Video Diffusion Models

Text-to-video diffusion models deliver impressive results but remain slow because of the sequential denoising of 3D latents. Existing approaches to speed up inference either require expensive model retraining or use heuristic-based step skipping, which struggles to maintain video quality as the number of denoising steps decreases. Our work, CHAI, aims to use cross-inference caching to reduce latency while maintaining video quality. We introduce Cache Attention as an effective method for attending to shared objects/scenes across cross-inference latents. This selective attention mechanism enables effective reuse of cached latents across semantically related prompts, yielding high cache hit rates. We show that it is possible to generate high-quality videos using Cache Attention with as few as 8 denoising steps. When integrated into the overall system, CHAI is 1.65x - 3.35x faster than baseline OpenSora 1.2 while maintaining video quality.

Sketching is inherently sequential: strokes are drawn progressively to explore and refine ideas. Yet most generative approaches treat sketches as static images, ignoring the temporal process underlying creative exploration. Modeling this sequential structure remains challenging: prior methods either rely on large-scale human-drawn datasets with limited diversity, or use large language models (LLMs) to produce drawing instructions, often at the cost of visual fidelity. We present VideoSketcher, a method for generating high-quality sketching processes by adapting pretrained text-to-video diffusion models to the sparse, continuous nature of sketch formation. Our key insight is that LLMs and video diffusion models offer complementary strengths: LLMs act as semantic planners that decompose concepts into step-by-step instructions, while video diffusion models serve as powerful "renderers" that translate them into temporally coherent sketch sequences. We introduce a two-stage fine-tuning strategy that decouples temporal structure from visual appearance: stroke ordering is learned from synthetic shape compositions, while style is distilled from as few as seven hand-drawn examples. Despite minimal supervision, our method can generate diverse, high-quality sequential sketches that faithfully follow specified drawing orders. Our framework naturally extends to brush style control and autoregressive generation, supporting artistic applications.

State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce DreamZero, a World Action Model (WAM) built upon a pretrained video diffusion backbone. Unlike VLAs, WAMs learn physical dynamics by predicting future world states and actions, using video as a dense representation of how the world evolves. By jointly modeling video and action, DreamZero learns diverse skills effectively from heterogeneous robot data without relying on repetitive demonstrations. This results in over 2x improvement in generalization to new tasks and environments compared to state-of-the-art VLAs in real robot experiments. Crucially, through model and system optimizations, we enable a 14B autoregressive video diffusion model to perform real-time closed-loop control at 7Hz. Finally, we demonstrate two forms of cross-embodiment transfer: video-only demonstrations from other robots or humans yield a relative improvement of over 42% on unseen task performance with just 10-20 minutes of data. More surprisingly, DreamZero enables few-shot embodiment adaptation, transferring to a new embodiment with only 30 minutes of play data while retaining zero-shot generalization.

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

Many training-free sparse attention methods are effective for accelerating diffusion models. Recently, several works suggest that making sparse attention trainable can further increase sparsity while preserving generation quality. We study three key questions: (1) when do the two common masking rules, i.e., Top-k and Top-p, fail, and how can we avoid these failures? (2) why can trainable sparse attention reach higher sparsity than training-free methods? (3) what are the limitations of fine-tuning sparse attention using the diffusion loss, and how can we address them? Based on this analysis, we propose SpargeAttention2, a trainable sparse attention method that achieves high sparsity without degrading generation quality. SpargeAttention2 includes (i) a hybrid masking rule that combines Top-k and Top-p for more robust masking at high sparsity, (ii) an efficient trainable sparse attention implementation, and (iii) a distillation-inspired fine-tuning objective to better preserve generation quality during fine-tuning using sparse attention. Experiments on video diffusion models show that SpargeAttention2 reaches 95% attention sparsity and a 16.2x attention speedup while maintaining generation quality, consistently outperforming prior sparse attention methods.

Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a heuristic split that assigns computations to the sparse or linear branch based on attention-weight magnitude, which can be suboptimal. Additionally, (ii) after formally analyzing the attention error in SLA, we identify a mismatch between SLA and a direct decomposition into sparse and linear attention. We propose SLA2, which introduces (I) a learnable router that dynamically selects whether each attention computation should use sparse or linear attention, (II) a more faithful and direct sparse-linear attention formulation that uses a learnable ratio to combine the sparse and linear attention branches, and (III) a sparse + low-bit attention design, where low-bit attention is introduced via quantization-aware fine-tuning to reduce quantization error. Experiments show that on video diffusion models, SLA2 can achieve 97% attention sparsity and deliver an 18.6x attention speedup while preserving generation quality.

We present HairWeaver, a diffusion-based pipeline that animates a single human image with realistic and expressive hair dynamics. While existing methods successfully control body pose, they lack specific control over hair, and as a result, fail to capture the intricate hair motions, resulting in stiff and unrealistic animations. HairWeaver overcomes this limitation using two specialized modules: a Motion-Context-LoRA to integrate motion conditions and a Style-Alignment-LoRA to preserve the subject's photoreal appearance across different data domains. These lightweight components are designed to guide a video diffusion backbone while maintaining its core generative capabilities. By training on a specialized dataset of dynamic human motion generated from a CG simulator, HairWeaver affords fine control over hair motion and ultimately learns to produce highly realistic hair that responds naturally to movement. Comprehensive evaluations demonstrate that our approach sets a new state of the art, producing lifelike human hair animations with dynamic details.

The landscape of AI video generation is undergoing a pivotal shift: moving beyond general generation - which relies on exhaustive prompt-engineering and "cherry-picking" - towards fine-grained, controllable generation and high-fidelity post-processing. In professional AI-assisted filmmaking, it is crucial to perform precise, targeted modifications. A cornerstone of this transition is video instance insertion, which requires inserting a specific instance into existing footage while maintaining scene integrity. Unlike traditional video editing, this task demands several requirements: precise spatial-temporal placement, physically consistent scene interaction, and the faithful preservation of original dynamics - all achieved under minimal user effort. In this paper, we propose PISCO, a video diffusion model for precise video instance insertion with arbitrary sparse keyframe control. PISCO allows users to specify a single keyframe, start-and-end keyframes, or sparse keyframes at arbitrary timestamps, and automatically propagates object appearance, motion, and interaction. To address the severe distribution shift induced by sparse conditioning in pretrained video diffusion models, we introduce Variable-Information Guidance for robust conditioning and Distribution-Preserving Temporal Masking to stabilize temporal generation, together with geometry-aware conditioning for realistic scene adaptation. We further construct PISCO-Bench, a benchmark with verified instance annotations and paired clean background videos, and evaluate performance using both reference-based and reference-free perceptual metrics. Experiments demonstrate that PISCO consistently outperforms strong inpainting and video editing baselines under sparse control, and exhibits clear, monotonic performance improvements as additional control signals are provided. Project page: xiangbogaobarry.github.io/PISCO.

Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves inference efficiency via KV caching and block-wise causal inference and has been widely adopted in diffusion language models and video generation. However, in long-context settings, block diffusion still incurs substantial overhead from repeatedly computing attention over a growing KV cache. We identify an underexplored property of block diffusion: cross-step redundancy of attention within a block. Our analysis shows that attention outputs from tokens outside the current block remain largely stable across diffusion steps, while block-internal attention varies significantly. Based on this observation, we propose FlashBlock, a cached block-external attention mechanism that reuses stable attention output, reducing attention computation and KV cache access without modifying the diffusion process. Moreover, FlashBlock is orthogonal to sparse attention and can be combined as a complementary residual reuse strategy, substantially improving model accuracy under aggressive sparsification. Experiments on diffusion language models and video generation demonstrate up to 1.44$\times$ higher token throughput and up to 1.6$\times$ reduction in attention time, with negligible impact on generation quality. Project page: https://caesarhhh.github.io/FlashBlock/.

