions. Although mask-free image-based try-on methods have shown promising results by leveraging large-scale pseudo data, extending this paradigm to videos remains difficult, as constructing video-level pseudo data is prohibitively expensive. Furthermore, coarse keyframe sampling and the scarcity of multi-view try-on data limit existing keyframe-driven methods in maintaining garment consistency and handling diverse try-on tasks. To address these challenges, we propose BooM-VVT, a mask-free VVT framework built upon the keyframe-driven paradigm. To achieve mask-free VVT, we introduce a multi-stage training strategy that leverages image-level pseudo data for mask-free localization learning, substantially reducing the need for costly video-level pseudo data. To improve garment consistency, we propose Garment-Sensitive Keyframe Sampling, which selects keyframes based on garment-relevant body regions to better capture garment appearance. We further introduce Frame-Shared 3D-RoPE to establish spatiotemporal correspondences between keyframes and target video frames for accurate garment-detail transfer. Finally, we construct OmniView, a large-scale multi-view try-on dataset to support reliable try-on video generation under complex camera viewpoints and diverse try-on tasks. Extensive experiments demonstrate that BooM-VVT achieves superior temporal consistency and garment fidelity over existing methods. Project page: https://boomvvt.github.io/boomvvt.

Video generators build long videos by composing shorter parts, either by generating segments one after another or by autoregressively extending chunks. Each new part usually depends on memories of historical observations, such as recent frames, selected key frames, memory banks, or cached features. These memories preserve visible evidence from the past, but current generators do not reliably turn such evidence into a world-state interface: what holds in the video world after previous actions and how it should change under the next prompt. A past frame remains valid history, but it may not describe the state needed by the next segment; some states must instead be inferred from occluded or implicit changes rather than copied from a directly observed frame. This creates a simple but overlooked question for video continuation: given a previous video, its prompt, and a new prompt, can a model generate a continuation that reflects the state determined by both the historical video and the new prompt? To answer this question, we introduce Statebench, a benchmark that targets this gap by testing continuations over three state categories: past-visible states, occluded-process states, and complex-transition states. We further propose Stateagent, which explicitly maintains an entity-state representation, updates it under the new prompt, grounds the predicted post-action state as a future end frame, and renders the next video. Experiments show that our method improves controlled video continuation by raising the all-case state score (SCS-All) from 45.2 to 69.3, and also benefits story generation at the one-minute scale. Code is avaliable at https://github.com/AMAP-ML/StateAgent.

Training-free, camera-controlled novel view synthesis from a single image using pre-trained video diffusion models often becomes unstable under large camera motion and long generation horizons. Existing approaches commonly combine several inference-time components, making it unclear which design choices are most important for stability. We show that the main source of stability is simple. Decomposing camera motion into small autoregressive steps limits per-step geometric distortion and reduces error accumulation. A controlled camera-step study shows that performance remains stable for small motions and degrades more strongly as the per-step motion approaches $18$-$20^\circ$. We further evaluate geometry-constrained spatial attention and low-frequency appearance anchoring as supporting refinements, together with an efficient registration-free warping pipeline. Across RealEstate10K and MegaScene, CamTrol++ improves temporal and geometric consistency, downstream 3D reconstruction quality, and generation efficiency over training-free baselines. The method remains effective for 56-frame generation and under substantial controlled depth corruption. These results show that careful control of camera motion at inference time can substantially improve the stability of camera-controlled novel view synthesis without retraining or modifying the diffusion backbone.

