Video Diffusion Models

Face video restoration from degraded observations is challenging, as it requires simultaneously recovering visual fidelity, temporal consistency, and subject identity. Existing approaches are often either reference-free, which can lead to identity loss when person-specific facial details are lost, or subject-specific, which limits generalization to unseen identities. We propose a subject-agnostic, reference-guided framework for identity-preserving face video restoration. Our method introduces bimodal perceptual-descriptive identity conditioning into a pretrained flow-based text-to-video generator and employs a two-stage training strategy to strengthen identity guidance during restoration. Experiments show that our approach improves restoration fidelity, temporal consistency, and identity preservation, achieving superior performance under challenging video degradations, including downsampling, blur, noise, and compression artifacts. The code is available under: https://github.com/batuhanntosun/RG-FVR.

Sparse attention accelerates Diffusion Transformers (DiTs) for video generation by computing only the important tokens while skipping the rest. The token selection strategy is key to balancing sparsity and accuracy. We formulate the token filtering process as a dual-goal optimization problem: maximizing sparsity and minimizing accuracy degradation. Existing algorithms cannot fulfill both objectives simultaneously. For example, Top-p only considers the accuracy constraint, while Top-k maintains a fixed computational budget but loosens the accuracy constraint. This paper demonstrates that maintaining a fixed recall rate is sufficient for ensuring accuracy, whereas a fixed threshold is suboptimal for reducing computational cost. Therefore, we propose a dynamic thresholding scheme to improve sparsity while maintaining the same level of accuracy. Furthermore, our algorithm is deeply integrated with Flash Attention (FA), eliminating the need for any additional masking computation overhead. Experimental results on Wan 2.2 validate that, compared to the BLASST algorithm which is also integrated with FA, our dynamic thresholding strategy enhances sparsity from 61.42% to 82% with a VBench metric drop of less than 5%. This results in an approximate 15% in attention computation and a $1.61\times$ increase in computational efficiency, which is 1.18x higher than that of BLASST.

Re-rendering an existing video from a novel camera viewpoint requires the output to follow the prescribed camera trajectory while preserving the appearance and dynamics of the original scene across every frame. Existing methods rely on per-frame pose embeddings, noisy point-cloud renderings, or implicit learned correspondences, none of which provides an explicit, temporally continuous link between source and target pixels. We propose Track2View, which conditions a video diffusion transformer on paired 3D point tracks: sparse trajectories of scene points projected into both the source and target camera views. These tracks provide explicit spatiotemporal correspondences that are temporally continuous by construction, encoding what content should appear where and when. At the core of Track2View is a dual-view track conditioner that transfers visual context from source to target view through parameter-free geometric operations and learned temporal aggregation, ensuring generalization to arbitrary camera trajectories without memorizing specific motions. We further introduce a data curation pipeline that extracts one-to-one track correspondences by running a 3D point tracker on temporally concatenated multi-camera view pairs. On a 400-video benchmark spanning static and dynamic scenes, Track2View achieves state-of-the-art results across visual quality, view synchronization, and camera accuracy, reducing rotation error by 30-65% and translation error by 61-72% relative to leading baselines. Project page is available at this https URL: https://qjizhi.github.io/track2view

Anonymizing human-centric video data is an understudied problem. Prior anonymization techniques either blur or redact pixels at the cost of realism and downstream utility, or generate frame-by-frame at the cost of temporal coherence. We introduce ReGenHuman, the first full-body video anonymization pipeline that is simultaneously realistic, temporally consistent, and anonymous by construction. Contrary to past approaches which redact or edit the inputs directly, we propose a regenerate, don't edit paradigm. Our approach composites 2D pose, segmentation, and monocular depth into two complementary conditioning streams - StructAll and StructHuman, which are used to fine-tune a video-to-video diffusion backbone on in-the-wild human videos, synthesizing the human regions entirely from identity-free structural cues. We evaluate our model on privacy, quality, and utility, and show that our ReGenHuman achieves the best tradeoff across all three axes against current baselines. We further show that our anonymized videos remain effective for downstream tasks, including video question answering.