Diffusion Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value blocks, it suffers from degradation at high sparsity by discarding context. In this work, we discover that attention scores of non-critical blocks exhibit distributional stability, allowing them to be approximated accurately and efficiently rather than discarded, which is essentially important for sparse attention design. Motivated by this key insight, we propose PISA, a training-free Piecewise Sparse Attention that covers the full attention span with sub-quadratic complexity. Unlike the conventional keep-or-drop paradigm that directly drop the non-critical block information, PISA introduces a novel exact-or-approximate strategy: it maintains exact computation for critical blocks while efficiently approximating the remainder through block-wise Taylor expansion. This design allows PISA to serve as a faithful proxy to full attention, effectively bridging the gap between speed and quality. Experimental results demonstrate that PISA achieves 1.91 times and 2.57 times speedups on Wan2.1-14B and Hunyuan-Video, respectively, while consistently maintaining the highest quality among sparse attention methods. Notably, even for image generation on FLUX, PISA achieves a 1.2 times acceleration without compromising visual quality. Code is available at: https://github.com/xie-lab-ml/piecewise-sparse-attention.

Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce $\textbf{AnyView}$, a diffusion-based video generation framework for $\textit{dynamic view synthesis}$ with minimal inductive biases or geometric assumptions. We leverage multiple data sources with various levels of supervision, including monocular (2D), multi-view static (3D) and multi-view dynamic (4D) datasets, to train a generalist spatiotemporal implicit representation capable of producing zero-shot novel videos from arbitrary camera locations and trajectories. We evaluate AnyView on standard benchmarks, showing competitive results with the current state of the art, and propose $\textbf{AnyViewBench}$, a challenging new benchmark tailored towards $\textit{extreme}$ dynamic view synthesis in diverse real-world scenarios. In this more dramatic setting, we find that most baselines drastically degrade in performance, as they require significant overlap between viewpoints, while AnyView maintains the ability to produce realistic, plausible, and spatiotemporally consistent videos when prompted from $\textit{any}$ viewpoint. Results, data, code, and models can be viewed at: https://tri-ml.github.io/AnyView/

Camera control has been extensively studied in conditioned video generation; however, performing precisely altering the camera trajectories while faithfully preserving the video content remains a challenging task. The mainstream approach to achieving precise camera control is warping a 3D representation according to the target trajectory. However, such methods fail to fully leverage the 3D priors of video diffusion models (VDMs) and often fall into the Inpainting Trap, resulting in subject inconsistency and degraded generation quality. To address this problem, we propose DepthDirector, a video re-rendering framework with precise camera controllability. By leveraging the depth video from explicit 3D representation as camera-control guidance, our method can faithfully reproduce the dynamic scene of an input video under novel camera trajectories. Specifically, we design a View-Content Dual-Stream Condition mechanism that injects both the source video and the warped depth sequence rendered under the target viewpoint into the pretrained video generation model. This geometric guidance signal enables VDMs to comprehend camera movements and leverage their 3D understanding capabilities, thereby facilitating precise camera control and consistent content generation. Next, we introduce a lightweight LoRA-based video diffusion adapter to train our framework, fully preserving the knowledge priors of VDMs. Additionally, we construct a large-scale multi-camera synchronized dataset named MultiCam-WarpData using Unreal Engine 5, containing 8K videos across 1K dynamic scenes. Extensive experiments show that DepthDirector outperforms existing methods in both camera controllability and visual quality. Our code and dataset will be publicly available.

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment. Although sparse attention methods attempt to address this challenge, existing approaches either rely on oversimplified static patterns or require computationally expensive sampling operations to achieve dynamic sparsity, resulting in inaccurate pattern predictions and degraded generation quality. To overcome these limitations, we propose a Mixture-Of-Distribution DiT (MOD-DiT), a novel sampling-free dynamic attention framework that accurately models evolving attention patterns through a two-stage process. First, MOD-DiT leverages prior information from early denoising steps and adopts a {distributed mixing approach} to model an efficient linear approximation model, which is then used to predict mask patterns for a specific denoising interval. Second, an online block masking strategy dynamically applies these predicted masks while maintaining historical sparsity information, eliminating the need for repetitive sampling operations. Extensive evaluations demonstrate consistent acceleration and quality improvements across multiple benchmarks and model architectures, validating MOD-DiT's effectiveness for efficient, high-quality video generation while overcoming the computational limitations of traditional sparse attention approaches.

