Video Generation

Follow this topic Ask about this topic

Momentum

48 papers in the last four weeks, up 380% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 238

Aug 6, 2026cs.CV

UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on

Video Virtual Try-On (VVT) synthesizes a video of a person wearing a target garment while preserving identity, motion, and scene dynamics. Dominant approaches cast VVT as mask-conditioned video inpainting and rely on separate modules for human parsing, pose estimation, and garment warping. This multi-stage design complicates deployment and, more critically, allows errors in explicit geometric priors to propagate irreversibly into the generated video. We present UniVVT, a unified end-to-end framework that reframes VVT as semantically conditioned video generation, eliminating mask, pose, and warping modules at inference. At its core, a scene-task perceiver built on a Multimodal Large Language Model jointly encodes the source video, target garment, and task instruction into compact, task-aware latent tokens, implicitly capturing what to transfer and where and how to transfer it. A lightweight semantic bridge then aligns these tokens with the conditioning space of a diffusion-based video generator, enabling coherent garment transfer. To robustly couple the heterogeneous components, we devise a three-stage progressive training strategy comprising semantic alignment, joint task adaptation, and flexible-resolution refinement. Extensive experiments demonstrate that UniVVT achieves state-of-the-art performance across multiple benchmarks, validating implicit semantic guidance as a simple and effective alternative to fragile geometric preprocessing for end-to-end virtual try-on.

Yushe Cao, Shikun Feng, Fei Shen +5

Tsinghua University · Zhongguancun Academy · National University of Singapore +2

Virtual Try-On Garments Video Generation Geometric Priors

Aug 6, 2026cs.CV

VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing

Evaluating generated videos remains challenging because existing benchmarks rely on fixed evaluation content, cover only a subset of generation and editing settings, and provide limited evidence for their scores. We introduce VideoArgus, a unified rubric-grounded framework covering five video generation and editing settings. For each input instance, VideoArgus generates an output-blind, sample-specific rubric once and reuses it to evaluate all corresponding candidate videos. The rubric defines concrete criteria, scoring rules, failure modes, and evidence plans, which guide criterion-specific VLM QA and visual tools to produce evidence-grounded criterion scores, rationales, and a diagnostic report. We further construct VideoArgus-Bench, containing 1,026 curated input instances built from 653 high-quality images and 416 high-quality videos, with all benchmark rubrics pre-generated, frozen, and released. On a separate 1,260-video human-alignment set, VideoArgus achieves higher within-input Spearman and Kendall correlations with human judgments than the corresponding benchmark-specific evaluators across all five tasks. Model rankings also remain largely consistent across different rubric-generation and evaluation-VLM backbones. All code and data are released. Visit our project page: https://zzzmyyzeng.github.io/VideoArgus

Ziyun Zeng, Zixuan Wang, Yongsheng Yu +2

University of Rochester

Long Videos Video Generation Unified Framework Agentic

Aug 5, 2026cs.CV

muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road Hazards

High-quality driving data are essential for autonomous-driving systems and generative world models. However, rare and safety-critical scenarios involving adverse weather, braking under low tire--road friction, and uneven road geometry are costly and risky to collect at scale. Existing video-generation and 3D Gaussian editing methods can modify weather appearance or road geometry, but typically do not couple these edits with tire--road interaction and vehicle dynamics. As a result, an edited video may retain its original trajectory even when the modified road condition should alter braking, wheel slip, load transfer, and ego-camera motion. We present muSync-GS, a physics-synchronized framework for driving video synthesis under adverse-weather and road-elevation hazards. A precipitation-derived road-surface condition jointly controls road appearance and tire friction, while a shared road-elevation profile drives both visible road-geometry editing and axle excitation. A calibrated vehicle model predicts speed, slip ratio, normal loads, and pitch for constructing the ego-camera trajectory and synchronized physical annotations. On 12 held-out CarSim cases spanning precipitation levels, brake inputs, and road-profile parameters, the model achieves mean case-wise RMSEs of 0.0273 m/s for speed, 0.0590 degrees for pitch, 0.0101 for slip ratio, and 26.61 N for per-wheel normal load. Together with the reconstructed-scene experiments, these results show that muSync-GS accurately reproduces vehicle responses under held-out controls while synchronizing them with controllable scene edits and ego-camera motion.

