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

812 papers72 papers in the last four weeks, down 36% on the four weeks before. 0.5% of all new papers.

Oct 31, 2026

Running a 20B Video Diffusion Transformer on Consumer Hardware: A Deployment and Measurement Report for MiniMax H3 on Apple Silicon

We report the end-to-end deployment and measurement of MiniMax H3, a 20.38-billion-parameter video diffusion transformer (DiT) - the count measured from the safetensors headers of the Q8 checkpoint as deployed locally (Section 3.2) - running entirely on consumer Apple Silicon hardware: an Apple Mac mini with M5 Pro chip and 64 GiB of unified memory. Using the official bf16-to-Q8 (8-bit, group size 64) quantization path executed locally on the machine, we produced a working text-to-video pipeline with no cloud dependency. We document the full deployment procedure, including two non-trivial blockers and their fixes, and report measured figures for build time, peak memory, and per-clip render latency across four resolution tiers (Draft 384x640 through Native 768x1344). A 15.08-second 576x1024 clip rendered in 4838.49 seconds with a measured MLX peak of 27.467 GiB. We further operated the system as an unattended production pipeline, completing 17 clips in 26.49 hours with zero render failures. A blind human review of the 17 production clips (generation prompts withheld) averaged 3.12, 3.18, and 2.94 out of 5 for structural integrity, temporal consistency, and visible artifacts. All figures in this report are our own measurements except where explicitly labeled as third-party data. This is a systems/empirical report; we make no claim of model innovation.
Oct 31, 2026

UniCaMo: Unified Camera and Motion Control for Video Diffusion Models

We present UniCaMo, an unified framework for joint control of camera and object motion in image-and-text-to-video diffusion models. Given a reference image, text prompt, sparse 3D object trajectories, and a 3D camera trajectory, UniCaMo constructs motion-consistent input noise that directly encodes the desired motion. Our 3D-grounded noise construction combines reference-derived noise propagation with a spherical Gaussian noise representation for newly revealed regions, providing a simple and effective motion prior without requiring reconstruction of unseen scene geometry. UniCaMo requires no architectural modifications or dedicated control modules and can be adapted using lightweight LoRA fine-tuning with low training data volume. Experiments on standard controllable video generation benchmarks demonstrate state-of-the-art motion controllability and high visual quality with minimal inference overhead.
Oct 30, 2026

CLiS: Plug-and-Play Attention Acceleration for Video Diffusion on TPUs via Certified Stabilization

High-resolution video diffusion relies on attention over long token sequences, making attention efficiency critical to generation latency. Our analysis identifies repeated maximum reductions and accumulator rescaling in online softmax as a bottleneck in long-context TPU attention. We propose CLiS (Certified Loop-invariant Stabilization), a training-free, plug-and-play optimization for video diffusion inference. CLiS fixes per-row stabilizers before the KV loop and certifies numerical safety per head, falling back to online softmax when certification fails. It integrates into existing fused-attention kernels without changing model weights or architecture. On Wan 2.2 and LTX-2 across TPU v6e and TPU7x, CLiS reduces diffusion transformer (DiT) step latency by up to 19.6% relative to tuned online softmax without measurable quality loss. Controlled TPU adaptations of prior GPU stabilization methods show performance or numerical-safety limitations. Preliminary causal LLM experiments also show up to 13.5% higher training throughput in continued pretraining and 7.7% in supervised fine-tuning.
Oct 30, 2026

Seeing the Unseen: Unified Visible--Invisible Motion for Physically Consistent Video Generation

Recent advances in video generation have achieved impressive visual quality, yet they often fail to produce physically consistent dynamics due to the lack of explicit modeling of underlying physical processes. Existing approaches either rely on simulators with strong assumptions or use coarse semantic guidance, and further struggle to effectively inject physical priors into generation models. In this work, we propose Seeing the Unseen, a unified framework for physics-grounded video generation. Our approach decomposes the problem into two stages: learning physical dynamics and injecting them into video synthesis. First, we introduce a lightweight Particle-based Graph Dynamics Simulator (PGDS) that learns generalizable physical interactions from data and predicts plausible 3D motion trajectories. Second, we propose a Visible--Invisible Motion Field (VIMF) that captures both motion observable in the input frame and motion that emerges over time due to object dynamics. This representation enables more complete and structured motion guidance compared to conventional physical signals. By integrating these trajectories into a diffusion-based generator, our method produces videos that are both visually coherent and physically consistent. Extensive experiments demonstrate improved motion accuracy, interaction consistency, and reduced physical artifacts compared to strong baselines.
Oct 29, 2026

AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers

Video diffusion transformers generate high-quality videos, but the quadratic cost of 3D full attention dominates their inference. Dynamic block-sparse attention reduces this cost by computing exact attention only on key/value blocks selected from current activations. However, its fidelity degrades under aggressive sparsity: blocks are scored from coarse summaries or formed by costly global clustering, pruned blocks vanish from the softmax, and whole tiles are kept or dropped even when only a few of their keys matter. To address these limitations, we propose Accurate Block Attention (AB-Attention), a training-free method that accurately approximates dense attention at high sparsity. Its Intra-Block Clustering Selector (IBCS) estimates block importance faithfully yet cheaply by clustering queries only within each query block, without permuting tokens. Sampling with Inclusion-Probability Weighting (SIP) then samples blocks in proportion to these estimates and reweights them by inverse inclusion probability, so that one pass estimates dense attention rather than truncating it. Finally, its kernel gathers key/value blocks much smaller than a tile into full tensor-core tiles, refining selection at no extra tensor-core cost. On Wan2.1 and HunyuanVideo, AB-Attention skips 89--92% of attention, whereas the baselines compute 1.8--3.6×\times as much, yet it still improves PSNR by up to 4.4~dB over the strongest baseline and achieves up to 2.23×\times end-to-end speedup. Our code is available at https://github.com/InfRec-Cardinal/AB-Attention.
Oct 29, 2026

Regional Anchor Routing for Multi-Object Motion Transfer

Compositional motion transfer requires a model to extract motions from multiple reference videos, and apply each motion to a user-specified object in one target scene. Existing methods normally struggle to reliably assign different reference motions to the correct target objects, thus a motion intended for one object may affect another. Meanwhile, some motion-specific tuning approaches are still facing another issue: they must run a new optimization whenever the reference video changes, making repeated transfers inefficient. To address these limitations, we propose RART, a framework that unifies object-wise motion extraction, target-region anchoring, and frame-aligned injection into a frozen video Diffusion Transformer for multi-object motion transfer. For each reference motion, RART extracts temporally ordered features from the masked reference video, and then conditions them on the target first-frame mask to form mask-anchored motion tokens. Frame-aligned motion cross-attention allows each generated frame to read only the motion tokens at the corresponding time slots, composing all object motions in one denoising process. During training, a motion-attention routing loss encourages each target region to attend to its corresponding motion tokens and reduces interference between objects. Therefore, RART can handle novel reference-target combinations without per-video optimization. Experiments show that RART achieves accurate motion preservation, efficient inference, and strong compositional generalization.
Oct 29, 2026

Seeing and Imagining as One: Unified Video Generation and 4D Perception for Embodied World Modeling

Embodied world models should not only imagine plausible futures, but also perceive the geometric, semantic, and motion structure of the evolving world. We present GenSight, a unified embodied world model that brings future video generation and dense perception into a single pretrained video diffusion transformer. GenSight uses a unified spatiotemporal representation for video, depth, embodiment segmentation, and first-frame-relative 2D flow. Built on a shared DiT backbone, GenSight uses lightweight task modulation to predict all modalities within the same architecture. All tasks are jointly optimized within a unified velocity prediction space. At inference, GenSight supports two complementary modes: multi-step future video generation with aligned dense predictions and single-step dense perception from an observed video. By unifying modality representation, model architecture, and prediction space, GenSight avoids separate modality-specific pipelines and couples appearance, geometry, semantics, and motion in a shared representation. It promotes cross-modal consistency and allows dense perception to benefit from the spatiotemporal priors learned through video generation. Trained on embodied manipulation data spanning multiple robot embodiments and human-hand interactions, GenSight demonstrates strong performance in both video generation and dense 4D perception, highlighting the effectiveness of unifying seeing and imagining for embodied world modeling.
Oct 27, 2026

Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence

Cross-view object correspondence identifies the same object across views. However, existing methods often rely on frame-wise matching or sequential tracking, which can propagate correspondence errors under appearance changes or occlusions. Therefore, we introduce cross-view temporal object correspondence, which requires preserving object identity across both views and time from a query mask. To address this, we propose XTrack, a unified framework which repurposes a pretrained video DiT with semantic and spatiotemporal priors for RGB-to-mask latent transport, jointly modeling cross-view matching and temporal tracking. However, naive video DiTs do not guarantee accurate cross-view grounding and often attend to semantically similar yet incorrect objects across views. Thus, we introduce focal cross-view attention alignment, hard negative conditioning, and local context crop strategies to ensure reliable grounding. Finally, beyond these architectural enhancements, we also tackle the lack of dense annotation by introducing a pseudo-label curation pipeline that converts sparse Ego-Exo4D annotations into dense supervision to enable effective video-level training. Our results demonstrate the effectiveness of XTrack as a unified framework, ensuring robust temporal consistency and identity preservation.
Oct 27, 2026