Commercial short-drama production follows a multi-stage chain: script, storyboard, keyframe imagery, shot-level video, and the finished short drama. Most existing benchmarks evaluate solely the video-generation stage using pre-authored inputs instead of real upstream pipeline outputs. This leaves two critical questions unanswerable: whether each stage adheres to the original script intent (rather than only its immediate input prompt), and whether disparate shots remain coherent after assembly into multi-episode releases. We present DramaChain Bench, the first short-drama benchmark that evaluates every stage of the complete production chain. It is built upon three in-house systems sharing one dimension system, DramaChain Dimensions: five evaluation axes instantiated at every stage, resolving into 63 leaf dimensions. DramaChain Agent is calibrated against commercial short-drama platforms in both workflow and finished short-drama quality, enabling stage-wise fair comparison across models. DramaChain Labeling System has each of the 5,785 items scored independently by three professional annotators, with all defects spatio-temporally localised and selected from a predefined defect list. This process produces 17,488 valid scores and 255,925 traceable attribution records. The human annotations confirm that upstream defects cascade across the pipeline, demonstrating that final episode quality is not governed by video generation alone. DramaChain Agentic Judge then scores every leaf dimension automatically, gathering evidence over multiple agentic rounds before judging against a per-item checklist; it reproduces the model ranking at a mean PLCC of 0.918, enough to admit new models at no annotation cost.

Video virtual try-on aims to transfer a target garment onto a moving person across video frames. Current methods rely on human parsing masks or pose keypoints that frequently fail under large motions and occlusions, causing boundary artifacts and temporal inconsistency. A further limitation is that most approaches rely solely on attention mechanisms for temporal modeling, providing no explicit motion supervision. We propose FlowVVTON, a mask-free framework that eliminates parsing mask dependency entirely. Optical flow is used solely as a training-time supervision signal: a flow-warped latent loss, applied across all layers of the generation model, enforces multi-scale temporal consistency by aligning adjacent-frame features under explicit physical motion constraints. A two-stage training strategy establishes mask-free spatial alignment before introducing flow-guided temporal supervision. Experiments on TikTokDress show that FlowVVTON outperforms baselines by substantial margins, particularly in temporal consistency (5.7$\times$ VFID-R improvement over SwiftTry), while requiring no segmentation masks, pose keypoints, or region annotations at any stage.

Geometry-aware video object scaling aims to anisotropically resize the object along object-centric axes while preserving geometric plausibility, temporal coherence, and background consistency. Existing text-guided methods mainly operate in the 2D image plane, while depth-guided approaches provide coarse control and mesh-based methods require costly 3D reconstruction. We present a progressive two-stage training framework that decouples geometry-aware foreground transformation from background preservation and realistic video composition, without mesh-pixel alignment and explicit 3D reconstruction at inference. In both stages, geometrically perturbed pseudo-sources are constructed from real videos, while the original complete videos are retained as reconstruction targets. The first stage uses planar transformations to learn robust foreground-background composition, whereas the second introduces object-centric 3D deformation guidance for geometry-aware scaling. This pseudo-source reconstruction formulation enables real-video synthesis without paired real-world scaling targets. We construct complementary paired-geometry and real-background benchmarks and further evaluate on in-the-wild videos. Extensive experiments demonstrate superior geometric consistency, foreground fidelity, and background preservation, together with faster and more practical inference than methods requiring explicit 3D reconstruction.

Latent diffusion models have recently advanced video frame interpolation by synthesizing intermediate frames between input images. However, handling large temporal gaps and complex motion remains challenging, often resulting in motion blur, structural distortions, and temporal inconsistencies. Event cameras provide high-temporal-resolution motion cues that are well suited for bridging these gaps and improving interpolation quality. To exploit this advantage without training an event-assisted model from scratch, we propose an adapter-based framework that incorporates event-derived cues into a pre-trained image-to-video diffusion model with minimal architectural changes. Specifically, our method leverages Image Warped Events (IWEs) and bidirectional sparse optical flow to provide spatially and temporally aligned guidance during generation. By injecting these event-guided structural and motion cues into the diffusion process, our approach reduces interpolation artifacts and improves both reconstruction fidelity and temporal coherence. Experimental results on real and synthetic benchmarks show that our method consistently outperforms existing state-of-the-art approaches. The project page is at https://joseph-lin-tech.github.io/BridgeEventDiT-VFI/.

