Video Diffusion Models

Ask about this topic

Overview

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

Latest papers

CardsList

738 papers122 papers in the last four weeks, up 171% on the four weeks before. 0.7% of all new papers.

Jul 8, 2026

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For example, their design inherently prioritizes visual fidelity and creativity over computational efficiency and physical realism. In this work, we present LingBot-Video, a DiT-based video pretraining paradigm specifically tailored for embodied intelligence. From the architecture perspective, we adopt the Mixture-of-Experts (MoE), instead of dense, framework to achieve a better trade-off between modeling capacity and inference efficiency, and manage to scale it up from scratch. From the data perspective, we construct a data profiling engine that augments standard internet videos with extensive robot-oriented footage, encompassing manipulation, navigation, and egocentric perspectives, to equip the base model with an intrinsic understanding of actions and world dynamics. From the training perspective, we develop a multi-dimensional reward system to enforce the alignment regarding physical rationality and task completion, going beyond standard criteria such as aesthetics, prompt-following, and motion consistency. Comprehensive evaluations validate its performance and efficiency as a video foundation model. We contribute LingBot-Video as the inaugural large-scale, open-source MoE video foundation model to the community, in a pioneering effort to bridge digital creativity and physical actuation.

Shuailei Ma, Jiaqi Liao, Xinyang Wang +24

Video Diffusion ModelsSelf-Supervised Pre-TrainingVideo GenerationMixture-of-Experts Models
AskPDF
Jul 8, 2026

DiffCVE: Diffusion-based Compressed Video Enhancement

Perceptual quality enhancement of severely compressed videos remains challenging due to complex artifact patterns and substantial information loss. Recent diffusion models have demonstrated strong generative capability for visual restoration, but directly applying them to compressed video often ignores compression degradation characteristics and may introduce structure-inconsistent hallucinations. To address this issue, this paper presents a diffusion-based compressed video enhancement method, named DiffCVE. Coding Prior-enhanced Dual Conditioning (CPDC) branches are designed to jointly model compressed video and coding prior conditions, where coding priors including residuals and motion vectors provide complementary structural and motion guidance during the diffusion denoising process. To make the diffusion process aware of compression severity, a Compression Degradation Semantic Prompting (CDSP) mechanism is introduced to leverage QP-conditioned textual prompts together with LoRA fine-tuning. In addition, a Coding Prior-guided Weighted Fusion (CPWF) module is incorporated into the VAE decoder to fuse VAE encoder and coding prior encoder features with QP-predicted weights. Extensive experiments demonstrate the effectiveness of the proposed method in improving perceptual quality, especially under severe compression settings. The project page with enhanced video demonstrations is available at https://wqmaker.github.io/projects/DiffCVE/.

Wenqiang Xiao, Wenzhuo Ma, Junxi Zhang +1

School of Remote Sensing and Information Engineering, Wuhan University

Video Diffusion ModelsVideo Compression
AskPDF
Jul 7, 2026

Gen4U: Unifying Video Generation and Understanding via Diffusion

Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics. We demonstrate that state-of-the-art video diffusion models overcome this limitation. By systematically probing their intermediate activations using recent mutual-kNN alignment metrics, we reveal a highly structured latent space where visual representations evolve across both network depth and noise levels. We show that while moderate noise levels yield linearly separable global semantics, fine-grained details persist at lower noise levels but become spatially scattered, requiring attention mechanisms to decode. Building on these insights, we introduce Gen4U (Generation for Understanding), a framework that repurposes these generative representations with a single forward pass. Our experiments establish that frozen, large-scale video diffusion models function as highly competitive video encoders across a wide spectrum of tasks, spanning semantic and non-semantic objectives (video classification, depth estimation, camera pose estimation, image and video captioning). Bypassing fine-tuning, Gen4U unifies the generation and understanding paradigms, achieving strong perception performance while fully preserving the model's ability to generate high-quality video.

Michael King, Aravindh Mahendran, Matthew Koichi Grimes +5

Google DeepMind

Video Diffusion ModelsVideo Representation LearningDiffusion Models
AskPDF
Jul 7, 2026

Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation

We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning. PACR-Video keeps a text-to-video diffusion transformer frozen and augments it with low-rank temporal adapters conditioned by learned shot-role prompt tokens. To maintain long-horizon coherence, it builds a recursive prompt bank that stores compact entity, location, action, and style prompts from previous shots, then routes them through adapter gates according to predicted narrative dependencies. A Shot-Local/Story-Global tuning objective combines next-shot reconstruction, cross-shot identity contrast, and prompt sparsity regularization, while an adapter composition schedule balances early-shot visual consistency with later-shot event progression and viewpoint change. Across six multi-shot and long-video benchmarks, PACR-Video outperforms text-to-video, tuning-based, memory-augmented, streaming, and recursive-context baselines on distributional quality, semantic alignment, identity consistency, temporal smoothness, motion stability, transition coherence, and human preference. These results show that compact prompt routing and lightweight temporal adaptation provide sufficient controllable capacity for stable long video extrapolation.

Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo +4

Instituto de Investigación en Visión Artificial

Video Diffusion ModelsVideo PredictionMulti-Shot Video GenerationTemporal Consistency in Video GenerationParameter-Efficient Fine-Tuning
AskPDF
Jul 7, 2026

FADRA: Frequency-Aware Diffusion with Residual Adaptation for Video Face Restoration

Video face restoration (VFR) aims to recover high-quality and temporally consistent facial details from severely degraded video sequences; however, existing methods still struggle to balance spatial fidelity and temporal coherence under complex degradations. To address this, we propose FADRA, a frequency-aware diffusion framework with iterative residual adaptation specifically tailored for robust VFR. We first leverage the strong temporal consistency of a pre-trained text-to-video diffusion model and introduce lightweight LoRA adapters together with a Low-Quality (LQ) Pixel-Alignment Feature Fusion module to efficiently adapt the frozen generative prior to the VFR task. To further adapt the frozen diffusion backbone to the downstream VFR task beyond LoRA-based adaptation, we introduce a Repeated Residual Adaptation Head (RRAH) for step-wise residual refinement after the diffusion backbone. To make this refinement explicitly guided by the degraded observation, RRAH further takes the LQ latent together with the current velocity prediction as input, allowing the model to repeatedly revisit LQ cues and predict residual updates at each flow-matching step. This LQ-guided repeated residual adaptation helps recover fine facial details while preserving the inherent temporal priors of the pre-trained model. Furthermore, to ensure the structural integrity of perceptually important details, we introduce a Frequency-Aware Loss that provides explicit supervision across multiple spectral bands, emphasizing visually sensitive frequency components that are crucial for perceptual quality and prone to temporal jittering. Extensive experiments demonstrate that FADRA recovers better facial structures and produces more temporally consistent videos than state-of-the-art methods, leading to clear gains in both quantitative metrics and visual perception. Our project page is available.

Jin Jiang, Jia Wang, Panwen Hu +2

College of Information Technology (CIT), United Arab Emirates University (UAEU), Al Ain, Abu Dhabi, United Arab Emirates · State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China (OUC), Shandong, 266100, China · Computer Vision Department, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab Emirates

Diffusion Model AdaptationVideo Diffusion ModelsImage RestorationVideo RestorationDiffusion Models
AskPDF
Jul 7, 2026

Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation

Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step distillation techniques significantly accelerate inference, they typically enforce a static model architecture across all denoising stages, ignoring the varying computational demands inherent to different noise levels. In this work, we propose a novel post-training acceleration framework that exploits this redundancy by integrating dynamic structural sparsification directly into the distillation process. Unlike conventional post-hoc compression applied to a fixed diffusion pipeline, our approach jointly optimizes the denoising steps and structured model sparsity, transforming a pre-trained VDM into a compact, step-specific Mixture-of-Models (MoM). To address the training instability arising from this joint optimization, we introduce a Progressive Training Strategy coupled with an Output Rollout Mechanism, which ensures the coherent learning of structural decisions across timesteps. Furthermore, we develop a specialized inference engine to deploy the resulting MoM efficiently. Our method is orthogonal to existing acceleration techniques and highly effective: On Wan-14B, it removes 24% of the per-step FLOPs on top of 4-step distillation, adding a 1.2x wall-clock gain and reaching a 30x speedup over the 50-step teacher while preserving competitive generation quality.

Yu Cheng, Siyue Yao, Zhongang Qi +3

Zhejiang University · BlueImage, vivo · Westlake University

Video Diffusion ModelsDiffusion Model DistillationFew-Step Diffusion SamplingDiffusion Model Inference AccelerationNeural Network Pruning
AskPDF
Jul 7, 2026

MobileWan: Closing the Quality Gap for Mobile Video Diffusion

Recent advances in video diffusion have been driven by scaling transformer-based architectures to billions of parameters, substantially improving visual fidelity and motion coherence. In contrast, existing mobile video diffusion models remain limited to relatively small parameter budgets, typically 0.4-1.8B, restricting generation quality. In this work, we show that high-quality mobile video generation does not require small models. Instead, we demonstrate that a server-scale 5B-parameter video diffusion transformer can be deployed efficiently on memory-constrained mobile hardware through recurrent reformulation and structured compression. Starting from Wan2.2-5B, we rely on a recurrence distillation framework that converts video generation into a chunk-wise autoregressive process with constant-memory attention computation. Combined with causal linear attention, the model operates as an RNN at inference time while preserving temporal coherence across chunks. We further propose a learnable attention head pruning method based on binary per-head gates optimized end-to-end using a noise-biased sparsity objective and distillation-based finetuning. Together with sampling-step distillation and memory-optimized VAE decoding, MobileWan becomes the first 5B-scale video diffusion model deployable on a commercial mobile device. Our system generates 5-second 480x832 videos at 16 FPS in 20 seconds end-to-end latency, achieving a VBench score of 83.79 and establishing a new state of the art in mobile video generation. Project page: https://qualcomm-ai-research.github.io/mobilewan

Mohsen Ghafoorian, Denis Korzhenkov, Adil Karjauv +9

Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc.

Video Diffusion ModelsVideo GenerationAttention Head PruningAutoregressive Video GenerationDiffusion Models for Motion GenerationDiffusion Model Inference Acceleration
AskPDF
Jul 6, 2026

MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing

Recent advances in video diffusion models have enabled either long single-view generation through temporal autoregression, or short multi-view synthesis through bidirectional attention. However, generating long, multi-view consistent videos of dynamic scenes remains unsolved. In this work, we present MV-Forcing, a framework that composes temporal and view-wise autoregression within a single diffusion model by introducing a 4D geometric bridge between sequentially generated views. Our key insight is that an autoregressive 3D reconstruction model naturally interfaces between autoregressively generated views. Given a completed source view, we reconstruct its 3D structure and render a geometric prior of the next target viewpoint, which the diffusion model refines into a high-quality video. To extend generation beyond the teacher's fixed temporal window, we introduce a joint denoising regime where both view slots are initialized from noise during training, enabling temporally unbounded generation. We distill the model via Distribution Matching Distillation with Spatio-Temporal Self-Forcing, closing the train-inference exposure bias gap for both temporal and view-sequential autoregression. Extensive experiments on both synthetic and real-world data demonstrate that MV-Forcing produces geometrically consistent multi-view videos of dynamic scenes at arbitrary lengths and viewpoint counts using a single few-step student model.