Yang Chen, Yicheng Zhu, Tao Li +1

Rochester Institute of Technology · City University of Hong Kong

Dynamic Driving Scenes Vehicle Dynamics Road Networks Video Generation

Aug 4, 2026cs.CV

BRACE: Taming Sharp Irregularities via Barycentric Rational Forecasting for Fast Diffusion Transformers Inference

Diffusion Transformers (DiTs) have demonstrated exceptional performance in high-fidelity image and video generation. To alleviate their massive computational overhead, temporal feature caching has been proposed to bypass redundant computations. However, existing cache-then-forecast methods driven by derivative-based polynomials often cause severe quality degradation under high acceleration due to unstable long-step predictions. To address this bottleneck, we propose Barycentric Rational Forecasting with Chebyshev Enhancement (BRACE). Motivated by the observation that DiT feature trajectories are globally smooth yet frequently exhibit sharp irregularities and local non-smoothness, BRACE shifts the paradigm from derivative-driven polynomial extrapolation to feature-driven rational forecasting. Specifically, it maintains a local sliding window to cache sparse historical features and leverages adapted Chebyshev weights to formulate a barycentric rational function, directly aggregating these raw features to ensure numerical stability. Extensive experiments demonstrate that BRACE achieves state-of-the-art quality-efficiency trade-offs across various DiT architectures with negligible computational overhead.

Jinlong Yang, Jinke Wu, Lizilin +1

Sichuan University Chengdu, China · School of Artificial Intelligence, Sichuan University Chengdu, China

Diffusion Transformers Extrapolation Video Generation

Aug 4, 2026cs.CV

SUV: Future Scene Understanding as Video Generation for End-to-End Driving

End-to-end driving requires a coherent understanding of future scenes, yet existing methods model these scenes using task-specific heads and output formats, with limited scalability. Can video generation instead provide a shared predictor? We introduce SUV, a unified end-to-end driving framework that casts future Scene Understanding as Video generation using a pretrained video foundation model. SUV models future appearance, semantics, relative depth, and instance-level dynamics as video streams with a shared video expert, without stream-specific visual prediction heads. Through joint video-action attention, the action expert attends to the latent representations of all future streams and generates the ego trajectory. Experiments show that SUV directly predicts all four future streams, while controlled ablations show that structured future supervision and direct future-stream access yield higher trajectory planning scores. With only a single front camera and no candidate-trajectory selection, SUV outperforms a broad set of recent state-of-the-art methods on both NAVSIM-v2 splits, achieving 91.0 EPDMS on navtest and 36.9 on navhard. On the long-tail WOD-E2E benchmark, SUV achieves a competitive RFS of 7.94.

Yibo Yuan, Jiacheng Fu, Jiangtong Zhu +8

Xi’an Jiaotong University · University of Science and Technology of China · Yinwang Intelligent Technology Co., Ltd. +1

Video Generation Mechanics

Aug 3, 2026cs.CV

UniMoCa: Unifying Motion and Camera Controls as Visual Proxies for Faithful Human Video Generation

Controlling human motion and camera movement is essential for faithful human-oriented video generation, yet remains challenging in multi-person scenes with large body motions, occlusions, and dynamic cameras. Existing pipelines typically rely on visual motion sequences, such as skeleton maps, pose maps, or rendered body representations, for motion control, while using camera embeddings for camera control. Such heterogeneous control interfaces force video generation models to reconcile pixel-aligned visual cues with non-visual geometric embeddings, making motion-camera attribution difficult and sensitive to camera estimation errors. We propose \textbf{UniMoCa}, a representation-driven framework that unifies motion and camera controls in visual space. At the core of UniMoCa is \textbf{Motion-Camera Visual Proxy} (\textbf{MCVP}), a mutually-sharable novel representation that converts 3D human motion and camera trajectories extracted from driving videos into an identity-neutral visual proxy. MCVP renders temporally aligned human geometry under the recovered camera trajectory and augments it with explicit camera trajectory markers, replacing heterogeneous visual-parametric controls with distinguishable visual cues. As both control factors are represented in the same visual space, they become mutually compatible rather than heterogeneous, enabling consistent joint reasoning and editing during video generation. We further curate a \textbf{MCVP-Video} dataset covering complex actions, multi-person interactions, and diverse camera trajectories. Experiments based on the Wan2.2 I2V show that UniMoCa achieves substantial gains in human motion control, camera control, temporal consistency, and camera-aware robustness with minimal additional complexity. More details are shown in our Project page: https://tanliming-daniel.github.io/UniMoCa/.