Streaming video generation holds strong potential for world modeling, where future frames must be inferred online sequentially to form a continuous video stream. However, streaming video diffusion models introduce a fundamental train-inference mismatch: inference follows a specialized denoising order, whereas advanced training strategies typically require diverse noise-level configurations. To address this trade-off between train-inference consistency and training coverage, we reformulate the video diffusion sampling as a frame-indexed stochastic process over noise levels. Within this stochastic process space, we construct a continuous training trajectory along which the sampling schedule progressively evolves from independent sampling to inference-consistent sampling. We further introduce a joint calibration algorithm and a temporal correlative sampling algorithm to ensure trajectory smoothness and cross-frame correlation. Building on these designs, we propose Stream Forcing, a unified training framework for streaming video generation that balances training sufficiency and inference efficiency. Extensive experiments demonstrate that Stream Forcing significantly improves generation quality with a 36.6% FVD improvement on the UCF-101 benchmark. Furthermore, our method facilitates robust zero-shot extrapolation to long-horizon video generation with a 27.9% FVD improvement on the UCF-101 benchmark.

Generating cross-shot videos that are logically connected is essential for content creation. Currently, most cross-shot video-generation workflows, such as short-drama production, still rely on isolated textual scripts or explicit reference images to specify the generated content. Consequently, when user instructions are underspecified or ambiguous, a generated clip may appear visually plausible on its own but fail to align with the overall narrative, leading to disjointed content. We argue that achieving cross-shot logical coherence in video generation requires establishing logical connections across shots and maintaining visual consistency. To this end, we propose LogiShot, which incorporates information through two complementary paths: 1) LogiShot jointly encodes the context video and other conditioning signals, yielding dense multimodal cues that provide visual-semantic evidence for cross-shot generation; 2) the model maintains a visual memory of the context video throughout generation to preserve visual consistency across shots. Additionally, we construct a dataset with 110K samples and a dedicated benchmark for evaluating cross-shot logical coherence. Experiments demonstrate that LogiShot consistently outperforms existing baselines in terms of logical coherence across multiple shots. Model and data will be made publicly available.

Generative traffic video forecasting aims to synthesize long-horizon, temporally coherent future videos of traffic scenes from a short observation history and textual descriptions. In this paper, we present CosmosAlign, a generative traffic video forecasting framework built upon the pretrained Cosmos3-Nano world foundation model. Our approach is motivated by the observation that successfully adapting large pretrained world models to downstream forecasting tasks depends primarily on distribution alignment rather than increased model capacity. To this end, we propose a two-stage LoRA adaptation strategy that first aligns the conditioning-mode distribution with the target forecasting task, and then aligns the training captions with the model's native structured prompting interface through an LLM-based re-captioning pipeline. During inference, we further improve prediction quality using a fully training-free procedure consisting of consensus-based medoid sample selection and motion-adaptive blending of static scene regions. CosmosAlign achieves a final score of 76.49 on the AI City Challenge 2026 Track 5 benchmark, ranking first on the final leaderboard. Our code is publicly available at https://quangminhdinh.github.io/CosmosAlign/.

We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames. However, we find that models can no longer reliably address stored content once rollouts extend beyond the training horizon, because temporal Rotary Positional Embeddings (RoPE) offsets then fall outside the range seen during training and the model struggles to retrieve the relevant visual information through attention. Moreover, naively compressing the cache in the RoPE-rotated space corrupts memory by averaging together incompatible positional phases. To address this, we propose WorldTrace, a training-free memory framework for long-horizon visual persistence. WorldTrace keeps compressed memory addressable by assigning each summary slot a distinct, in-distribution virtual position. Within this addressable cache, we study two memory compression approaches: WorldTrace-Field compresses history for temporal coherence, while WorldTrace-Landmark stores verbatim scene traces at detected transitions for episodic recall. We further introduce LoopBench, a benchmark evaluating whether a compressed cache can reconstruct a previously visited scene after a long detour. WorldTrace-Field improves temporal consistency by +15.5%, and WorldTrace-Landmark improves episodic recall by +19.5% on LoopBench, extending visually persistent generation without retraining.