Human identity-preserving text-to-video generation remains challenging under large changes in viewpoint, facial expression, illumination, and motion. Existing methods condition the generator on a single reference portrait, but a static image cannot capture how identity-bearing cues evolve across views and expressions, leading to face deformation, pose locking, identity drift, or over-smoothed faces. We observe that a short reference clip naturally provides richer temporal and multi-view identity cues than any single image, motivating a video-referential formulation. This richer signal, however, introduces a new challenge: identity evidence is distributed across many frames and must be distilled into a compact, stable representation under a limited token budget. To this end, we propose Slot-ID, a lightweight identity-conditioning framework built on a frozen text-to-video backbone. Slot-ID employs a slot-based temporal identity encoder with Sinkhorn-routed iterative reading to distill a compact, stable set of identity tokens from the reference clip, complemented by an image-anchor stream for dual-source conditioning. Extensive experiments demonstrate that Slot-ID outperforms state-of-the-art methods in identity preservation and visual naturalness while remaining competitive in prompt following, with particularly large gains under challenging pose, expression, and motion variations.

Despite achieving strong results on standard benchmarks, current point tracking methods rely on feature backbones that are rarely designed with the temporal coherence needed for robust real-world performance. While recent works incorporate powerful visual foundation model (VFM) features into tracking pipelines, no prior work has systematically analyzed which VFM provides the most robust representations for point tracking. We present the first such analysis, evaluating diverse VFMs in a zero-shot setting on both standard and robustness benchmarks for point tracking. Our study reveals that video diffusion transformers (DiTs) consistently yield the most temporally coherent and discriminative features, even surpassing ResNet backbones explicitly supervised on tracking data. We hypothesize this advantage stem from large-scale video pretraining, full 3D spatio-temporal attention, and a diffusion training objective. Motivated by this finding, we propose DiTracker, which integrates video DiT features into existing tracking frameworks through query-key matching cost computation, cost-level fusion with a lightweight ResNet branch, and LoRA adaptation. Under the same tracking head, DiTracker is trained solely on synthetic data with far fewer iterations, yet outperforms CoTracker3 trained with additional real-world videos, with the largest gains under challenging and corrupted scenarios. It further generalizes across tracking heads and scales with backbone size, confirming that generative video pretraining provides real-world priors that reduce the dependence on large-scale real-data supervision.

Recent advances in diffusion models have enabled impressive video editing capabilities, yet production-grade Video Object Insertion (VOI) remains challenging due to inadequate 4D scene understanding and a lack of proper optical interactions, such as shadows and reflections. To address these limitations, we present InsertAnywhere, a comprehensive VOI framework that achieves geometrically grounded object placement and optics-aware video synthesis. Our approach first leverages a 4D-aware mask generation module that allows users to anchor an object's 3D pose in a single frame. The framework automatically propagates this placement across the video, accurately handling local scene dynamics and occlusions. To synthesize realistic physical lighting interactions, we introduce Optics-Aware Representation Alignment, a novel strategy that utilizes an extended mask to guide feature extraction, enabling optical effects to seamlessly extend beyond the inserted object's boundary. Finally, to overcome the lack of training data for such phenomena, we construct and open-source ROSE++, a specialized quadruplet dataset tailored for the supervised learning of optical effects. Extensive experiments demonstrate that InsertAnywhere produces geometrically plausible and photometrically realistic insertions in complex real-world scenarios, significantly outperforming existing research and commercial generative tools.

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

The growing demand for immersive 3D content calls for automated monocular-to-stereo video conversion. We present Elastic3D, a controllable, direct end-to-end method for upgrading a conventional video to a binocular one. Our approach, based on (conditional) latent diffusion, avoids artifacts due to explicit depth estimation and warping. The key to its high-quality stereo video output is a novel, guided VAE decoder that ensures sharp and epipolar-consistent stereo video output. Moreover, our method gives the user control over the strength of the stereo effect (more precisely, the disparity range) at inference time, via an intuitive, scalar tuning knob. Experiments on three different datasets of real-world stereo videos show that our method outperforms both traditional warping-based and recent warping-free baselines and sets a new standard for reliable, controllable stereo video conversion. Please check the project page for the video samples https://elastic3d.github.io.