Recent advances in diffusion-based video generation have significantly improved visual quality and short-term temporal coherence. However, existing methods still struggle to produce videos with physically consistent and causally plausible dynamics, especially in scenarios involving long-horizon interactions. This limitation arises from the fact that video diffusion models primarily learn physical consistency implicitly, while vision-language models can directly model physical laws. Based on this idea, in this work, we propose CausalMotion, a training-free framework that injects explicit physical reasoning into video generation through structured intermediate representations. Our key idea is to decouple reasoning from generation by leveraging a vision-language model to decompose a text prompt into a sequence of causally consistent keyframes and object-centric motion trajectories. These representations are then aligned and integrated as soft constraints to guide a pretrained video diffusion model during inference. This design enables explicit modeling of object dynamics and causal transitions without requiring additional training or supervision. Extensive experiments show that our method consistently improves physical plausibility and temporal coherence, particularly in dynamics-intensive scenarios, while maintaining high perceptual video quality.

Large-scale video diffusion models often fail to preserve 3D structure over time, causing geometric drift and implausible motion under viewpoint changes. Existing methods usually enforce geometric consistency by using explicit geometry reconstructions, such as depth maps, point clouds, or reconstructed 3D structures, to define conditions, supervision, or reward signals, making the generator sensitive to errors from upstream geometry pipelines. We propose VideoWeave, a latent-space post-training framework that uses implicit geometry-model features to constrain the generative distribution, providing a more flexible and non-rigid form of guidance that mitigates the impact of reconstruction errors from geometry models. Specifically, VideoWeave adapts these features into geometry latents and jointly models them with video latents in a shared denoising space, allowing geometry to shape the generative distribution during training. To support this process, we build GeoVid-80K, an 80K-video dataset with paired appearance and geometry representations. Experiments on text-to-video and image-to-video generation show that VideoWeave improves geometric coherence while preserving strong visual quality. VideoWeave project page at https://videoweave.github.io/

While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current practice requires training a separate Low-Rank Adaptation (LoRA) module for each effect, incurring substantial data curation and iterative optimization costs that hinder interactive control. We present Prompt2Effect, a weight-driven hypernetwork that amortizes per-effect training by directly synthesizing effect-specific LoRA weights in a single forward pass. Unlike prior hypernetworks that regress adapter weights purely from semantics, Prompt2Effect is explicitly conditioned on the frozen base model weights, grounding prediction in the structural geometry of each layer. Furthermore, instead of predicting raw LoRA matrices, we introduce an SVD-canonicalized parameterization that resolves factorization ambiguity and stabilizes large-scale synthesis. Extensive experiments demonstrate that Prompt2Effect achieves on-par or superior video quality and effect alignment compared to conventional LoRA fine-tuning, while reducing the computational cost from 56 GPU training hours to 3.3 seconds of hypernetwork inference. When used as initialization for subsequent fine-tuning, our predicted weights further improve final performance and accelerate optimization by approximately 10x.

Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions. Together, these elements demand a level of fine-grained control beyond current text-to-video models. Existing work addresses each axis in isolation: multi-subject personalization, temporal control, multi-shot synthesis, or camera control; no prior framework jointly integrates all four. We present CineOrchestra, a unified video diffusion model that controls subjects, events, cameras, and shot transitions simultaneously. Our key insight is that these heterogeneous cinematic elements share a fundamental structure: each is an entity acting over a specific temporal interval, which can therefore all be expressed through one shared structure of entity-centric conditioning primitives, augmented with reference images for visual entities. This formulation reduces the architectural challenge to a single positional encoding problem, which we solve with two parameter-free coordinated rotary embeddings: (a) an interval-sampled temporal RoPE that yields consistent attention behavior across events of dramatically varying duration, and (b) a 2D entity-temporal cross-attention RoPE that disambiguates per-entity conditions and routes each to its corresponding spatiotemporal region. On two new benchmarks, CineOrchestra outperforms six per-axis specialists on dense caption following and shot-transition timing, with consistent gains in a pairwise user study and component ablations. Project page: https://snap-research.github.io/CineOrchestra