Liming Tan, Ye Chen, Hao Zhang +3

Shanghai Jiao Tong University · Monash University · USC-SJTU Institute of Cultural and Creative Industry

Camera Control Human Motion Generation Camera-Conditioned Video Generation Video Generation

Aug 3, 2026cs.CV

CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation

Text-to-video (T2V) generation models have advanced rapidly, yet their ability to represent diverse cultural contexts remains underexplored. Existing benchmarks mainly focus on perceptual quality, physical plausibility, and text-video alignment, but do not directly assess whether generated videos capture culturally specific objects, actions, rituals, visible text, or audio cues. We introduce CultureVidBench, a comprehensive benchmark for evaluating cultural understanding in T2V generation. CultureVidBench contains 1,000 curated prompts covering 12 countries, 6 continents, 8 cultural regions, and 14 cultural aspects organized into three categories: material culture, social practice & performance, and ritual & ceremony. Designed specifically for video generation, CultureVidBench emphasizes dynamic and multimodal cultural representation, including social interactions, ritual procedure, and culturally appropriate visible text and audio. We evaluate seven representative T2V models through human user studies and MLLM-based automatic assessment across cultural faithfulness, multimodal cultural rendering, semantic adherence, and perceptual quality. Results show that although current models achieve strong semantic adherence and visual quality, they often fail to faithfully capture fine-grained cultural details, particularly for underrepresented regions, rituals, and multimodal cultural cues.

Xianjing Han, Yuhan Su, Yang Deng +3

Nanyang Technological University · Centrale Supélec · Singapore Management University +1

Text-To-Video Generation Model Cultural Awareness Long-Video Benchmarks Video Generation Perceptual Quality

Aug 1, 2026cs.CV

Diagnosing Under-Development of Irreversible Processes in Video Generation

Many physical attributes are \emph{irreversible}: ice melts but does not re-freeze, paper chars but does not un-burn. Do video generators respect this? We show the question is hard to measure, and that what can be measured reliably is \emph{development} rather than reversal. Metrics of local reversal are null-degenerate: a per-clip violation rate scores

0.50

on pure noise, and a variance-normalized reversal residual sits at its noise ceiling. What survives null-testing is a two-part protocol: progress (a directional attribute correlation) and a stasis rate. Under this protocol, generated video separates cleanly from real footage, and the gap is human-validated. Across seven text-to-video models, real reference footage advances (

ρ{=}{+}0.40

,

35\%

static) while every generator shows near-zero progress and

92

--

100\%

stasis; nine annotators rate real footage far above generated (

2.75

vs.\

0.99

on a

0

--

4

scale). The reliable finding is \emph{under-development}: generators barely advance irreversible attributes rather than reversing them. As a complementary mechanism, we show that post-hoc readout guidance is gameable, whereas enforcing monotonicity by construction in a disentangled attribute latent removes the gameable readout, validated in controlled and semi-synthetic settings.

Jian Xu, Yanning Wu, Delu Zeng +2

Video Generation Irreversibility Violation

Jul 30, 2026cs.CV

WaiT for the Signal: Simple Frequency-Aware Flow-Matching

As image generation models scale to ever higher resolutions, global coherence, local detail, and texture fidelity become critical axes for generation quality. However, standard flow matching treats all spatial frequencies uniformly, ignoring the natural frequency hierarchy where high-frequency bands become indistinguishable from pure noise far earlier than coarse structures. We introduce WaiT, a Wavelet-aware image Transformer that decomposes generation into coarse and fine bands via lossless wavelets. True to its name, the high-frequency bands wait for the signal: staying pure noise until coarse structure has emerged, then joining the flow for joint refinement. Since standard FID discards fine-grained detail through aggressive downsampling, we introduce a more stringent three-axis evaluation protocol to assess quality at native resolution. On ImageNet 512x512, WaiT achieves a pixel-space FID of 1.43 and is Pareto-optimal across all three axes, reducing sampling compute by up to 50%. With our largest 2B model, we set a new state-of-the-art FID of 1.3 for pixel-space models on ImageNet 512 resolution. Our formulation outperforms even the strongest latent-space models on texture fidelity, and scales seamlessly to high-resolution OpenImages and to video generation, achieving a state-of-the-art FVD of 0.84 on Kinetics-600 with no algorithmic modifications.