TAPESTRY: A Single Backbone for Video Generation and Robot Control

Pretrained video generation models encode rich priors about physical interactions, but leveraging them for robot control typically requires either resource-intensive video generation at test time or action heads trained from scratch that do not fully utilize the pretrained backbone. We introduce Tokenizing Actions as Video Patches in a Shared Transformer Policy (TAPESTRY), a world action model that repurposes a pretrained video diffusion transformer into a robotic policy without requiring video generation at inference. Our key idea is to treat robot actions as single-patch tokens in the video model's latent space. A lightweight linear projection maps each action timestep to the patch dimensions of the pretrained VAE, and the resulting tokens are processed by the same patchifying layers and transformer backbone used for video. The shared backbone is optimized through three diffusion objectives sampled per minibatch element: Video diffusion uses VAE latents from robot and human videos to establish dynamics priors. Joint video+action diffusion trains on robot demonstrations using a coupled diffusion timestep and an asymmetric attention mask. Action-only diffusion denoises actions conditioned on clean image latents. At test time, the model generates a compact action token sequence in a single DDIM step from pure noise, producing smooth action chunks at 84 ms per action chunk on consumer hardware and avoiding the cost of full video generation. Across simulation benchmarks and real-robot experiments, TAPESTRY achieves strong performance with substantially lower inference cost than comparable joint video--action policies. More information can be found at https://tapestry-wam.github.io.
Oct 27, 2026

Hy-Nomas: Towards Free-form Interactive World Generation

Interactive world generation requires models to follow successive commands while preserving relevant history and action consequences. We present Hy-Nomas, a video world model with an 8B diffusion backbone that supports free-form text instructions and continuous camera control across multiple interaction turns. It generates variable-length segments conditioned on current inputs and cached history. Our central design aligns structured video captions with action-aware causal attention: descriptive context remains accessible across segments, while action instructions are restricted to their intended temporal windows. A vision-language Prompt Enhancer (PE) translates user requests and multimodal interaction histories into structured conditions for the next segment. A multi-stage curriculum progressively introduces causal generation, text interaction, camera control, and training on model-generated histories, followed by diffusion distillation. In human evaluation, Hy-Nomas shows superior performance over existing world models. We release model weights, code and benchmarks, together with a lightweight adaptation workflow, to support reproducible research on interactive world generation.
Oct 26, 2026

TriTile: Three-Tier Attention for Video Diffusion Transformers

Attention over tens of thousands of visual tokens dominates the inference of video diffusion transformers (DiTs). Existing methods reduce this cost through sparsity, low precision, or both, but use a single precision for all kept tiles. We observe that the output error introduced by approximation varies widely across tiles. Many tiles can be skipped with little error, others must be computed but gain little beyond low precision, and a few retain substantial error even at low precision. We present TriTile, a training-free attention method that assigns each tile one of three approximation tiers: skipping it by replacing it with its block means, skimming it in NVFP4, or refining it with NVFP4 residual correction. A lightweight router predicts each tile's error under each tier from block statistics and spends extra compute on a tile only where it removes enough error; a single knob, a price on compute, controls the whole speed-quality trade-off. A fused kernel executes all three tiers in a single pass on the FP4 tensor cores. Over dense FlashAttention, TriTile speeds up generation by 1.38-1.83x on Wan2.2 at 23.0-27.6 dB PSNR, 2.28-2.32x on HunyuanVideo at 34.5-36.0 dB, and 1.84x on LTX-2.5 at 34.1 dB, and in every setting it Pareto-dominates every baseline in speed and PSNR.
Oct 26, 2026

Beyond Distribution Matching: Self-Supervised Representation Forcing for Few-Step Video Generation

Few-step distillation is essential for deploying modern video diffusion models. Among existing approaches, Distribution Matching Distillation (DMD) has emerged as a highly promising paradigm by achieving strong output-space fidelity without adversarial training, while remaining flexible across various student architectures. We observe, however, that DMD fundamentally relies on an output-space objective, lacking explicit regularization on the model's internal representations. As the distillation step count aggressively shrinks, this output-only supervision becomes insufficient, causing the distilled student to degrade in both fine-grained spatial structures and coherent temporal dynamics. To address this limitation, we introduce Self Flow Forcing (SF2^2), which incorporates a predictive representation loss into the DMD framework without altering its output objective. By providing the student and an Exponential Moving Average (EMA) teacher with heterogeneous noise levels, we establish an information asymmetry. This formulation forces the student to predict the teacher's internal representations from a more corrupted input, effectively integrating self-supervised representation alignment into distribution matching. Extensive experiments demonstrate that SF2^2 effectively mitigates temporal flickering and consistently improves both spatial fidelity and motion quality. Furthermore, the proposed mechanism is architecture-agnostic - seamlessly supporting both bidirectional and causal models - and requires no external feature extractors, introducing minimal computational overhead.
Oct 25, 2026