Gal Fiebelman, Hadar Averbuch-Elor, Sagie Benaim

The Hebrew University of Jerusalem · Cornell University

Multi-View ConsistencyVideo Diffusion ModelsMulti-View Video GenerationLong Video GenerationAutoregressive Video GenerationMulti-View Diffusion Models
AskPDF
Jul 6, 2026

UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation

World Action Models (WAMs) have shown strong potential for improving action generalization in autonomous driving by using future video prediction as dense supervision for scene dynamics and temporal causality. However, it remains unclear which architecture better transfers video-modeling benefits to trajectory generation. Existing cascaded or dual-DiT designs separate video imagination from action prediction, weakening the transfer of video-learned world dynamics to the trajectory branch: the action model may still overfit dataset-specific driving priors, while the video model only indirectly regularizes planning. We propose UNIVERSE, a unified video-action model built upon a single mask-modulated Diffusion Transformer. By co-training future video latents and ego-trajectory tokens within shared generative parameters, UNIVERSE allows dense video supervision to directly shape trajectory denoising, leading to stronger cross-domain action generalization. To ensure causal validity and efficient deployment, we introduce a Modality-Decoupling Visibility Mask, which shares historical context across modalities while blocking mutual attention between future video and trajectory tokens. This prevents future-target leakage and enables trajectory-only inference by removing future-video denoising at test time, achieving a 4.3×4.3\times speedup over joint video-action rollout while maintaining comparable planning accuracy. The same model also supports video-only and joint video-action rollouts. Experiments show that UNIVERSE achieves 91.0 PDMS on NAVSIM (vs. 89.6 for the Two-DiT variant), and demonstrates strong zero-shot transfer to nuScenes and Bench2Drive without fine-tuning, while ablations confirm the importance of single-DiT unification, video co-training, and mask-based modality decoupling.

Mengmeng Liu, Diankun Zhang, Jiuming Liu +7

University of Twente · Xiaomi EV · University of Cambridge +1

Action-Conditioned Video GenerationVideo Diffusion ModelsEnd-to-End Autonomous DrivingWorld Action ModelsWorld Models for Autonomous DrivingAutonomous Driving Planning
AskPDF
Jul 6, 2026

Consistent and Editable: A Balanced Framework for Text-Guided Video Editing

Recently, diffusion models have achieved considerable success in the text-guided video editing domain. However, existing works often struggle to balance the trade-off between temporal consistency and editability in video editing, with consistency and editability typically being inversely related. To address this, we propose a high-quality video editing framework enhanced for consistency and editability, named EquiEdit, which improves coordinatively the temporal consistency and editability of the edited videos while achieving a balance between the two. In terms of temporal consistency, the proposed temporal Mamba module with a tailored temporal-aware scanning scans fused video sequences following four designed directions, effectively enhancing the inter-frame consistency of edited videos. For editability, we design a noise injection strategy based on the spectral transformation to increase editing flexibility, where the Fourier transform is used to preserve the hidden structure in the initial latent noise used for editing, ensuring inter-frame consistency of the edited video and fidelity to the input video. Extensive qualitative and quantitative experiments demonstrate the effectiveness of our method in terms of temporal consistency and editability, as well as its great fidelity to the input video itself.

Tao Jin, Li Xiao

University of Science and Technology of China

Video Diffusion ModelsVideo EditingInstruction-Based Video EditingTemporal Consistency
AskPDF
Jul 6, 2026

Video Generation Models Are Inherent Lighting Estimators

Recovering dynamic environment maps from a single in-the-wild video is crucial for photorealistic rendering, yet remains a challenge. Recent video generation models can produce photorealistic scenes with complex lighting, possessing an inherent understanding of lighting. In this paper, we introduce V-LITE (Video generation models are inherent lighting estimators), a framework that unlocks this internal knowledge by reframing lighting estimation as a guided video inpainting task. Inspired by VFX industry practices, we insert a synthetic chrome ball into the scene to compel the model to generate physically plausible reflections from the surrounding spatio-temporal context. To bridge the gap from LDR-native models to the HDR domain, we design an HDR-aware VAE and employ an efficient LoRA-based fine-tuning strategy. We then construct a mixed dataset comprising high-fidelity HDR images to provide realistic HDR priors, and in-the-wild HDR videos to provide dynamic spatio-temporal context. Extensive experiments demonstrate that V-LITE produces temporally coherent HDR environment maps, revealing that modern video diffusion models are not merely synthesizers but also powerful, inherently capable estimators of physical scene lighting.