Krunoslav Lehman Pavasovic, Théophane Vallaeys, Stéphane Mallat +4

1FAIR, Meta · 2École Normale Supérieure, Paris · 3Sorbonne University, Paris

Multi-Reference Image Generation Contrastive Flow Matching Wavelets Fréchet Inception Distance Video Generation Texture

Jul 29, 2026cs.CV

FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring

Autoregressive video diffusion models enable real-time streaming video generation. However, errors introduced during self-rollout accumulate over long horizons, manifesting as color drift, motion stagnation, and eventual visual collapse. In this paper, we characterize this phenomenon from a frequency-domain perspective: error accumulation appears as a pronounced energy drift in the low-frequency bands. We further investigate the effectiveness of attention sink in the frequency domain, and find that it improves the video quality by alleviating the spectral energy drift to some extent, but cannot fully resolve it. Motivated by the above analysis, we propose FreqForcing, a training-free framework that addresses error accumulation in long-video generation via Spectral Self-Anchoring (SSA). The proposed SSA leverages the low-frequency components of anchor attention to maintain long-horizon visual stability, while preserving dynamic motion through the high-frequency components of local attention. Our FreqForcing extends Self-Forcing pretrained on 5s clips to two-minute generation, achieving 24x extrapolation. Extensive experiments show that FreqForcing outperforms existing training-free methods quantitatively and qualitatively while remaining competitive with representative training-based approaches.

Jiatong Li, Leo Liang, Linghe Kong +1

Shanghai Jiao Tong University · Tencent HY Team

Autoregressive Video Diffusion Models Autoregressive Video Generation Long Video Generation Video Generation Spectral

Jul 29, 2026cs.CV

CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling

Cinematic video generation is challenging for text-to-video diffusion models due to concurrent requirements on multi-shot generation, fine-grained controllability over characters and scenes, and long-form generation across extended temporal horizons. Existing methods rely on customization and retraining to separately address specific requirements, and cannot simultaneously fulfill all the requirements with a unified framework. In this paper, we shed light on the training-free paradigm with the key insight that the difficulty of multi-shot generation arises from a structural bias toward temporal continuity in pretrained video diffusion models, and consequently, propose a unified framework named CineWeaver to achieve reference-controllable multi-shot long-video generation without retraining. We manipulate positional encoding and attention patterns to break temporal continuity during inference to enable clear shot transitions using pretrained video diffusion models. Furthermore, we extend the proposed framework with a shot-routed reference conditioning mechanism for per-shot fine-grained controllability, and develop an anchor memory mechanism to allow long-form generation with consistent global appearance cues. To our best knowledge, CineWeaver is the first unified framework to simultaneously enable \textbf{long-form}, \textbf{reference-controllable}, and \textbf{multi-shot} video generation in a training-free fashion. Experimental results demonstrate that CineWeaver produces high-quality cinematic videos of long durations with consistent identities, stable global appearance, and clear shot transitions. The project page is available at: https://cineweaver.github.io.

Yuyang Huang, Yabo Chen, Wenrui Dai +6

Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China. · Institute of Artificial Intelligence (TeleAI), China Telecom, China. · Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.

Interactive Video Generation Text-To-Video Diffusion Models Long Video Generation Video Generation Sharp Transitions Films+1

Jul 28, 2026cs.CV

LumaGuide: Distribution Shaping for Training-Free HDR Generation in Diffusion Models

Pretrained diffusion models generate realistic images but are constrained by the statistical biases of their training data, limiting their ability to produce high dynamic range (HDR) content. In this work, we introduce LumaGuide, a training-free framework for distribution shaping in diffusion models. Instead of modifying model parameters, LumaGuide steers the sampling process to match target feature distributions via differentiable energy-based guidance. We instantiate this framework for HDR generation by controlling luminance distributions in perceptually uniform PQ space. Our results show that aligning luminance histograms is sufficient to induce HDR-consistent behavior, including coherent highlights and preserved shadow detail, while maintaining semantic fidelity. Beyond HDR, LumaGuide enables flexible specification of target distributions through data-driven presets, reference images, or text-driven predictors, and extends naturally to video generation with temporal consistency constraints. More broadly, our work demonstrates that controllable generation can be achieved by directly shaping output distributions at sampling time, without retraining diffusion models.