The collection of large-scale and diverse robot demonstrations remains a major bottleneck for imitation learning, as real-world data acquisition is costly and simulators offer limited diversity and fidelity with pronounced sim-to-real gaps. While generative models present an attractive solution, existing methods often alter only visual appearances without creating new behaviors, or suffer from embodiment inconsistencies that yield implausible motions. To address these limitations, we introduce AnchorDream, an embodiment-aware world model that repurposes pretrained video diffusion models for robot data synthesis. AnchorDream conditions the diffusion process on robot motion renderings, anchoring the embodiment to prevent hallucination while synthesizing objects and environments consistent with the robot's kinematics. Starting from only a handful of human teleoperation demonstrations, our method scales them into large, diverse, high-quality datasets without requiring explicit environment modeling. Experiments show that the generated data leads to consistent improvements in downstream policy learning, with relative gains of 36.4% in simulator benchmarks and nearly double performance in real-world studies. These results suggest that grounding generative world models in robot motion provides a practical path toward scaling imitation learning.

Recent progress in text-to-video generation has achieved remarkable realism, yet fine-grained control over camera motion and orientation remains elusive, especially with extreme trajectories (e.g., a 180-degree turnaround, or looking directly up or down). Existing approaches typically encode camera trajectories using relative or ambiguous representations, limiting precise geometric control and offering limited support for large rotations. We introduce GimbalDiffusion, a framework that enables camera control grounded in physical-world coordinates, using gravity as a global reference. Instead of describing motion relative to previous frames, our method defines camera trajectories in an absolute coordinate system, allowing accurate, interpretable control over camera parameters. Using panoramic 360-degree videos for training, we cover the full sphere of possible viewpoints, including combinations of extreme pitch and roll that are out-of-distribution of conventional video data. To improve camera control, we introduce null-pitch conditioning, a strategy that prevents the model from overriding camera specifications in the presence of conflicting prompt content (e.g., generating grass while the camera points toward the sky). Finally, we propose new benchmarks to evaluate gravity-aware camera-controlled video generation, assessing models' ability to generate extreme camera angles and quantify their input prompt entanglement.

While traditional and neural video codecs (NVCs) have achieved remarkable rate-distortion performance, improving perceptual quality at low bitrates remains challenging. Some NVCs incorporate perceptual or adversarial objectives but still suffer from artifacts due to limited generation capacity, whereas others leverage pretrained diffusion models to improve quality at the cost of heavy sampling complexity. To overcome these challenges, we propose S2VC, a Single-Step diffusion based Video Codec that integrates a conditional coding framework with an efficient single-step diffusion generator, enabling realistic reconstruction at low bitrates with reduced sampling cost. Recognizing the importance of semantic conditioning in single-step diffusion, we introduce Contextual Semantic Guidance to extract frame-adaptive semantics from buffered features. It replaces text captions with efficient, fine-grained conditioning, thereby improving generation realism. In addition, Temporal Consistency Guidance is incorporated into the diffusion U-Net to enforce temporal coherence across frames and ensure stable generation. Extensive experiments show that S2VC delivers state-of-the-art perceptual quality with an average 52.73% bitrate saving over prior perceptual methods, underscoring the promise of single-step diffusion for efficient, high-quality video compression. Project: https://onedc-codec.github.io/s2vc/

Text-to-video generation has advanced rapidly, yet preserving a character's holistic appearance from a single reference image remains challenging, particularly when the character undergoes large pose, motion, and scene changes. Existing reference-conditioned approaches primarily treat the reference image as a conditioning signal, which can weaken fine-grained appearance information as reference and noisy video tokens interact during denoising. We propose ContextAnyone, a context-aware diffusion framework that instead treats the reference as an explicitly preserved appearance anchor. Our key idea is to jointly reconstruct the reference image and generate the target video within a shared diffusion transformer, providing direct supervision for preserving identity and fine-grained appearance throughout denoising. To maintain the reference as a stable source of appearance information, we further introduce asymmetric information flow that allows video tokens to selectively access reference tokens while preventing noisy video features from propagating back to the reference branch. We complement this design with Gap-RoPE, which separates the positional representations of the reference and generated video tokens. Experiments on a benchmark constructed from OpenVid-HD demonstrate that ContextAnyone improves both identity and fine-grained appearance consistency over existing reference-conditioned baselines while maintaining motion characteristics close to the underlying text-to-video generator.