Ziqi Cai, Shuchen Weng, Kaiqi Liu +5

State Key Laboratory of Multimedia Information Processing and National Engineering Research Center of Visual Technology, School of Computer Science, Peking University · Beijing Academy of Artificial Intelligence · School of Software and Microelectronics, Peking University +1

Video Diffusion ModelsHDR Imaging
AskPDF
Jul 6, 2026

Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoising

While modern video diffusion models excel in visual fidelity, maintaining long-range physical consistency remains a formidable challenge. Conventional pixel-reconstruction objectives mainly focus on appearance details and often fail to capture the underlying dynamics of a scene. To mitigate this, recent efforts have integrated auxiliary modalities (e.g., optical flow) to introduce physics priors via joint training with video appearance. However, these methods have three main limitations: (1) they do not distinguish the different motion patterns of different entity types; (2) joint modeling of visual and auxiliary modalities can cause capacity conflicts and weaken the pretrained visual prior; and (3) auxiliary modalities may accumulate errors during inference. To address these issues, we propose VPT, a fine-tuning framework for improving physical consistency in video diffusion models. VPT introduces a role-aware signal that groups entities into agents, controlled objects, passive objects, and background, so that different physical roles can be modeled more clearly. We further propose a modality-decoupled denoising strategy, where the visual and auxiliary channels are assigned independent noise levels. Together with a loss-weight decay strategy, this design makes auxiliary modalities serve as soft constraints rather than strong dependencies, mitigating recursive prediction errors during inference. We also introduce cross-step auto-guidance to further strengthen physical dynamics. Experiments show that VPT improves physical consistency while preserving visual quality, achieving relative gains of 39.4% in SA and 17.9% in PC on VideoPhy benchmark over Wan2.1-T2V-1.3B, and consistent improvements on VideoPhy-2 benchmark. The project page is available at https://tom-zgt.github.io/VPT.

Guangting Zheng, Haojing Chen, Hao Li +6

University of Science and Technology of China · University of Electronic Science and Technology of China · 3Fudan University +2

Physical Consistency in Video GenerationDiffusion Model GuidanceVideo Diffusion Models
AskPDF
Jul 5, 2026

Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption

We present a bidirectional framework for estimating the energy consumption of text-to-video (T2V) and text-to-video-audio (T2VA) models from architectural first principles and observable generation parameters such as resolution and duration, requiring no access to weights, model size, or implementation details. Forward, it predicts energy from generation parameters and architectural principles; backward, it recovers architectural scaling behavior from observed inference times, with accuracy serving as a criterion for architectural validity. Building on the established compute-bound nature of video diffusion models, we demonstrate that each model's energy profile obeys theoretically derived scaling laws, decomposing into quadratic and linear terms whose coefficients directly reflect the underlying architectural complexity. Validated across six open-source models spanning 8.3B-27B parameters and three GPU configurations, this decomposition achieves below 3% MAPE across all architectures. This approach offers a standardized, empirically and theoretically grounded framework for sustainability benchmarking across T2V models and architectures.

Nidhal Jegham, Boris Gamazaychikov, Sasha Luccioni

University of Rhode Island, Sustainable AI Group Rhode Island, United States · Sustainable AI Group Paris, France · Sustainable AI Group Montreal, Canada

Video Diffusion ModelsVideo GenerationVideo Generation Evaluation
AskPDF
Jul 5, 2026

Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment

Subject-driven and multi-element video generation are central to controllable video synthesis, but existing methods still struggle to preserve identity consistency and model complex relationships among multiple subjects. In this paper, we propose Aura, a unified framework for high-fidelity and identity-consistent video generation. To better capture scene dynamics and subject interactions, we introduce AI director-level captions that provide dense and structured descriptions of video content. We further leverage a vision-language model (VLM) with learnable queries to extract multimodal semantic features from textual and visual references, covering both global semantics and fine-grained visual cues. To bridge the representational gap between the VLM and the Diffusion Transformer (DiT), we design a two-stage alignment strategy that progressively maps VLM features into the DiT feature space. For visual conditioning, we adopt token concatenation to inject reference information directly into the generation process. To distinguish heterogeneous subject types and reduce common copy-paste artifacts, we develop a subject-aware RoPE-Shift mechanism. To further differentiate reference images of different categories, we introduce subject-aware learnable tokens. In addition, we introduce Memory Tokens to balance the training signal across examples with different numbers of reference subjects. During inference, Progressive-APG (Adaptive Prompt Guidance) further alleviates oversaturation and improves semantic alignment with user prompts. Finally, we build a high-quality video-subject image dataset through a dedicated data construction pipeline. Extensive experiments show that our method achieves state-of-the-art performance on both single-subject generation and more challenging multi-element scenarios.

Zixiang Zhou, Zhentao Yu, Yifeng Ma +9

Tencent Hunyuan

Video Diffusion ModelsIdentity-Preserving Video GenerationVideo GenerationVision-Language Alignment
AskPDF
Jul 4, 2026

Reward Lightning: Fast Video Generation via Homologous Preference Distillation

Achieving simultaneous preference alignment and distillation acceleration in video diffusion models remains an open challenge. Existing methods optimize the two objectives over mismatched representation spaces, where improving one objective often compromises the other. To overcome this, we propose Reward Lightning, a unified framework that aligns and accelerates a video diffusion model within a single shared representation. Its central principle is homology: both objectives are evaluated on identical latent features, which mitigates the gradient conflicts that arise when they are optimized over disjoint representations. As a foundational component, we first introduce a latent reward model (LRM) that scores videos directly in the latent space, without decoding back to the pixel space. Building on the LRM, homologous preference distillation (HPD) reuses this shared backbone to perform adversarial distillation and preference alignment jointly, yielding few-step generators that remain faithful and well aligned. Extensive experiments demonstrate that the LRM surpasses pixel-level and latent-level reward baselines by 11.0%11.0\% and 14.7%14.7\% in preference accuracy, and that Reward Lightning generates high-fidelity videos in merely 11 to 44 steps, improving the average VBench score by 2.1%2.1\% while leading in text alignment, motion quality, and visual quality. Project page: https://reward-lightning.github.io.