Bowen Chen, Shreshth Saini, Balu Adsumilli +1

The University of Texas at Austin · Google/YouTube · University of Colorado Boulder

Diffusion Models High Dynamic Range Video Generation Distributions Training-Free

Jul 28, 2026cs.CV

I2VShield: An Efficient Proactive Defense Framework against DiT-based Image-to-Video Models

The rapid advancement of video generation models has led to the increasing misuse of image-to-video (I2V) models. Although substantial progress has been made in detecting AI-generated videos, proactive defenses against I2V models remain underexplored. In particular, current proactive defenses against I2V models predominantly rely on gradient-based adversarial attacks, which require defenders to possess GPUs with substantial memory resources (VRAM) to generate adversarial examples. To address this issue, we propose I2VShield, a privacy protection method based on generative adversarial attacks tailored to Diffusion Transformer (DiT)-based I2V models. The proposed method primarily consists of two components: (1) a text-adaptive perturbation generation framework integrating adversarial learning to mitigate computational overhead while maintaining visual imperceptibility; and (2) an untargeted Multimodal Attention Disruption (MAD) attack that exploits the inherent vulnerabilities of DiT-based I2V models, maximizing the deviation of the internal attention features from their clean states. Extensive experiments demonstrate that our approach achieves highly competitive protection performance across various datasets and mainstream DiT-based I2V models, particularly in disrupting spatiotemporal coherence, while substantially reducing computational costs.

Yimao Guo, Zuomin Qu, Wei Lu

School of Computer Science and Engineering, Sun Yat-sen University Ministry of Education Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Guangzhou 510006, China · Guangdong Province Key Laboratory of Information Security Technology Guangzhou 510006, China · State Key Laboratory of HVDC, China Southern Power Grid Electric Power Research Institute

Diffusion Transformers Black-Box Adversarial Attacks Video Generation Cross-Modal Attention LLM Defense Mechanisms

Jul 27, 2026cs.CV

FilmBench: A Film-Grade Benchmark for Cinematic Video Generation

Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM templates and score them with untrained, generic multimodal models. More fundamentally, their evaluation taxonomies remain rudimentary (overall visual quality, coarse text alignment and temporal smoothness) rather than the professional Cinematic Language criteria by which films are actually made and judged, so they assess basic video plausibility rather than film-grade craft. We introduce FilmBench, a text-to-video (T2V) and reference-to-video (R2V) benchmark grounded in the professional Cinematic Language of the film- academy tradition and co-developed with directors and faculty from the Beijing Film Academy and the Hujing Digital Media & Entertainment Group film studio. It rests on three choices. First, prompts are reverse-engineered from clips of award-winning films spanning 20 cinematic genres and chosen by professional directors, so every prompt is anchored to a verified live-action reference; the prompts follow real shot lists, and most script multiple shots (1,056 of the 1,169 prompts are multi-shot), unlike prior single-clip benchmarks. Second, evaluation follows a three-level Cinematic taxonomy of 3 axes, 12 components and 35 (T2V) +3 (R2V-only) sub-metrics. Third, we develop an in-house expert-grade automatic evaluation agent and open-source its core suite of Cinematic Language operators (FilmOps). Benchmarking leading video generation models (9 for T2V, 7 for R2V), the evaluator reproduces the human model ranking at model-level Spearman \r{ho} = 0.95 (T2V) and 0.96 (R2V). Scores fall well below prior web-style benchmarks, with two consistent gaps in dynamic aesthetics and a marked single- to multi-shot performance drop that widens for weaker models.