FlockWorld: Toward Population-Scale Multi-Agent Video World Models through Artificial Life Simulation

Most action-conditioned video world models remain limited to a single player, while existing multiplayer models support only small, fixed groups of agents. We introduce FlockWorld, an artificial-life environment built on Reynolds's Boids algorithm for studying population-scale multi-agent video world models. Specifically, FlockWorld renders synchronized egocentric crops, assigns distinct colors to preserve camera-agent identity across views, exposes rule-derived accelerations as actions, and lets the number of camera agents be configured independently of the size of the surrounding population. We further introduce FlockDiT, an action-conditioned latent diffusion transformer trained with flow matching on FlockWorld data to jointly generate synchronized egocentric videos for multiple agents. Our results suggest that joint generation benefits agent detection at density-matched settings and that diffusion forcing improves rollout fidelity. Together, FlockWorld and FlockDiT provide a controlled testbed for multi-agent video generation.
Oct 25, 2026

EditDistill: Is It Possible to Guide Video Editing with Image Editing?

Recent advances in image editing have enabled fine-grained and highly controllable visual modifications. However, achieving similar levels of controllability in video editing remains an open challenge, particularly for precise local edits, dynamic temporal effects, and consistent lighting across frames.In this paper, we propose EditDistill, a framework that distills image-level visual transformations from edits to guide video editing.Specifically, given a source video and an edit prompt, we first generate an edited version of the initial video frame using an off-the-shelf image editing model. We then distill the visual transformation of this original-edited image pair into a compact representation termed an edit descriptor.This descriptor is injected into a video diffusion model through our lightweight fusion module, which steers the denoising process toward the desired edit. To align the video trajectory with the demonstrated image edit while preserving motion and layout, we train with edit-descriptor alignment and DINO structural consistency losses, and derive an equivalent inference-time guidance formulation under flow matching.Extensive experiments demonstrate that our method achieves strong performance on standard benchmarks and produces high-quality video editing results across diverse scenarios. For more details and videos, please refer to the anonymous webpage: https://yu-shaonian.github.io/EditDistill-Web/.
Oct 25, 2026

X-World: Transferring Video Priors to Variable-View Robot Control

Video diffusion models provide a source of interaction representations for robot control, but transferring these representations requires reconciling variable camera inputs with heterogeneous action interfaces and closed-loop execution. We present X-World, a framework that transfers a video prior through a fixed-length token sequence to a shared action expert. A residual cross-view attention branch extends a pretrained video backbone to one, two, or three views while retaining its original self-attention path. A layer-aligned Q-Former aggregates backbone features, and dataset-specific modules map between native state and action interfaces and the shared action expert. Training separates video adaptation from action-only pretraining by freezing the video backbone in the latter stage, followed by joint target-domain post-training. The policy extracts video features with a single backbone pass and uses asynchronous action chunking for execution. On LIBERO, X-World reaches 98.5% mean success; its LIBERO-trained checkpoint obtains 76.5% on LIBERO-Plus without further adaptation. The seven-shift breakdown reveals gains in robot, language, lighting, and layout perturbations, alongside weaknesses under camera, background, and noise shifts relative to OpenVLA-OFT. On six dual-arm real-world tasks, it achieves 81.7% mean success over 20 trials per task. Removing video adaptation or cross-view fusion produces the largest observed success drops among the tested removals.
Oct 25, 2026

Learning the Autoregressive: Direct Score-Difference Estimation with Amortized Future Credit for Video Distillation