Jiaxiang Cheng, Bing Ma, Xuhua Ren +4

Tencent Hunyuan, China

Diffusion Model AlignmentReward ModelingVideo Diffusion ModelsDiffusion Model DistillationDiffusion Model Acceleration
AskPDF
Jul 4, 2026

ProxyUp: Training-Free Proxy-Conditioned Video Generation for Controllable Dynamics

Precise control over complex dynamics remains challenging for modern video generative models, as text prompts alone often cannot specify physically plausible, fine-grained motion and interactions. We introduce proxy-conditioned video generation\textit{proxy-conditioned video generation}, where a coarse proxy video from physics-based simulation or real-world recording serves as a dynamics carrier to control foreground object motion. Given a proxy video and a text prompt, the goal is to synthesize a new video that preserves the proxy dynamics while generating novel content and plausible interactions aligned with the prompt. Since paired proxy-target videos are difficult to obtain, we propose ProxyUp\textbf{ProxyUp}, a training-free framework built on pretrained video generative models. ProxyUp first inverts the proxy video into an intermediate latent representation and applies region-wise latent noising\textbf{region-wise latent noising}, preserving motion-critical proxy latents while injecting noise into regions intended for text-driven regeneration. To mitigate the distribution mismatch and weak foreground-background coupling introduced by this heuristic latent composition, we further propose Stochastic Flow Relaxation (SFR)\textbf{Stochastic Flow Relaxation (SFR)}, which progressively relaxes the composed latent toward the model's learned distribution before ODE sampling. Experiments on both simulation and real-world proxies show that ProxyUp outperforms strong video editing and motion transfer baselines in dynamic fidelity and text alignment.

Zanwei Zhou, Jiazhong Cen, Jiemin Fang +7

1Shanghai Jiao Tong University · 2Huawei Inc.

Physical Consistency in Video GenerationVideo Diffusion ModelsControllable Video Generation
AskPDF
Jul 3, 2026

Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model

Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional diffusion models excel at global coherence and visual fidelity but suffer from slow inference, while autoregressive models offer efficient and streaming generation at the cost of long-range consistency and exposure bias. We introduce Flex-Forcing, a unified training and inference framework that enables a video diffusion model to seamlessly operate under both bidirectional and autoregressive generation regimes. The core idea is a flexible chunking mechanism jointly defined over the temporal axis and denoising steps. This design allows the model to (1) perform flexible chunking according to different device budgets, (2) perform bidirectional inference across chunks for global structure planning, while generating frames autoregressively within each chunk for efficient and fine-grained synthesis, and (3) perform any-order, any-timestep autoregressive generation without the strict causal constraint. Extensive experiments on multiple video generation benchmarks demonstrate that Flex-Forcing achieves consistently better video quality, long-video stability than strong baselines with a rigid inference schedule, while offering faster inference.

Xinyin Ma, Julius Berner, Chao Liu +3

Electrical and Computer Engineering, National University of Singapore, Singapore · NVIDIA Research, California, USA

Video Diffusion ModelsAutoregressive DiffusionLong Video GenerationAutoregressive Video GenerationDiffusion Model Inference Acceleration
AskPDF
Jul 3, 2026

Vidu S1: A Real-Time Interactive Video Generation Model

We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up to 42 FPS on regular consumer GPUs. Users can upload custom images of real people, anime, and pets, and choose different voice tones for personalized experiences. Experiments show that Vidu S1 achieves the best performance across all test metrics while fully meeting real-time inference requirements. A playable online demo is available at https://vidu.com/vidu-stream.

Jintao Zhang, Kai Jiang, Jintao Chen +24

Tsinghua University, Shengshu Technology · Shengshu Technology

Streaming Video GenerationReal-Time Interactive Video GenerationLong Video GenerationVideo Diffusion ModelsVideo GenerationControllable Video Generation+1
AskPDF
Jul 3, 2026

HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion

Video Diffusion Transformers (VDiTs) have demonstrated significant capabilities in high-fidelity video generation. However, their ability to produce long-duration videos is fundamentally constrained by the quadratic complexity of the self-attention mechanism. Recent clustering-based sparse attention methods improve the quality-speed trade-off by grouping semantically similar tokens, but their practical efficiency remains limited by two bottlenecks: substantial clustering overhead and low CTA utilization caused by irregular cluster-induced blocks. We propose HyperVAttention (HVA), a training-free sparse attention framework that addresses both bottlenecks jointly. To reduce clustering overhead, we introduce 3D local-window clustering, which exploits the spatio-temporal locality of video tokens to restrict centroid search to fixed local neighborhoods, and implement it with a custom Triton kernel for efficient execution. We further propose a hybrid clustering strategy that performs full clustering only at anchor steps and updates only subset tokens at intermediate steps, leveraging the temporal stability of cluster assignments across denoising steps. To improve CTA utilization, we present hardware-aware cluster merging that minimizes CTA-aligned execution cost through parallel agglomerative merging, improving block density and approximation fidelity by utilizing idle tile capacity. Together, these components reduce clustering overhead, avoid redundant updates, and better align sparse attention with the fixed tile structure of modern GPU kernels. Experiments on Text-to-Video generation show that HVA establishes a new Pareto frontier for training-free sparse attention in video diffusion, reducing end-to-end latency by up to 2.13×2.13\times while improving fidelity over existing training-free sparse attention baselines.