Shengyi Wang, Niantong Li, Guangzheng Hu +27

Alibaba Group · Moku Lab, Hujing Digital Media & Entertainment Group · Beijing Film Academy

Cinematic Ideal Long-Video Benchmarks Video Generation

Jul 27, 2026cs.CV

Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification

Diffusion transformers are essential for high-fidelity video generation, but long token sequences make attention a dominant inference bottleneck. Training-free dynamic sparse attention alleviates this bottleneck by computing only selected key-value blocks, yet existing methods struggle to sparsify attention both efficiently and accurately for two reasons: (1) Rigid, unpredictable, and costly routing: selecting a fixed fraction of top-ranked blocks by proxy score imposes fixed budgets, whereas retaining blocks to reach a target cumulative proxy probability mass yields dynamic but potentially imbalanced budgets; both incur non-negligible overhead from computing and materializing proxy scores. (2) Lossy keep-or-drop sparsification: unselected blocks are discarded entirely, degrading accuracy under aggressive sparsity. These limitations motivate cheaper dynamic-budget routing while limiting accuracy degradation. In this paper, we introduce training-free Sol-Attn (Sparsifying online attention), which unifies dynamic routing, sparse computation, and approximation correction in a single online-softmax pass, achieving a better accuracy-efficiency trade-off in sparse attention. The core of Sol-Attn is on-the-fly block thresholding with proxy-score reuse, which selects critical blocks by comparing block proxy scores against a threshold during online softmax. This design enables dynamic yet controllable block budgets without materializing the proxy map, while directly reusing the proxy scores of unselected blocks to approximate their contribution. Experiments across image and video generation tasks show that Sol-Attn advances the quality-efficiency frontier of training-free sparse attention, delivering 2.1 times and 2.3 times end-to-end speedups for video generation and editing, respectively, while preserving visual quality.

Haopeng Li, Yitong Li, Junsong Chen +8

NVIDIA

Dynamic Sparse Attention Long Video Generation Video Generation Sparsity Token Budget Allocation

Jul 27, 2026cs.CV

AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars

Production-ready audio-driven avatar generation requires efficient inference without sacrificing fidelity or motion expressiveness. However, existing acceleration methods often compromise quality through restrictive architectural choices, such as causal attention and short temporal horizons, or by reducing model capacity and resolution. Without such compromises, we propose AptAvatar, a 14B-parameter long-form audio-driven avatar generation framework that delivers fast and expressive inference. For efficiency in production-level applications, AptAvatar addresses the extreme two-step generation challenge. To bridge the gap between the multi-step teacher model and the two-step student model, we introduce Endpoint-Anchored Distribution Distillation. It augments vanilla distribution matching with a dedicated Anchor Score Estimator trained on the trajectory-endpoint distribution defined from a frozen pretrained 4-step bridge generator. This provides an attainable endpoint-level anchor for the evolving two-step student. To improve long-horizon consistency, we further introduce Self-Generated History Replay, which reuses cached outputs from earlier generator checkpoints as history conditions during chunk-wise training. This approximates inference-time conditioning on self-generated histories without costly online rollouts, mitigating quality degradation from accumulated history errors. Extensive experiments demonstrate that AptAvatar generates vivid 720p long-form avatar videos with only 2 NFEs, achieving a 60x speedup while preserving visual fidelity and long-horizon identity. Code is available at https://github.com/TaoLiveAIGC/AptAvatar

Hengyuan Zhang, Jingna Sun, Meiguang Jin +1

Alibaba Group, Taobao and Tmall Group

Audio-Video Generation Video Generation Avatars Few-Step Generation

Jul 24, 2026cs.CV

AgentHOI: Multi-Agent Reasoning for Human-Object-Interaction Video Generation via Implicit Representation Alignment

Recent advances in video diffusion models have spurred interest in human-object interaction (HOI) video generation, which demands fine-grained control over interaction logic beyond single-subject animation. However, existing HOI methods rely heavily on explicit motion control, limiting scalability and generalization across diverse objects and interactions. In this study, we propose AgentHOI, a text-driven HOI video generation following a thinking-before-generation framework that bridges the gap between high-level textual intent and physical execution through multi-agent reasoning over perception, interaction, and motion planning. Building upon the generated interaction plans, we further strengthen text-driven motion understanding. We introduce an implicit text-motion alignment strategy that distills text-to-motion priors into the video diffusion model, enabling robust HOI synthesis without explicit motion inputs at inference. Experiments show that AgentHOI significantly improves interaction naturalness, object appearance preservation, and adherence to complex textual instructions across challenging object-centric scenarios such as wearing and riding. The code is available at https://github.com/bone-11/agenthoi.