Few-step distillation for autoregressive (AR) video generation commonly first initializes an AR student and then refines it with distribution matching distillation (DMD). This refinement process faces two challenges. First, although initialization already yields a reasonably capable student, DMD obtains the refinement direction indirectly by estimating the full student score before forming the teacher-student correction. Second, detached-history training prevents the generator from assigning credit to a current chunk for its influence on subsequent chunks. We introduce Leta, a few-step distillation framework that addresses these challenges with ScoreDelta and FutureCredit. ScoreDelta directly estimates the teacher-student correction from denoising residuals, while FutureCredit learns an auxiliary cross-chunk update signal from vector-Jacobian products (VJPs) of next-chunk teacher residuals. Leta combines these signals into a joint teacher-guided update field in a single forward pass during generator updates. Teacher evaluations and credit VJPs are used only for estimator training. For ScoreDelta, we establish population equivalence to score-difference estimation and a conditional approximation advantage under limited capacity in a fixed-feature linear model. In our controlled experiments, Leta improves over DMD by 0.9 points on VBench and 0.66 on VideoAlign. This advantage persists at a higher generator update frequency (a generator-to-estimator update ratio of G:E=1:1), where Leta improves over DMD by 1.6 on VBench and 0.35 on VideoAlign. Project page: https://scdzx.github.io/Leta/.
Oct 24, 2026

Mix Forcing: Causal Pre-Training via Mixture Attention for Interactive World Models

While interactive video world models require autoregressive generation, directly adapting pretrained bidirectional video diffusion models into autoregressive ones with teacher forcing can disrupt their visual priors and degrade autoregressive generation quality. In this paper, we introduce Mix Forcing, a causal pre-training paradigm for interactive video world models, implemented with the Mixture-of-Bidirectional-and-Autoregressive (MoBA) attention. Mix Forcing jointly trains a video diffusion model with both teacher forcing and bidirectional training, yielding a strong causal initialization for few-step post-training. In self-attention, Mix Forcing leverages teacher forcing to learn causal next-chunk prediction for autoregressive rollout, while using bidirectional attention to preserve pretrained visual priors. To support online text interaction, Mix Forcing further adopts a chunk-wise cross-attention design that conditions each video chunk on a shared environment prompt and its own local prompt, without exposing future instructions to the current chunk. Following causal pre-training on a 14B image-to-video model, we apply consistency and distribution matching distillation to obtain a four-step autoregressive generator. Experiments on our internal benchmark and public benchmarks, including WBench and SANA-WM-Bench, show that our model achieves state-of-the-art visual quality and timely event following with precise camera control. Notably, our model supports high-fidelity long-horizon generation without quality degradation even over one-hour rollouts. Project page is here: https://zelingao98.github.io/mixforcing
Oct 22, 2026

SyncVid: World-Equivariant Diffusion for Synchronized Video Generation

Generating multiple videos of a dynamic scene from a single reference video requires synthesizing both observed and unobserved content consistently across viewpoints. Existing camera-control methods for video diffusion typically rely on architectural mechanisms, including camera embeddings, cross-view attention, and geometric conditioning. Although effective for static scene content, these approaches often struggle with the fine-grained, dynamic geometry that must remain coherent across views and over time. We synchronize the diffusion process itself by sampling the Gaussian noise prior in a canonical 3D space derived from the source video and rasterizing it into target cameras, rather than sampling independently in each 2D image plane. Our method, SyncVid, lifts a monocular video into a canonical 4D representation, associates noise with scene geometry and unseen space, and rasterizes the resulting structured noise into arbitrary views. Because rendering can introduce local correlations, we further propose a cross-view-consistent whitening procedure that decorrelates neighboring pixels while preserving correspondence across views. The structured noise serves as the diffusion prior for a LoRA-adapted pretrained video diffusion model, requiring no architectural modifications. By enforcing spatiotemporal and cross-view coherence at the source of stochasticity, SyncVid generates synchronized videos and improves both perceptual quality and cross-view consistency in our experiments. Project page: https://qualcomm-ai-research.github.io/SyncVid-Webpage.
Oct 22, 2026

WorldForge V2: Eliciting Camera-Trajectory Alignment in Video Diffusion Models

Video diffusion models have learned rich 3D/4D priors, making them promising for scene generation and video re-rendering. However, their use in spatial tasks is limited by imprecise camera control, spatial and temporal inconsistencies, and entangled camera motion with scene dynamics. Existing approaches, such as task-specific fine-tuning and post-process warping, often introduce visual artifacts, generalize poorly, or incur high computational costs. We propose WorldForge V2 to achieve accurate camera control while preserving the generative capabilities of pretrained video models. We first develop a training-free guidance framework using warped references to iteratively refine generation along a target camera path. Optical-flow analysis identifies motion-related latent channels for selective guidance, helping separate motion control from appearance. A dual-path strategy further compares guided and unguided predictions to correct artifacts from imperfect references. Together, these components guide viewpoint changes while preserving scene appearance and object motion. To reduce refinement costs, v-cache approximates the correction using the preceding denoising prediction, avoiding an additional model evaluation. We further extend motion localization from latent channels to network blocks and introduce Trajectory LoRA, which concentrates adaptation on blocks most responsive to trajectory guidance. A two-stage training strategy teaches these adapters to denoise the states encountered during guided generation, using limited supervision effectively. This enables reliable camera control with very little training data, with a single training scene already supporting generalization to unseen scenes. Quantitative and qualitative evaluations across multiple datasets show that our method achieves state-of-the-art generation quality and trajectory accuracy in camera-controlled video generation.
Oct 22, 2026