We present Flex4DHuman, a multi-view video diffusion model that transforms a monocular or sparse multi-view video of a dynamic subject into synchronized dense multi-view videos using only relative camera-pose conditioning. Unlike prior human-centric methods that rely on skeletons, depth maps, normals, or rendered target-view geometry, Flex4DHuman requires no explicit geometry priors and instead conditions generation through relative camera-pose positional encoding. The generated videos can be directly ingested by downstream reconstruction pipelines to create dynamic 4D Gaussian splats. Built on the Wan 2.1 1.3B text-to-video model, Flex4DHuman preserves the backbone architecture and encodes camera and view information through a five-axis positional encoding that extends spatio-temporal RoPE with view indices and continuous SE(3) relative camera geometry. A three-stage curriculum progressively trains the model for pose following, flexible reference-to-target view generation, and temporal rollout. To support temporal rollout, we train with clean historical target-view tokens. We also add multi-view captions to enable test-time text control. Combined with an off-the-shelf 4D Gaussian Splatting stage, our framework lifts monocular static-camera videos into dynamic 4D Gaussian splats. Experiments on DNA-Rendering and ActorsHQ show that Flex4DHuman surpasses prior state-of-the-art methods, while the same formulation generalizes to animal categories after mixed human-animal training. These capabilities make Flex4DHuman a practical step toward scalable 4D content creation from casual monocular videos for simulation, gaming, AR/VR, and video re-shooting.

Cloning camera motion from reference videos is an important task in video generation, as videos provide intuitive and precise control. Existing methods either directly use parametric representations that fail to handle multi-shot generation or synthesize cross-paired data, which suffer from data scarcity, resulting in poor performance in complicated camera motion cloning. To address these issues, we introduce a general camera motion representation that encodes cameras as grid motion videos. This camera grid represents the camera parameters visually and supports the integration of diverse trajectories for multi-shot video generation. Building upon this, we propose OmniDirector, a unified framework trained on a million-scale camera grid-video pairs that coordinates characters, actions, and cameras to provide director-level control for multimodal diffusion transformers. Furthermore, we design a novel hierarchical prompt expansion agent that harmoniously integrates different control signals by systematically describing camera motion and visual content through understanding signal relationships. Extensive experiments demonstrate the superior performance and outstanding controllability of our framework. Project page: https://ymlinfeng.github.io/OmniDirector.github.io/

Pretrained video generators are promising visual world models that exhibit emergent task-solving abilities; however, their reliance on detailed textual descriptions limits their direct use for planning and decision-making. Existing approaches either outsource this reasoning to language or vision-language models, or rely on supervised fine-tuning with paired task-execution videos, which are costly to collect and difficult to scale. We propose a scalable framework that elicits task-solving ability in such models by combining self-distillation with reinforcement learning. Given an unlabeled scene image, a vision-language model generates a candidate task and a detailed step-by-step solution. The solution conditions a pretrained video diffusion model, the Demonstrator; we distill its behavior into an Executor conditioned only on the image and a short task prompt. This transfers execution knowledge from caption-guided generation to instruction-conditioned task solving without curated task-video supervision. We further improve the Executor with reinforcement learning from VLM feedback, exploiting the asymmetry between judging whether a sampled video satisfies a task and generating the solution. Experiments on our proposed WorldTasks-Benchmark and the DreamGen robotics benchmark show that the Executor surpasses the Demonstrator under our VLM-based evaluation protocol and transfers competitively to robotic tasks.

Subject-preserving video generation is not solved by frontal-face similarity alone: a generated person must remain recognizable across motion, large viewpoint changes, expression shifts, occlusion, scale variation, and conflicts among text, first-frame, and identity references. We argue that the central bottleneck is the point-reference paradigm, which collapses identity into a single static observation entangled with pose, accessories, lighting, background, and camera statistics. We introduce Argus, a Wan-based framework centered on Stacked Multi-View Identity Mosaic Injection (SMII). SMII converts MLLM-selected image/video identity evidence into a 3*3 stacked mosaic, synchronizes the mosaic with the current diffusion time, and injects it as negative-time read-only memory in Wan's native token space. This turns identity from an external clean adapter or a single reference image into a compact dynamic distribution. Around SMII, an MLLM Identity Director selects informative identity moments and resolves condition conflicts, while no-cross-pair counterfactual training, Temporal Identity Annealing, and Adaptive Self-Likeness Guidance improve robustness without paired subject-video supervision. We further release HardID-Celeb, a public-figure identity-stress benchmark, and introduce YawScore and OccScore to probe large-yaw and first-frame-occlusion robustness. Argus achieves state-of-the-art results on OpenS2V-Eval Human-Domain, reaching 64.38 Total Score, 71.86 FaceSim, 51.62 NexusScore, and 79.14 NaturalScore. On HardID-Celeb, Argus obtains 76.80 FaceSim and improves YawScore and OccScore by 12.60 and 15.10 points over the strongest baselines, demonstrating that dynamic identity memory and large-scale counterfactual self-supervision are highly effective for subject-preserving video generation.