Controllable surgical world models can provide a generative foundation for surgical artificial intelligence and simulation by synthesizing realistic instrument--tissue interactions. However, existing methods lack a unified multimodal control paradigm, while direct fusion of heterogeneous visual conditions often causes anatomical distortion, instrument appearance drift, and temporally inconsistent interactions. In this work, we propose {Surg-UniWorld}, a unified surgical world model with multimodal control experts. Surg-UniWorld first constructs a {Hierarchical Surgical Anchor} from first-frame appearance and hierarchical semantic masks to preserve persistent scene identity, anatomical organization, and interaction boundaries. {Anchor-Relative Modality Experts} then interpret edge, depth, and optical-flow evidence relative to the shared anchor, capturing complementary boundary, geometric, and motion information. A {Multimodal Control Expert} further performs contribution-preserving stage-wise composition of the activated modality increments and generates control hints for the Wan2.2 video diffusion backbone. To support multimodal surgical world modeling, we further construct Cholec80-SurgWAM, a benchmark for controllable surgical video generation. Extensive experiments demonstrate that Surg-UniWorld consistently outperforms existing controllable video generation methods and surgical world-model baselines in generation quality, temporal consistency, and multimodal controllability.

Emotion shapes how viewers interpret a scene, yet existing video generators entangle global atmosphere, affect-bearing semantic cues, and temporal progression within a single text condition. We present EmoWorld, a framework that decouples these factors within a frozen flow-matching video diffusion transformer (Video DiT). A one-time preparation stage extracts layer-specific affect directions and a reusable cue library from geometry-preserving neutral and emotion-edited panoramas. At inference, Visual Atmosphere Steering (VAS) injects atmosphere directions into hidden states, Semantic Affective Steering (SAS) isolates a separately scalable prompt residual for semantic cues, and Temporal Affective Steering (TAS) interpolates endpoint residual fields across denoising and video time. On Wan2.2, VAS improves target-emotion alignment by 19% while reducing a temporal-fluctuation proxy by 48%; SAS improves target-emotion alignment by 37% and increases detected affect-bearing cues by 36%; and TAS improves transition monotonicity by 15% over the strongest baseline. EmoWorld is evaluated across 27 emotion categories in text-to-video and image-to-video settings, demonstrates portability across multiple Video-DiT backbones, and supports camera-conditioned composition without updating generator parameters.

Recently, diffusion models have made great progress in video generation. However, most existing video diffusion models are trained with short videos, and degrade when extrapolated to long videos, struggling to maintain long-range temporal coherence while retaining diverse motions. To generate consistent, high-quality and dynamic long videos, we propose Diff-VF, a training-free, plug-and-play and model-agnostic framework that converts existing short-video diffusion backbones into long-video generators without modifying or fine-tuning the base model. Diff-VF couples three complementary strategies: Hybrid Noise Initialization (HNI) to constrain global semantics, Weighted Window Sampling (WWS) to remove inter-window discontinuities, and Temporal Extended Sampling (TES) to establish long-range dependencies with a timestep-varying fusion. We further extend Diff-VF to long-video enhancement via Skip Residual Guidance that balances fidelity and realism through timestep-dependent guidance. VBench-Long evaluation results show that Diff-VF achieves a more favorable balance between temporal coherence and motion diversity than base models and recent training-free long video generation baselines, including FreeNoise, FreeLong, and RIFLEx, while maintaining competitive frame-wise quality. Experiments on two base models demonstrate the applicability to video diffusion models with different spatial-temporal modeling strategies. Extensive ablations validate the contribution of each component and hyperparameters.