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

Cinematic video generation requires both temporal inference from limited inputs (i.e., sparse rather than frame-by-frame guidance) and factor-aware control of character, scene, action, and camera. Multimodal large language models (MLLMs) offer useful priors for both capabilities, but their representations are not automatically actionable for video generation: a Video Diffusion Transformer (DiT) may bypass them through native conditioning pathways, and using them does not ensure either factor-aware control or generation-compatible temporal prediction. We propose Factor-Aware Predictive Learning (FAPL), which establishes effective MLLM latent use as a shared prerequisite and then targets the two capabilities with complementary learning signals. First, latent-only generator grounding trains the DiT with a frozen MLLM and connector, strengthening the DiT's use of MLLM latents for generation. Second, for factor-aware control, paired videos specify a target-factor change and non-target preservation, and factor-span replacement trains the DiT to realize this relationship in its output. Third, for temporal inference, text-only and text-plus-complete-video observations share a video target, and the trained DiT is then frozen while the MLLM and connector are optimized through it. This final stage trains limited-input representations for generation while retaining complete-observation reconstruction as a complementary training mode. Extensive experiments demonstrate our consistently better performance on three cinematic video generation tasks (i.e., sparse-to-video, factor-aware editing, and multi-shot generation) over baselines and validate FAPL's contributions to MLLM feature use, temporal control, and factor coordination.
Oct 21, 2026

Latent Space Jam: Layout Guided Video Synthesis

Adding control to video generation often requires training, which demands additional computational resources, data, or architectural changes. We propose a training-free approach that utilizes pretrained video diffusion models to control object layout and motion using coarse layouts. Our method operates in two passes: first, it steers spatiotemporal placement through prompt-guided cross-attention to produce a coarse visual guide; second, this guide conditions the same model to generate a high-quality, layoutconsistent video. The approach enables coordinated motion with strong temporal consistency, supporting diverse trajectories and object interactions without additional training. Extensive experiments show that our method consistently outperforms prior work in overlap and trajectory accuracy, as well as visual quality across static, dynamic, and multi-object scene settings.
Oct 21, 2026

RealMe: Immersive Volumetric Video from Minimal Captures

This paper addresses the problem of creating immersive volumetric videos from sparse and low-resolution capture resources. Conventional dense multi-view reconstruction methods can produce high-quality volumetric videos, but their reliance on costly capture setups makes them impractical in real-world scenarios. Recent approaches use generative models to relax capture requirements, but still suffer from limited resolution and 4D inconsistency. To overcome these constraints, we propose RealMe, a unified framework built around a high-resolution video diffusion model that enhances limited captures into high-resolution (2K), 4D-consistent videos for volumetric video reconstruction. Specifically, RealMe constructs auxiliary data from capture videos and encodes them into latents along with layout-aware positional embeddings. The video diffusion model adapts factorized spatio-temporal attention to the multi-view capture layout, denoises these latents across viewpoints and time, and decodes them into enhanced videos to refine the 4D representation. This adaptation helps the model capture temporal dynamics and multi-view relationships, leading to more 4D-consistent generation. To reduce the data gap between generated videos and real captures, we apply a latent frequency loss that provides frequency-domain supervision in latent space. Extensive experiments on the public DNA-Rendering benchmark and our self-captured RealVV dataset demonstrate that RealMe is able to create immersive volumetric videos and outperforms state-of-the-art methods in visual fidelity and 4D consistency.
Oct 21, 2026

Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation

Autoregressive video diffusion models generate videos chunk by chunk, yet producing plausible continuations does not guarantee that they capture how scenes evolve. Under teacher forcing, strong temporal redundancy may allow local visual continuity to serve as a shortcut for current-chunk denoising, reducing the pressure to model visual evolution. We introduce Future Chunk Prediction (FCP), an auxiliary objective jointly optimized with teacher-forced denoising that predicts temporally separated chunks without access to the intervening visual context. Drawing supervision directly from training videos, FCP requires no additional pretrained visual encoder and leaves autoregressive inference unchanged. Our method achieves superior physical plausibility over standard teacher-forced autoregressive training with a lower overall training compute budget, highlighting the effectiveness and efficiency of future-chunk supervision for modeling visual evolution. Intriguingly, our visualizations suggest that FCP fosters a more structured representation space, which may be valuable for building autoregressive world models.
Oct 21, 2026

CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion

Diffusion-based video generation models (VGMs) can produce visually plausible videos, yet their camera ego-motion often drifts over long horizons. Camera ego-motion determines how the viewpoint changes between frames and is essential for maintaining consistent geometry and trajectories. To address this problem, we propose CausalAlign, a causal alignment framework with two components. First, we diagnose how precise ego motion is represented, used, and retained within VGMs using linear probes and causal interventions, revealing a rise-and-fall pattern during denoising. Second, we strengthen ego-motion state in VGM by aligning the representations at the identified layers to a 3D foundation model through delta-token space. This space encodes the changes between consecutive frames, allowing the alignment to focus on ego-motion dynamics rather than static scene content. With Wan2.2 fine-tuned on DL3DV and RealEstate10K, CausalAlign can largely improve motion accuracy, geometric consistency, and temporal smoothness, while preserving visual quality. For example, it improves geometric consistency by more than 20% relative to the base model. Moreover, with the fine-tuned VGM, CausalAlign improves the success rate of world action models (WAMs) by 10 points on mobile manipulation tasks of RoboCasa365 benchmark. Overall, CausalAlign improves ego-motion consistency in diffusion-based VGMs and yields noticeable gains in embodied models.
Oct 21, 2026

JointLight: Human-Centric Video Relighting with Asynchronous RGB-Irradiance Joint Modeling

Understanding and modeling light transport in human-centric scenes is a longstanding challenge. While recent progress in diffusion models has boosted research in relighting, precise illumination control still lags, primarily due to the scarcity of diverse, high-quality, precisely labeled video relighting datasets. Existing end-to-end relighting approaches model light transport implicitly through neural networks, which substantially complicates controllability. In contrast, some works resort to path-traced irradiance cues as an explicit blueprint for light transport. However, such constructed irradiance cues are prone to artifacts and hinder generative quality when directly used as control signals. With the key observation that noise corruption removes high-frequency artifacts and preserves low-frequency light transport, we introduce an asynchronous joint-modeling paradigm that facilitates fine-grained illumination control. During two-stage training, we force the model to jointly denoise RGB and ground-truth irradiance frames with separate timesteps scheduling. A domain matching strategy is applied to the second stage to bridge the domain gap between irradiance cues and ground-truth irradiance maps. At inference time, we introduce an asynchronous hijacked generation pipeline that facilitates flexible illumination control. For training data, we develop a multi-illumination high-quality synthetic video dataset with paired irradiance maps using a powerful game engine. Trained exclusively on this dataset, our model exhibits robust generalization to real- world scenarios and outperforms prior approaches in both lighting fidelity and generative quality. Project page: http://www.geometrylearning.com/JointLight/
Oct 21, 2026

Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers

Full 3D attention is costly in video Diffusion Transformers. Block-sparse attention reduces this cost by computing only selected attention blocks. However, existing methods either overlook the potential to optimize sparsity allocation or rely on heuristic rules or local metrics to guide it. In this work, we observe that sparsifying attention in different layers and at different denoising steps affects final-video fidelity to substantially different degrees. Yet the identities of the most sensitive layer-step pairs remain nearly unchanged across inputs. Building on these findings, we propose Allocating Layer-step Latency by Output Tests (ALLOT), a training-free sparsity allocation method. Treating each layer-step pair as a cell, ALLOT estimates each cell's contribution to final-video error through (i) cell probing and (ii) trajectory calibration, then jointly optimizes cell densities under a measured-latency budget. It preserves existing selection strategies and kernels, replacing only the allocation component. At equal or shorter wall-clock time, ALLOT outperforms every compared allocation strategy with XAttention, with an 11.8 dB PSNR gain on HunyuanVideo. Extensive experiments across four additional published pipelines on Wan2.1, Wan2.2, and HunyuanVideo show that ALLOT outperforms or ties the default in all nine settings.
Oct 21, 2026