Current identity-consistent video generation methods struggle to preserve appearance fidelity under large viewpoint changes. While introducing multi-view reference input offers a natural solution, progress remains constrained by the lack of effective frameworks for multi-view inputs and the scarcity of multi-view data. We address these challenges by proposing HarmoView, a robust framework for identity-consistent video generation that effectively integrates multi-view cues through three architectural refinements complemented by a staged training curriculum. Specifically, we first introduce Multi-level Feature Injection to anchor identity fidelity; by injecting raw ViT features from frontal references alongside text tokens via cross-attention, MFI provides persistent low-level appearance anchors that complement the high-level identity features within DiT blocks, leading to enhanced identity preservation. Then, we employ learnable proxy tokens to unify heterogeneous reference layouts across single-/multi-view settings while simultaneously resolving the reference-view mismatch problem. Jump-RoPE is further developed for identity-wise feature isolation to reduce identity crosstalk. To activate these structural capabilities while preserving the original generative priors, we propose the Progressive View Curriculum. This four-stage training strategy employs view dropout to facilitate a stable transition from vanilla T2V generation to high-fidelity, identity-persistent spatial reasoning. Furthermore, we construct a large-scale multi-view dataset to address the issue of data scarcity. Extensive evaluation on our multi-view benchmark, comprising 100 manually-curated cases spanning 52 unique identities, demonstrates that HarmoView significantly outperforms open-source baselines and matches leading closed-source engines, achieving state-of-the-art performance in identity-consistent video generation.

Modern Diffusion Transformers for video generation provide limited control over the progression of time and the editing of temporal dynamics. We propose a temporal-control methodology that extends a pretrained DiT with explicit time editing, allowing control over motion speed and temporal structure without redesigning the backbone. Its core implementation augments the pretrained model with a lightweight temporal module, preserving the original generative prior while expanding its controllable dynamic range.

Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed in RGB space. This design is both computationally expensive, requiring repeated rendering and VAE encoding, and inherently lossy, as the round trip through pixel space discards rich features of the learned latent representation. In this paper, we introduce latent spatial memory for video world models, a persistent 3D cache that stores scene information directly in the diffusion latent space, avoiding pixel-space reconstruction. Building on this, we propose Mirage, a latent-space spatial memory framework that constructs the memory by lifting latent tokens into 3D via depth-guided back-projection and queries it by synthesizing novel views through direct latent-space warping. This unified formulation eliminates both the information loss of pixel-space reconstruction and the computational burden of repeated encoding and rendering. Experiments show that latent spatial memory achieves up to 10.57$\times$ faster end-to-end video generation and 55$\times$ reduction in memory footprint relative to explicit 3D baselines. Leveraging the geometric prior of the diffusion model, Mirage attains state-of-the-art performance on WorldScore and strong reconstruction quality on RealEstate10K.

We present Echo-Memory, a controlled study of memory mechanisms in action-conditioned world models. These models generate multi-segment videos from a first frame, text prompt, and camera-action sequence, but their central failure is often memory rather than local image synthesis: after the camera leaves and returns, the scene or salient object may silently change. Existing memory designs are hard to compare because gains are entangled with backbone, training, retrieval, and evaluation differences. Echo-Memory fixes the action-to-video interface and varies only how history is stored and read by the generator. Under a shared video diffusion backbone, optimizer, camera-action representation, sampler, and evaluation pipeline, we compare raw context, compression-based memory, spatial summaries with different read-out paths, and state-space recurrence. This matched matrix separates four otherwise conflated axes: capacity, compression, read-out, and recurrence. We also evaluate memory through a three-branch protocol: replay quality, in-domain loop revisit, and open-domain return probes. The branches routinely disagree, showing that replay fidelity is not a sufficient proxy for remembering a world. Three findings follow. Raw context is a strong capacity baseline and improves open-domain return far more than it improves replay metrics. Compactness is not a free substitute for capacity: aggressive spatial and hybrid-compression memories lose the salient evidence needed for return. Finally, block-wise state-space recurrence is the strongest open-domain return mechanism in our matrix, showing that the structure of implicit memory matters as much as the decision to use it. These results provide a compact protocol for studying memory in action world models beyond isolated replay metrics.