Dongyeun Lee, Amir Zandieh, Vahab Mirrokni +2

KAIST · Google Research

Video Diffusion ModelsDiffusion TransformerSparse AttentionDiffusion Model Inference Acceleration
AskPDF
Jul 2, 2026

Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generation

Modern image-and-text-to-video diffusion models can synthesize highly realistic videos by iteratively denoising an initial Gaussian noise tensor conditioned on reference image and text inputs. However, existing approaches still lack precise and unified controllability over both object motion and camera motion within a single generation process. We present UniCaMo, a unified framework that enables simultaneous control of object trajectories and camera viewpoints by directly constructing the input noise of the diffusion model. Specifically, UniCaMo builds a shared 3D-grounded motion-consistent noise space across latent video frames. Sparse 3D point tracks are used to warp the Gaussian noise of the reference frame along desired object trajectories, while a virtual spherical noise representation provides globally consistent noise values for newly revealed scene regions under camera motion. By combining local track-guided noise warping with global sphere-based noise sampling, UniCaMo maintains geometric and temporal consistency under both object movement and viewpoint changes. Because UniCaMo modifies only the input noise, it requires no auxiliary adapters, control branches, or architectural changes to the underlying video diffusion model. With lightweight LoRA fine-tuning on large pretrained video diffusion models, including Wan 2.1 (14B), UniCaMo achieves state-of-the-art results in both video quality and motion controllability on standard controllable video generation benchmarks.

Long Vu, Tan Ngo, Animesh Karnewar +5

Qualcomm AI Research · Trinity College Dublin, Ireland

Camera-Controlled Video GenerationVideo Diffusion ModelsDiffusion Models for Motion GenerationControllable Video GenerationTrajectory-Guided Video Generation3D-Aware Video Generation
AskPDF
Jul 2, 2026

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT activations shift across timesteps, prompts, and guidance branches, forcing prior methods to re-fit calibration data for every new checkpoint or modality. We present OrbitQuant, a data-agnostic weight-activation quantizer that bypasses range estimation by quantizing in a normalized, rotated basis. In this basis, a randomized permuted block-Hadamard (RPBH) rotation concentrates each coordinate around one fixed, known marginal regardless of the input, so a single Lloyd-Max codebook serves all timesteps, prompts, and layers of a given input dimension. We extend the same quantizer to weight rows offline, absorbing the rotation into the weights so that it cancels inside each linear layer and only a forward rotation on the activations remains at runtime. The same recipe transfers from image to video with no per-modality tuning. Across FLUX.1, Z-Image-Turbo, Wan 2.1, and CogVideoX, it sets the state of the art for PTQ at several low-bit settings. It also pushes PTQ of image diffusion transformers to W2A4 with usable generation quality.

Donghyun Lee, Jitesh Chavan, Duy Nguyen +5

Cantina Labs · University of Southern California · *Work done during an internship at Cantina Labs. +1

Video Diffusion ModelsDiffusion TransformerDiffusion Model QuantizationRotation-Based QuantizationActivation QuantizationPost-Training Quantization+1
AskPDF
Jul 2, 2026

NeoMap: Training-free Novel-View Synthesis from Single Images and Videos

We study the challenging problem of novel view video synthesis from single images or monocular videos. Existing methods, which operate under the assumption that pre-trained video models lack native novel view synthesis capability and enforce view alignment via camera conditioning, task-specific fine-tuning, or stepwise hard denoising guidance, often suffer from artifacts and compromised global scene consistency. In this paper, we introduce NeoMap, a novel training-free framework designed to locate high-fidelity, view-consistent novel view solutions from general pre-trained video models. The key to our approach is the core insight that promising novel view solutions are inherently encoded within the natural video data manifold learned by pre-trained models, and the core challenge is simply to locate this optimal solution. We solve this via our core mechanism: convergent manifold alternating projection iterations that optimize the initial noise. Extensive experiments demonstrate that NeoMap significantly outperforms all existing methods across 3 standard novel view synthesis benchmarks, including the challenging Tanks-and-Temples, LLFF and DAVIS datasets, achieving state-of-the-art generation fidelity and top-tier view consistency.

Jinxi Li, Tianyi Zhang, Yafei Yang +4

Shenzhen Research Institute, The Hong Kong Polytechnic University · vLAR Group, The Hong Kong Polytechnic University

Multi-View ConsistencyVideo Diffusion ModelsDynamic Novel View Synthesis
AskPDF
Jul 2, 2026

ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning

Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-frame accuracy but suffer from temporal drift due to limited context windows, while generative methods improve consistency and generalization at the cost of extensive training data (10M+ samples) and lack of geometric precision. In response to these issues, we introduce ICDepth, a framework that adapts pre-trained text-to-video diffusion transformers for video depth estimation via In-Context Conditioning (ICC), leveraging their rich spatial-temporal priors. To address key challenges in transferring ICC from generation to dense prediction, we propose: (1)SAND-Attention, which ensures precise spatial-temporal alignment via shared RoPE and enforces unidirectional attention to prevent noise contamination; (2)SRFM, which injects DINOv2 semantic and resolution priors to enhance geometric precision. ICDepth achieves state-of-the-art results on multiple benchmarks with remarkable data efficiency, trained on only 0.8M frames (66--13×13\times less than competing generative methods), while demonstrating strong zero-shot generalization to diverse domains.