NeuralSRender: G-Buffer Guided Video Diffusion for Sim-to-Real Rendering

The scarcity of high-quality annotated visual data remains a critical bottleneck for autonomous-driving perception. Simulators provide training data at scale, but the limited realism of synthetic videos compromises perception performance in real-world applications. To address this limitation, we propose NeuralSRender, a sim-to-real video translation framework that enhances the photorealism of synthetic videos while maintaining geometric consistency with the source scenes. Built on a pretrained video diffusion transformer (DiT), NeuralSRender uses a lightweight projector to inject geometric and material priors from G-buffers, and LoRA enables parameter-efficient adaptation. The model is trained in two stages: it first learns G-buffer conditioning from synthetic videos with accurate G-buffers, then adapts to real-world appearance using real videos with estimated G-buffers. During the second stage, an additional LoRA module is trained while the projector and first-stage LoRA remain frozen to reduce interference from estimation noise. NeuralSRender introduces only 1.45% parameter overhead and can be trained on consumer-grade GPUs with 24 GB of memory. To support training and evaluation, we introduce GenReal, a large-scale driving video dataset comprising synthetic and real-world videos with corresponding G-buffers. Experiments demonstrate improved photorealism with competitive geometric consistency. Training perception models on our translated videos instead of raw simulator renders improves detection AP50\mathrm{AP}_{50} on nuImages from 35.1 to 40.6 and segmentation mIoU on Cityscapes from 32.4 to 40.8. Our code, data, and model weights are available at: https://github.com/WHU-USI3DV/NeuralSRender.
Oct 20, 2026

SolarRenderer: Few-Step Generative Reference Rendering

Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the structure and completes the appearance it leaves open. Existing renderers are tied to the representation of one engine, need tens of denoising steps or a costly distillation of their own, and learn from conditions that are not aligned with their target videos. We present SolarRenderer, a structure-conditioned video renderer that adapts a frozen MiniMax-H3 33B backbone with two lightweight LoRAs. Structural videos enter the native reference pathway of the backbone at the positions of the frames they describe, without a type identifier and described only in plain text, so that a single control LoRA follows arbitrary structural representations. Starting from a pretrained four-step LoRA, structure-guided distribution matching renders in four steps, 12.3 times faster than 50-step sampling, while preserving the learned control. A block-causal variant extends the same design to streaming and renders 768p video in real time. To train the model, we build a frame-aligned corpus of 136K clips from game engines, simulators, and YouTube videos. Experiments on an in-distribution test set and a generalization benchmark of 16 structural representations show that SolarRenderer achieves state-of-the-art results across both, and generalizes to 11 unseen representations, including pose skeletons, drawings, and point clouds.
Oct 20, 2026

MoDDiT: Simple Token Routing in Diffusion Transformers

Real-time video generation, interactive world models, and on-device image synthesis are almost a reality. Diffusion Transformers (DiT) achieve excellent sample quality, shifting the bottleneck to the throughput of the models themselves. Natural images are inherently sparse, as large portions of an image are often background, contribute little to the scene content, and are easy to denoise. DiTs fail to exploit this sparsity, as they process image tokens statically and uniformly. We propose MoDDiT, a simple architecture modification that learns to route tokens through both MLP and self-attention operations. By routing tokens through both blocks independently, MoDDiT allows for dynamic compute allocation in MLPs that varies across tokens, images, and denoising timesteps. Using MoDDiT to train image generation models from scratch significantly reduces computational costs of training and inference, processing as few as 12.5% of the tokens. By increasing sparsity and model depth, MoDDiT reduces costs and improves generation performance over unrouted baselines. The learned allocation is interpretable, revealing how computation varies with visual content and noise level. We also use MoDDiT to train video generation models, where allocation correlates with motion, and to distill a dense bidirectional video model into a sparse autoregressive student.
Oct 20, 2026

Decoupling Action from Egocentric Observation for World Simulation

Egocentric action transfer aims to decouple the semantic action from egocentric observations and reproduce them in new visual contexts, enabling scalable world simulation, embodied policy learning, and robotic data generation. Existing approaches to transferring actions rely on condition-guided video generation, which converts the observation video into explicit geometric controls (e.g., hand poses or meshes) to drive synthesis. However, these methods introduce geometric estimation errors, making it difficult to preserve physically plausible interactions when transferred to new scenes. Alternatively, motion transfer methods directly extract motion patterns from the observation video, yet motion-level features alone cannot encode rich contact dynamics, frequently leading to severe hand structural collapse and implausible contact layout. To address both limitations, we present EgoACT, a test-time framework for egocentric action transfer that operates directly on the denoising process of video diffusion models without requiring additional geometric estimators. EgoACT uses Velocity-guided Structure Anchoring to stabilize reference-consistent hand-object structure in the early denoising stage, and Sparse Correspondence Calibration to refine reliable local correspondences in the mid-to-late denoising stages. Together, these two components preserve transferable action semantics while improving temporal coherence and interaction realism. We further establish EgoActionBench, a benchmark for evaluating action preservation, visual quality, and hand-object plausibility across diverse egocentric manipulation scenarios. Experiments show that EgoACT generates more coherent and physically plausible interaction videos than strong baselines.