Real-time video restoration (VR) for live streams requires high-resolution outputs under strict per-frame latency constraints. Existing one-step diffusion-based VR models remain difficult to deploy on consumer-grade GPUs due to two main bottlenecks: quadratic spatial attention at high resolutions and the latency-memory overhead of large video autoencoders. We present SwiftVR, a streaming one-step generative VR framework that reduces both bottlenecks under a causal chunk-wise protocol. For attention, mask-free shifted-window self-attention gathers each spatial window into a dense tensor via deterministic indexing, keeping all attention calls on the dense scaled dot-product attention path without masks, cyclic shifts, padding, or hardware-specific sparse kernels. Because SwiftVR uses only standard dense SDPA calls, the trained model transfers to consumer GPUs without retraining or custom kernels. For autoencoding, a lightweight Restoration-aware Autoencoder enables fast chunk-wise decoding while preserving reconstruction quality. On a single H100, SwiftVR sustains 31FPS at 2560x1440 and 14FPS at 3840x2160, whereas all compared diffusion-based VR baselines exceed the memory limit at 4K. On a consumer RTX5090, SwiftVR reaches 26FPS at 1920x1080. To our knowledge, SwiftVR is the first generative VR model to achieve real-time 1080p streaming on a consumer-grade GPU, while attaining strong no-reference perceptual quality with lower inference cost. Project is available at https://h-oliday.github.io/SwiftVR.

Adapting large-scale pre-trained video generators for Video Super-Resolution (VSR) in novel domains remains computationally prohibitive. Methods that reformulate generation as direct Low-Quality to High-Quality mappings deviate from the original generative formulation, demanding extensive fine-tuning. ControlNet-style adapters lose their efficiency under modern Diffusion Transformers since the absence of encoder-decoder hierarchy forces duplication of the entire backbone. We observe that flow matching offers a principled alternative for cross-domain VSR adaptation. By predicting a constant velocity field across all timesteps, the adaptation task reduces to learning a fixed injection pattern rather than time-varying transformations. Building on this insight, we propose LiteVSR, a minimalist framework that performs VSR using a completely frozen Diffusion Transformer with a lightweight State-Aware Adapter. The adapter employs a dual-stream architecture that extracts static structural cues from the LQ input and dynamic cues from intermediate denoising states, aligning them through time-dependent cross-attention to enable adaptive transition from structural alignment to texture refinement as denoising proceeds. LiteVSR achieves competitive restoration quality with only 11.25% trainable parameters and 12 GPU-hours of training on a single A100, while maintaining fast sampling (down to a single step) compatibility.

Estimating full-hand grasp pressure from egocentric video is critical for immersive VR and robotic manipulation, yet dense tactile sensing often relies on intrusive hardware. Existing vision-based methods predominantly rely on planar surfaces or fingertip contacts, failing to generalize to complex 3D object interactions. Therefore, we introduce EgoTactile, a benchmark pairing egocentric video with full-hand pressure supervision for diverse everyday objects, incorporating a bare-hand transfer subset to enable generalization to natural scenarios. Leveraging this benchmark, we first establish EgoPressureFormer as a discriminative baseline. Beyond this, to explicitly address the uncertainty in partial observations, we propose EgoPressureDiff, a conditional diffusion framework that adapts a large-scale pre-trained video diffusion backbone. By combining rich world knowledge priors with a Physically-Informed Feature Rectification layer to inject semantic constraints, our approach effectively infers plausible contact patterns and resolves visual-physical ambiguities. Extensive experiments demonstrate that our method achieves superior performance on the benchmark and robust transferability to in-the-wild scenarios. Our project page is available at https://egotactile.github.io/.