Xuanhua He, Jiaxin Xie, Mingzhe Zheng +1

The Hong Kong University of Science and Technology, Hong Kong SAR, China

Video Diffusion ModelsDepth EstimationMonocular Depth EstimationIn-Context LearningVideo Depth Estimation
AskPDF
Jul 1, 2026

TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control

Controlling the motion of multiple objects in image-to-video (I2V) generation requires preserving object identities while enforcing adherence to distinct target trajectories. This becomes particularly challenging as the number of objects increases and their paths intersect or occlude one another. Existing approaches entangle multiple trajectories within a shared, dense conditioning signal, making object-level correspondence difficult to preserve in crowded scenes. We depart from this paradigm and enforce a strict, per object spatial constraint that isolates instances independently. Our method, TrajLoc, achieves this directly within the attention layers by substituting the cross-attention weights of each object token with a Gaussian heatmap centered on its target location at every frame. The same per object token interface carries trajectory and depth through a learned embedding and preserves identity by encoding first frame appearance in place of an object token. Evaluations across six datasets, featuring up to 20 simultaneously controlled objects and out of distribution real world scenes, demonstrate that our method consistently improves both visual fidelity and trajectory adherence. Applied to two architecturally distinct backbones (CogVideoX 5B and WaN 2.1 14B), our approach achieves average gains of +4.3 dB PSNR and a 51% reduction in trajectory end point error compared to the strongest baselines. Project page: https://sela-omer.github.io/traj-loc/

Omer Sela, Inbar Huberman-Spiegelglas, Michael Rotman +2

Amazon Prime Video · Tel Aviv University

Image-to-Video GenerationVideo Diffusion ModelsCross-AttentionControllable Video GenerationTrajectory-Guided Video Generation
AskPDF
Jul 1, 2026

RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation

In DiT-based video generation models equipped with 3D Rotary Position Embeddings (3D RoPE)\textbf{DiT-based video generation models equipped with 3D Rotary Position Embeddings (3D RoPE)}, the attention mechanism remains a primary computational bottleneck due to its quadratic complexity with respect to sequence length. While quantized FlashAttention\textbf{FlashAttention} offers a promising path toward hardware acceleration, existing low-bit quantization methods overlook two critical challenges in this setting: 1)\textbf{1)} applying online rotation matrices -- a widely used technique for mitigating outliers in Queries (QQ) and Keys (KK) -- is difficult to reconcile with RoPE\textbf{RoPE}; and 2)\textbf{2)} the non-negative attention matrix P=exp⁡(QK−max⁡(QK))P = \exp(QK - \max(QK)) makes symmetric quantization waste half of the 4-bit dynamic range. In this work, we observe that the outlier distributions of QQ and KK are strongly affected by the dimensional partitioning of 3D RoPE\textbf{3D RoPE}. Based on this finding, we propose RotateAttention\textbf{RotateAttention}, an efficient mixed-precision INT4 FlashAttention\textbf{mixed-precision INT4 FlashAttention} framework tailored for DiT-based video generation models with 3D RoPE\textbf{DiT-based video generation models with 3D RoPE}, using selective FP16 fallback\textbf{FP16 fallback} for accuracy-sensitive attention blocks and denoising steps. RotateAttention introduces two core techniques: 1) RoPE-aware Rotation\textbf{1) RoPE-aware Rotation}, which employs either mergeable rotation matrices that can be fused into RoPE or negligible-overhead matrices to mitigate RoPE-induced outliers in QQ and KK; and \textbf{2) Range-optimized P Quantization}, which uses fixed scales and zero-points to fully exploit the INT4 numerical range\textbf{INT4 numerical range} with minimal computational overhead. Experiments show that RotateAttention\textbf{RotateAttention} preserves video generation quality nearly identical to full-precision baselines while achieving up to 1.68×\times end-to-end speedup and 2.2×\times kernel-level acceleration.

Yaofu Liu, Wanli Lan, Jinxi Li +2

The Hong Kong University of Science and Technology, Hong Kong SAR, China · Independent Researcher, China

Mixed-Precision QuantizationRotary Positional EmbeddingsVideo Diffusion Models4-Bit QuantizationRotation-Based QuantizationAttention Quantization+1
AskPDF
Jun 30, 2026

Bridging Video Understanding and Generation in a Unified Framework

Recently, unified image generation and understanding have been extensively explored. However, extending such unified modeling paradigms to the video domain remains largely underexplored. A central challenge is that video understanding favors compact, discriminative semantic representations, whereas video generation requires dense signals that preserve visual details and temporal coherence. Videos naturally capture both spatial semantics and temporal dynamics, making them a more suitable modality for unified multimodal modeling compared to static images. In this paper, we propose Vega, a unified framework that bridges video understanding and generation. Vega leverages a shared vocabulary to jointly model text and visual representations and employs a hybrid architecture combining autoregressive (AR) prediction with diffusion-based rendering. Specifically, the AR model focuses on predicting semantically meaningful visual tokens for keyframes, providing a structured representation that guides the diffusion module in rendering dense, high-resolution video frames. Extensive experiments demonstrate that Vega achieves strong performance on video generation benchmarks such as VBench and video understanding benchmarks like VideoMME.