Autoregressive continuation provides a natural path toward minute-scale audio-visual generation by repeatedly extending a short-window generator conditioned on previously generated video and audio. However, models are trained on clean ground-truth histories, while inference relies on their own generated histories, where accumulated errors cause identity drift, over-smoothing, and audio-visual desynchronization. Recent methods reduce this mismatch by reusing prediction residuals as synthetic corruption, but we observe that the effectiveness of residual correction critically depends on the flow-matching noise level at which residuals are produced. We propose Vorch-Director, a noise-level-aware residual correction strategy that associates each residual with its originating noise level and injects residuals from matched noise regimes during training. By aligning injected errors with the denoising process, Vorch-Director produces more realistic autoregressive histories while retaining efficient teacher-forcing training. Built on the audio-visual LTX-2 diffusion transformer, Vorch-Director further introduces task embeddings to distinguish historical video, reference images, and target video, enabling unified conditioning for long-horizon generation. Together with a clean conditioning sink and mixed-task training, Vorch-Director supports multi-shot, multi-subject, reference-guided audio-visual long-video generation. We evaluate Vorch-Director on ST-Bench and introduce a new long-horizon audio-visual benchmark with metrics for quality drift and long-range consistency. Extensive experiments demonstrate improved stability and audio-visual fidelity over strong baselines.

Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame. However, these clean frames leak excessive local details, which causes the model to take shortcuts, resulting in compromised temporal semantics and dynamics. Inspired by the perspective of diffusion as masking, we explore the impact of noisy contexts on few-step autoregressive generation. Yet, simply applying contexts with the same noise levels provides insufficient guidance, leading to poor temporal consistency. To resolve this dilemma, we introduce In-Context Forcing, a progressive autoregressive paradigm that utilizes contexts with decreasing noise levels. By applying less masking to distant frames and more masking to adjacent ones, this approach provides adaptive guidance, effectively ensuring both robust temporal consistency and high inter-frame dynamics. Furthermore, by decoupling the strict dependence on previous clean frames, our paradigm enables cross-frame parallel denoising, achieving substantial inference acceleration without sacrificing performance. Extensive experiments on VBench demonstrate that our method significantly outperforms state-of-the-art approaches in both visual fidelity and inference speed.

Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present JoyAI-Video-Edit, a 16B-parameter autoregressive diffusion framework for real-time, open-ended video editing without access to future frames or a predefined video duration. Our method combines chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation (SA-DMD), and Long-Horizon Autoregressive Distillation to reduce train--inference mismatch, preserve source fidelity during two-step generation, and mitigate accumulated temporal drift. Extensive automatic and human evaluations show that JoyAI-Video-Edit substantially outperforms existing streaming editors and remains competitive with strong offline systems on both short and long videos. The complete system achieves end-to-end 720p video editing at approximately 30 FPS on a single Nvidia B200 GPU. Code is available at https://github.com/jd-opensource/JoyAI-Video-Edit.

We present LiveLight, the first diffusion-based framework for real-time streaming video relighting with interactive 3D lighting control. Achieving this is non-trivial, as it requires overcoming three critical challenges: effectively injecting dynamic 3D lighting into a diffusion model, maintaining high-fidelity generation under an extremely low NFE (Number of Function Evaluations) budget for real-time speed, and facilitating continuous streaming for interactive control. To address these pain points, we propose three key designs. First, for accurate lighting injection, we propose a lightweight adapter that feeds Multi-Plane Light Irradiance (MPLI) conditions-depth-aware irradiance maps encoding 3D lighting geometry-directly into the diffusion backbone. Second, to prevent rendering quality degradation at low NFEs towards real-time distillation, we introduce a geometry-guided feedback branch. This training-time constraint leverages a frozen geometry estimator to enforce depth- and normal-consistent relighting, ensuring geometrically plausible shading without adding inference overhead. Finally, to enable streaming interaction, we develop a progressive rolling-window strategy that maintains a denoising ladder of latent chunks at varying noise levels. By propagating intermediate states, this strategy guarantees temporal coherence and supports arbitrarily long video relighting with per-frame reference refresh. Extensive experiments on real-world and synthetic benchmarks demonstrate that LiveLight achieves state-of-the-art relighting quality while running at real-time speed, significantly outperforming offline baselines in temporal stability, lighting controllability, and user preference. To foster real-time interactive relighting research, we will publicly release our models, training data, and synthetic data generator.