Recent approaches in controllable novel view video generation often rely on fine-tuning pre-trained Video Diffusion Models (VDMs). This dominant paradigm is computationally expensive and frequently suffers from catastrophic forgetting of the model's original generative priors. To address this challenge, here we propose InverseCrafter, a VDM training-free framework that reformulates novel view video generation as an inpainting-based inverse problem in the latent space, eliminating the need for any annotated 4D training data. The core of our method is to establish operator equivalence by employing a lightweight latent mask encoder to define a latent-domain masking operation via a continuous, multi-channel representation. This principled representation faithfully models the forward process in the latent domain, enabling efficient, backpropagation-free solvers while bypassing the costly bottleneck of repeated VAE operations. InverseCrafter achieves high-fidelity, spatio-temporally coherent novel view synthesis with near-zero additional inference overhead and excels at general-purpose video inpainting and editing by fully preserving the pre-trained VDM's generative capabilities.

Latent diffusion models pair VAEs with diffusion backbones, and the structure of VAE latents strongly influences the difficulty of diffusion training. However, existing video VAEs typically focus on reconstruction fidelity, overlooking latent structure. We present a statistical analysis of video VAE latent spaces and identify two spectral properties essential for diffusion training: a spatio-temporal frequency spectrum biased toward low frequencies, and a channel-wise eigenspectrum dominated by a few modes. To induce these properties, we propose two lightweight, backbone-agnostic regularizers: Local Correlation Regularization and Latent Masked Reconstruction. Experiments show that our Spectral-Structured VAE (SSVAE) achieves a $3\times$ speedup in text-to-video generation convergence and a 10% gain in video reward, outperforming strong open-source VAEs. The code is available at https://github.com/zai-org/SSVAE.

Generating interactive and dynamic 4D scenes from a single static image remains a core challenge. Most existing generate-then-reconstruct and reconstruct-then-generate methods decouple geometry from motion, causing spatiotemporal inconsistencies and poor generalization. To address these, we present MoGe4D (Motion and Geometry-Aware image-to-4D Synthesis), a geometry-conditioned framework for single-image 4D synthesis that models a scene as dense 4D point trajectories. Instead of treating geometry and dynamics as two disconnected stages, our method starts from an initial geometric prior inferred from the input image and predicts future time-varying trajectories in a diffusion process, improving spatiotemporal coherence while preserving structural stability. To support this task, we first introduce TrajScene-60K, a large-scale dataset of 60,000 video samples with dense 4D point trajectories, addressing the scarcity of high-quality training data for scene-level 4D generation. Built on this, our diffusion-based 4D Scene Trajectory Generator (4D-STraG) predicts geometry-consistent and motion-plausible trajectory fields conditioned on the input image, with a depth-guided motion normalization strategy to reduce scale ambiguity and a Motion Perception Module (MPM) to inject motion-aware priors. We further propose a 4D View Synthesis Module (4D-ViSM) to render the generated 4D representation into videos under arbitrary camera trajectories. Experiments show that MoGe4D produces high-quality 4D scenes with strong temporal coherence, favorable geometry-aware consistency, and compelling novel-view synthesis from a single image. Code: https://github.com/Zhangyr2022/MoGe4D.

Previous works that leverage video models for image-to-3D scene generation often suffer from geometric distortions and blurry content. Using video generation models to implicitly maintain geometric consistency according to a single-frame input is ineffective. In this paper, we present a two-stage method, named $\textbf{GeoWorld}$, that renovates the image-to-3D scene generation pipeline by providing full-frame geometry features. The first-stage video generation model, followed by a multi-view geometry model, produces $\textbf{full-frame}$ geometry features, which are then used as a mental draft of geometric conditions to aid the second-stage video-generation model. A geometric loss is proposed to impose real-world geometric constraints, and a geometry adaptation module is introduced to ensure the effective utilization of geometry features. Thanks to full-frame geometric modeling, the two smaller video models in our two-stage method can generate higher-fidelity 3D scenes than SOTA methods, while being even faster, e.g. 7.5$\times$ faster than Hunyuan-Voyager. Project page: https://peaes.github.io/GeoWorld.