Yuqi Wang, Runyi Li, Ruoyu Feng +3

arXiv:2606.31326v1

Video Diffusion ModelsUnified Multimodal ModelsAutoregressive Video Generation
AskPDF
Jun 29, 2026

EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics

DiT video generation is latency-intensive due to iterative full-frame denoising, while prior cloud-edge methods largely rely on static inter-step decoupling and cannot leverage inter-frame similarity or adapt to system dynamics. We propose EcoVideo, an entropy-orchestrated framework for dynamic inter-frame decoupling: early-stage self-attention entropy provides a training-free estimate of frame-wise information density for frame selection; a cloud large model denoises sparse high-entropy keyframes; and an edge lightweight model reconstructs the remaining frames via motion-aware interpolation with refinement for temporal stability. EcoVideo further adapts the keyframe budget and edge refinement depth to real-time bandwidth and compute availability, optimizing end-to-end latency under constraints. Experiments on representative DiT video generators show improved quality--efficiency trade-offs and up to 2.9x end-to-end speedup in low-bandwidth, compute-limited edge settings. Code is available at https://github.com/IF-LAB-PKU/EcoVideo.

Jiayu Chen, Hengyi Zhang, Maoliang Li +5

School of Computer Science, Peking University, China · International School, Beijing University of Posts and Telecommunications, China · School of Information Science and Technology, Beijing Forestry University, China +1

Video Diffusion ModelsEdge ComputingVideo GenerationEfficient Video Generation
AskPDF
Jun 29, 2026

The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction

4D hand motion reconstruction from egocentric video is bottlenecked by clear limitations of existing methods: image-based pipelines depend on a detector that fails under heavy occlusion, while video-based methods rely on temporal modules learned only from scarce hand-pose annotations, a narrow signal insufficient to model motion dynamics, occlusion reasoning, and hand-object interaction. These capabilities, however, are exactly what video generative models must implicitly acquire when trained to synthesize coherent video at internet scale. Motivated by this, we present ViDiHand, which leverages the representations of a pretrained video diffusion model to reconstruct 4D two-hand pose. We adapt it via a hand-overlay rendering objective that specializes its features for hands while preserving its world priors. A decoder then recovers metric-scale pose from the adapted features. The whole pipeline operates directly on full frames--no detector, no infiller, and no test-time optimization. On ARCTIC, HOT3D, and HOI4D, ViDiHand substantially outperforms prior methods, establishing video diffusion models as a powerful new foundation for hand motion reconstruction and a promising route to scalable in-the-wild data collection for embodied AI. Project page: https://vidihand.github.io.

Yuxi Wang, Chengkai Jin, Yufei Liu +6

1Nanyang Technological University · 2Shanghai Jiao Tong University

Articulated Object ReconstructionVideo Diffusion Models3D Hand Pose Estimation
AskPDF
Jun 29, 2026

Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation

Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve realism. These signals, however, incur substantial computational overhead, require costly human annotations, and often yield limited improvement in fine-grained local details. In this paper, we argue that your data manifold is secretly a reward model. By explicitly modeling the manifold structure of high-quality Supervised Fine-Tuning (SFT) data and encouraging video latents to lie on this manifold, we derive dense, differentiable, and nearly cost-free reward signals that significantly improve video quality, particularly in mitigating low-level distortions. Our modeling builds upon Local Coordinate Coding (LCC), which captures the skeleton' of the manifold. However, directly applying LCC suffers from mean regression, pulling latents toward the geometric mean and losing high-frequency details. We therefore extend it to Shell Local Coordinate Coding (Shell-LCC), which models the manifold surface' as an isotropic shell to align with the true high-density region. Experiments demonstrate that our approach improves realism, enhances high-frequency details, reduces over-smoothing artifacts, and alleviates motion blur.

Shihao Zhang, Yunzhi Li, Yuguang Yan +4

Huawei Central Research Institute · Guangdong University of Technology

Reward ModelingDiffusion Model GuidanceVideo Diffusion ModelsT2V GenerationManifold Learning
AskPDF
Jun 27, 2026

SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending

While diffusion models excel in video restoration, their reliance on extensive iterative steps limits efficiency. Conversely, aggressive single-step distillation often compromises fine texture recovery. To achieve an optimal balance, we present SATB-VR, a few-step paradigm that jump-starts the denoising process via an auxiliary predictor, explicitly bypassing early low signal-to-noise ratio (SNR) steps. However, naive joint training of the predictor and the denoiser inherently introduces a severe train-inference discrepancy. To resolve this, we propose the SNR-Aware Trajectory Blending (SATB) strategy. During the forward process, SATB constructs the noisy input by dynamically blending the predictor's output with the ground-truth trajectory based on the SNRs. This forces the denoiser to robustly compensate for initial prediction errors while smoothly converging to the clean data manifold. Furthermore, we introduce a Denoiser-Driven Consistency (DDC) loss, leveraging the concurrently updated denoiser as a dynamic evaluator to explicitly align internal features and boost predictor accuracy. Extensive experiments demonstrate that, under flexible few-step inference regimes (\eg, ≤5\le 5 steps), SATB-VR performs favorably against existing approaches on synthetic, real-world, and AIGC benchmarks.

Haoran Bai, Xiaoxu Chen, Xiaoyu Liu +4

1Alibaba Group · 2Harbin Institute of Technology · 3Xi’an Jiaotong University

Video Diffusion ModelsFew-Step Diffusion SamplingDiffusion Model AccelerationVideo RestorationDiffusion Model Inference Acceleration
AskPDF