Video generative models have become increasingly powerful, but long-range consistency remains challenging to achieve because even a few dozen frames require impractically long transformer sequence lengths. We show that this issue can be mitigated by generating video using coarse-to-fine rollout within a multi-scale token space. Our approach is simple: first, we pre-train an autoencoder that compresses each frame into a hierarchy of tokens, with levels ranging from the typical latent resolution to only a handful of tokens per frame. The coarsest levels capture the most consequential information, such as scene layout and semantics, while finer levels add high-frequency appearance and texture. Then, we train a video diffusion model to generate these tokens using coarse-to-fine rollout. By carefully controlling the level of detail at which frames are generated and used as context during each rollout step, we are able to preserve long-range consistency in geometry and object permanence while spending less compute on the long-range consistency of less perceptually relevant details. We validate this approach using a custom dataset of long Minecraft videos, where it produces substantially more consistent rollouts compared to existing baselines.

Existing zero-shot video editing methods rely on pre-trained diffusion models, successfully achieving spatial control and basic temporal consistency but fundamentally fail to preserve the video's original temporal structure.This distinction is critical: temporal consistency ensures visual smoothness, but temporal structure dictates the video's high-level narrative, rhythm, and semantic flow. Without this preservation, the edited output, especially for long videos with complex semantic variations, becomes narratively incoherent and semantically ambiguous. To address this limitation, we introduce a novel zero-shot editing approach that, for the first time, explicitly focuses on preserving the source video's temporal structure. We achieve this by adaptively partitioning the video into semantically distinct clips based on feature similarity and selecting a representative anchor frame for each clip. To enhance both intra-clip fidelity and computational efficiency, we design a clip-adaptive token merging strategy which leverages the anchor's semantic dominance to stabilize the editing. Furthermore, we employ an alternating combination strategy that ensures seamless inter-clip transitions while maintaining semantic distinction. Extensive experiments demonstrate that our method achieves state-of-the-art results, successfully balancing the preservation of original temporal structure with computational efficiency, and setting a new benchmark for zero-shot video editing fidelity.

Recent advances in Diffusion Transformers have driven rapid progress in video generation and editing, yet these capabilities are still handled by separate, task-specific models. Building a unified framework that supports diverse video tasks remains an open challenge: existing unified attempts either require dedicated auxiliary encoders or lack explicit mechanisms to distinguish heterogeneous conditioning tokens, struggling when the number and type of visual conditions vary across tasks. We propose TIDE, a unified framework that integrates instruction-based editing, reference-guided editing, and multi-reference generation. At its core, we introduce per-token task embeddings that assign each input token a task-specific identifier, enabling the model to explicitly disambiguate target, source, and reference tokens. To simultaneously capture high-level semantic understanding and fine-grained structural fidelity, we design a dual-path conditioning scheme that couples a vision-language model with a VAE latent path for complementary signals. We further devise a multi-task progressive training strategy that incrementally introduces tasks of increasing complexity, effectively harmonizing diverse objectives and enabling smooth generalization across heterogeneous task distributions. Extensive experiments on multiple video editing and generation benchmarks demonstrate that TIDE achieves state-of-the-art performance across all evaluated tasks. Our project page is available at https://LittleWork123.github.io/tide.

Human image animation aims to generate a video from a static reference image, guided by pose information extracted from a driving video. Existing approaches often rely on pose estimators to extract intermediate representations, but such signals are prone to errors under occlusion or complex poses. Building on these observations, we present DirectAnimator, a framework that bypasses pose extraction and directly learns from raw driving videos. We introduce a Driving Cue Triplet consisting of pose, face, and location cues that captures motion, expression, and alignment in a semantically rich yet stable form, and we fuse them through a CueFusion DiT block for reliable control during denoising. To make learning dependable when the driving and reference identities differ, we devise a Same2X training strategy that aligns cross-ID features with those learned from same-ID data, regularizing optimization and accelerating convergence. Extensive experiments demonstrate that DirectAnimator attains state-of-the-art visual quality and identity preservation while remaining robust to occlusions and complex articulation, and it does so with fewer computational resources. Our project page is at https://directanimator.github.io/.