Recent advances in video world models enable interactive environments with free navigation, making translation between first-person (egocentric) and third-person (exocentric) perspectives increasingly important. However, existing studies focus on unidirectional exocentric-to-egocentric translation, overlooking reference-guided exocentric perspective synthesis. This capability is crucial for gaming and embodied AI applications. Motivated by this, we present WorldWander, an in-context learning framework tailored for translating between egocentric and exocentric worlds in video generation. Building upon advanced video diffusion transformers, WorldWander integrates (i) In-Context Perspective Alignment and (ii) Collaborative Position Encoding to model cross-view synchronization and character consistency. To support our task, we curate EgoExo-8K, a dynamic and scene-rich dataset containing synchronized egocentric-exocentric triplets from both synthetic and real-world scenarios. Experiments demonstrate that WorldWander achieves superior perspective synchronization, character consistency, and generalization, setting a new benchmark for egocentric-exocentric video translation.

Foundation video generation models such as WAN 2.2 exhibit strong text- and image-conditioned synthesis abilities but remain constrained to the same-view generation setting. In this work, we introduce Exo2EgoSyn, an adaptation of WAN 2.2 that unlocks Exocentric-to-Egocentric(Exo2Ego) cross-view video synthesis. Our framework consists of three key modules. Ego-Exo View Alignment(EgoExo-Align) enforces latent-space alignment between exocentric and egocentric first-frame representations, reorienting the generative space from the given exo view toward the ego view. Multi-view Exocentric Video Conditioning (MultiExoCon) aggregates multi-view exocentric videos into a unified conditioning signal, extending WAN2.2 beyond its vanilla single-image or text conditioning. Furthermore, Pose-Aware Latent Injection (PoseInj) injects relative exo-to-ego camera pose information into the latent state, guiding geometry-aware synthesis across viewpoints. Together, these modules enable high-fidelity ego view video generation from third-person observations without retraining from scratch. Experiments on ExoEgo4D validate that Exo2EgoSyn significantly improves Ego2Exo synthesis, paving the way for scalable cross-view video generation with foundation models. Source code and models will be released publicly.

Rotary positional embeddings (RoPE) are widely used in diffusion transformers (DiTs) to encode spatial relationships, yet their behavior with mixed-resolution tokens remains underexplored. A natural approach is to rescale token positions from different resolutions into a unified coordinate system before attention, but we show this fails. Our analysis shows that with RoPE, the attention similarity score is a highly structured and periodic function of token distance, so rescaling distances across resolutions moves token pairs to different regions of this periodic function, leading to incorrect attention scores. Motivated by this, we introduce Phase-Aligned Mixed-Resolution Attention (PMA), a training-free mechanism that stabilizes mixed-resolution attention. PMA modifies the RoPE position mapping to enforce a consistent positional scale for every query-key pair, ensuring that relative distances are evaluated under a single reference scale. To further improve local coherence near resolution transitions, we incorporate a lightweight boundary refinement module that softly exchanges features across adjacent scales. Experiments on image and video diffusion models validate our analysis and demonstrate consistent improvements in visual fidelity and computational efficiency.

Camera-controlled video generation has attracted increasing interest for its applications in simulation, gaming, and world modeling. However, current models often deform rigid objects and scene structure as the viewpoint changes. We investigate whether this failure is related to a measurable internal property: the view consistency of diffusion representations. Across a diverse collection of camera-controlled image-to-video diffusion models, we find that models exhibiting more view-consistent representations generate videos with superior 3D consistency. We complement this correlation-based evidence with a within-model controlled intervention, ViCoDR, which directly supervises the view consistency of internal diffusion representations, during training. Across camera-controlled image-to-video, camera-controlled text-to-video, and multi-view generation tasks, ViCoDR consistently improves output 3D consistency. Finally, we evaluate the loss used for these interventions as an auxiliary training objective by retraining a camera-controlled I2V model using either ViCoDR or existing methods for supervising diffusion representations under the same training setup. We show that the ViCoDR loss improves output 3D consistency more reliably than the alternatives and remains effective across design variants, while exhibiting camera-control trade-offs and requiring additional training computation. Together, these results establish view consistency of internal diffusion representations as an important property for analyzing and improving camera-controlled video generation. Project page: https://danier97.github.io/ViCoDR.