Estimating hand-surface contact pressure from an egocentric view is crucial for AR/VR devices, robotic imitation, and ergonomic analysis. Existing methods often discretize pressure signal and process frames independently, leading to quantization errors and temporal inconsistencies. We present EgoPressDiff, a conditional video diffusion framework that generates UV-pressure maps from visual input. The core of our approach is a multi-modal conditioning strategy, introducing a PoseNet and a Vertex Encoder to efficiently extract features from hand pose and 3D mesh vertices. These signals, along with depth information, guide the generative process to ensure the pressure fields are physically grounded. To effectively fuse these heterogeneous features, we further propose a Distribution-Calibrated Spatial Layer, which aligns their statistical properties before combination. Evaluated on the EgoPressure ego-view setting, EgoPressDiff achieves state-of-the-art results, improving Volumetric IoU by over 34% relative to prior baseline, while reducing MAE and maintaining high temporal accuracy. Our project page is at https://egopressdiff.github.io/.

Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis, yet they suffer from high inference latency and computational costs due to the quadratic complexity of 3D attention. Existing acceleration methods primarily reduce computational complexity within each individual denoising steps through techniques such as sparse attention and KV-caching. However, they rigidly adhere to the inherent constraint of the standard diffusion pipeline: every frame in the target video sequence must be subjected to a complete, dense denoising process across all diffusion timesteps. We observe that due to the corresponding contents and motions among adjacent frames, when keyframes with critical semantic transitions are anchored, the intermediate states of others often follow more predictable trajectories, which indicates that such uniform, dense denoising process is inherently redundant for natural video data. To this end, we introduce RhymeFlow, a training-free framework that decouples the denoising trajectories of different frames. Specifically, we first identify a sparse set of pivotal key frames that dominate the latent semantic evolution. Then, only these keyframes undergo dense, step-by-step denoising to ensure structural integrity, while non-keyframes progressively skip denoising steps to minimize computational cost. Since skipped intermediate states of non-keyframes break the temporal coherence in keyframe denoising steps, leading to visual degradation, we further introduce a latent trajectory projection module, which enables keyframes to interact with a complete and temporally consistent sequence representation. Extensive experiments on current DiT-based video generation models demonstrate our method outperforms existing baselines with higher inference speed and better visual quality.

Developing unified video generation and editing models capable of interpreting interleaved multimodal inputs is a promising yet challenging frontier field. Existing unified frameworks predominantly rely on massive models (typically 13B parameters or more) and incorporate source video conditions for editing by concatenating sequence tokens. This concatenation inevitably doubles the sequence length, quadrupling the computational complexity of the self-attention mechanism and introducing prohibitive overhead. To address these bottlenecks, we present LoomVideo, a highly efficient 5B-parameter unified architecture for both video generation and editing. LoomVideo replaces the standard text encoder with a Multimodal Large Language Model (MLLM) and employs Deepstack injection mechanism to align multi-layer MLLM features with the Diffusion Transformer (DiT). Crucially, we introduce a zero-overhead Scale-and-Add conditioning approach for video editing. By scaling and directly adding the clean source video latent to the noised target latent, this elegant design eliminates the need for token concatenation, drastically reducing computational cost while maintaining robust capabilities for complex, non-rigid edits. Furthermore, a Negative Temporal RoPE strategy is seamlessly integrated to handle multiple reference images. Extensive experiments demonstrate that our compact 5B model achieves state-of-the-art or highly competitive performance across comprehensive benchmarks, exhibiting exceptional superiority in e-commerce and fashion generation scenarios. Benefiting from the zero-overhead conditioning mechanism, LoomVideo achieves at least a 5.41x acceleration in inference speed compared to models of similar capabilities, paving the way for highly practical and efficient video foundation models.

Aggressive distillation of the diffusion U-Net inverts the per-frame bottleneck of real-time text-to-image pipelines: once the denoiser is a 4-step or 1-step distilled student, the text encoder becomes the critical path. This inversion is most acute in vision-aware edit diffusion, where the encoder is a multimodal large language model (MLLM). We study a 0.39B distilled edit U-Net paired with a 2.13B MLLM text encoder (Qwen3-VL) and present a streaming pipeline for this regime built on three mechanisms that keep the encoder off the denoiser's critical path rather than shrinking the encoder: asymmetric side-stream / main-stream CUDA pipelining with batched text-encoder amortisation, a compile-friendly ControlNet-LLLite reformulation that folds the whole U-Net + adapter stack into one fused graph, and a periodic conditioning-refresh schedule with a hook subset that amortises the per-frame conditioning cost. On a single consumer RTX 3090 Ti at 512x512 this sustains 27-30 fps over a 480-frame run; at the same operating point steady-state throughput scales to 55 fps on RTX 4090 and 74 fps on RTX 5090. This shows that once distillation is aggressive enough, further gains come from encoder-side systems work rather than further denoiser compression -- the opposite lever from the one the streaming-diffusion literature has optimised to date. We report video-rate streaming throughput, not interactive low latency, and locate our numbers against same-stack StreamDiffusion re-runs as systems context, not a superiority claim. The released oil-painting adapter generalises within in-clip noise to 19 unused DAVIS-2017 sequences and 15 non-DAVIS clips from seven sources; prompt-level generalisation to unseen styles is bounded and reported separately.

Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether these models internally encode physical structure, or merely reproduce motion patterns seen during training. We study this question by probing video diffusion models along latent trajectories corresponding to real videos with known physical plausibility. To obtain such trajectories, we approximately invert the deterministic sampling process by integrating the learned velocity field backward from a clean video latent to noise, giving access to the model's intermediate states and attention maps. Using these recovered trajectories, we show that physical plausibility is linearly decodable from diffusion transformer states across IntPhys and InfLevel, reaching around 81.27% average accuracy and outperforming dedicated representation-learning baselines such as V-JEPA and VideoMAE. Surprisingly, this signal is absent from the VAE latent input and emerges inside the denoising transformer itself, despite the model not being trained with a self-supervised predictive objective. These findings suggest that physically meaningful representations can arise as a byproduct of generative denoising.

World-action models (WAMs) jointly generate future video and robot actions through iterative diffusion, achieving strong performance on manipulation benchmarks but requiring tens of denoising steps, a cost that precludes real-time control. Step distillation has emerged as the natural remedy, but off-the-shelf methods break down in the joint video-action setting because video and action streams use different SNR-shifted noise schedules and reach training with substantially different marginal noise distributions, an asymmetry that single-modality distillation methods cannot accommodate. We introduce Flash-WAM, a modality-aware step-distillation framework inspired by consistency distillation that selects the consistency function for each modality to match its noise regime: a linear-gradient-scaling parametrization for the action stream's low-noise regime, paired with a variance-preserving parametrization for the video stream's high-noise regime, grounded in a structural analysis of the consistency-function family that characterizes the achievable gradient scaling under the consistency boundary condition. Instantiated on LingBot-VA, Flash-WAM compresses inference to a single step in each modality. On RoboTwin 2.0, this reduces per-chunk latency from $8.1$ seconds to $348$ ms on NVIDIA L40S, a $23{\times}$ speedup that enables real-time inference. Flash-WAM preserves task success on simulation benchmarks ($85.5\%$ RoboTwin 2.0, $95.7\%$ LIBERO) and substantially recovers real-world performance ($60\%$ average on a Unitree G1 humanoid robot), while naive consistency distillation drops to $24\%$ at the same step budget.

Large-scale video generation models have made remarkable progress in semantic consistency and visual quality, producing videos that are increasingly coherent and visually convincing. Nevertheless, the dynamics induced by pixel-level fitting do not naturally accommodate the regularities that govern real-world motion and interaction, resulting in persistent shortcomings in physical plausibility. To address this limitation, we propose PILA (Physics-Informed Latent Alignment), a framework that injects physics-structured latent guidance into the frozen flow-matching dynamics of pretrained video models. Specifically, PILA first employs anchored field estimation to map frozen-generator latents into an operational physical attribute bank organized by field-proxy slots, using observable motion as a kinematic anchor for constructing less directly observed proxies. To handle the heterogeneity of real-world dynamics, PILA adopts a mixture-of-experts design over physical categories. Label-prior masked expert routing selects category-specific operator experts, whose refinements are regularized by operational residuals abstracted from physical relations. Finally, the refined proxies are fused into the physical attribute bank and decoded into a correction to the flow-matching vector field, injecting physics-aware guidance while preserving the visual prior of the pretrained backbone. With staged adapter training on Wan 2.1-1.3B and direct transfer of the learned adapter to Wan 2.2-14B, PILA achieves state-of-the-art results on VBench-2.0, VideoPhy-2, and PhyGenBench in both visual quality and benchmark-measured physical plausibility.