Ziyao Huang, Shunkai Li, Juan Cao +7

University of Chinese Academy of Sciences · Tencent HunYuan

Articulated Objects Human Motion Generation Video Generation Video Diffusion Models Multi-Agent Reasoning Value Alignment

Jul 21, 2026cs.CV

Learning Explicit Physical Parameter Control and Benchmarking for Video Generation

Recent advances in image-to-video generation have improved visual realism, making physically grounded and controllable dynamics an important step toward future world simulation. Current models often generate plausible motion, but it is not reliably governed by explicit physical causes, and instance-level constraints can leak or become entangled in multi-object interactions. We attribute this gap to two missing pieces: large-scale, fine-grained physical parameterization, and model designs that correctly bind physical attributes to instances and emphasize dynamics over appearance. To bridge this gap, we introduce PhyParam-Dataset, an interaction-centric collection of 130K physically simulated videos with dense physical parameterization, including force vectors, object material properties, and environmental constants across five representative rigid-body motion types. Built on this data, we present PhyParam, a physics-guided image-to-video diffusion model that conditions on object-level forces, masses, friction, restitution, and scene-level gravity via a lightweight physical-attention routing mechanism, and further improves motion learning with semantic-structural feature-space supervision. We also establish PhyParam-Bench, a benchmark for physical-law consistency in image-to-video generation, with a multi-level protocol evaluating temporal dynamics, spatial stability, and semantic--physical alignment. Experiments show that PhyParam improves physical consistency while maintaining high visual fidelity, advancing explicit rigid-body physical-parameter control for image-to-video generation. We will publicly release the dataset, benchmark, and code to support future research.

Yanxun Li, Hao Wen, Bingze Song +7

State Key Laboratory of Virtual Reality Technology and Systems, SCSE, Beihang University · AMAP, Alibaba Group

Video Generation Human Motion Generation Rigid-Body Dynamics Gravity

Jul 21, 2026cs.CV

DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking

Video generation models achieve high visual quality but often struggle to generate physics-aware videos. Unlike rigid-body motion, which can be described by explicit trajectories or formulas, complex deformation dynamics remain challenging to synthesize. We observe that a lack of physical reasoning for localizing dynamic areas allows irrelevant regions to dilute the model's attention, leading to generation failure. In this paper, we propose DeforM, a reasoning-guided image-to-video generation framework that directs the model's focus toward physics-critical regions. To reason about and localize these critical regions, we introduce a VLM-guided physical reasoning module, DeforM-Reason, to identify target objects and generate spatial-temporal masks. For physical guidance, we develop two alternative strategies: DeforM-Free for training-free mechanism analysis and DeforM-Injection as a powerful training-based generator. Experimental results demonstrate that DeforM improves the realism of generated deformation scenarios, outperforming baseline models in both visual quality and physical consistency.

Yunyi Li, Yu Qiao, Yaohui Wang +1

Shanghai Artificial Intelligence Laboratory, Shanghai, China

Generative Video Models Video Generation Human Motion Generation Deformable Physics-Aware Models

Jul 20, 2026cs.CV

Keyframe-Anchored Identity Preservation for Sequential-Action Video Generation

Identity-preserving text-to-video generation aims to synthesize a video that accurately follows a textual description while maintaining the recognizability of a user-specified subject throughout. The IPVG26 challenge extends this framework from a single holistic prompt to a temporally structured specification. The model additionally receives a sequence of timestamped action captions and must render the subject performing these actions in the specified order. This temporal structure presents a challenge not encountered in previous identity-preserving generation tasks, as the subject must continuously perform a scripted sequence of distinct actions while maintaining a consistent identity. However, end-to-end video generators are prone to appearance drift as motion accumulates and the depicted actions change. We address this challenge with a training-free, three-stage pipeline framework. An action-aware prompt polishment stage first rewrites the inputs into image-generation prompts that specify the terminal state of each action. An identity-preserving generation stage then produces the keyframe sequence by conditioning each frame jointly on the reference identity and its predecessor, thereby decoupling time-invariant appearance from time-varying pose. Finally, an identity-aware inference enhancement stage synthesizes the intermediate segments using multi-reference guidance and identity-driven noise searching, both of which reinforce identity fidelity during sampling. Our method ranked third on the official Track 2 leaderboard, demonstrating competitive performance and strong generality.

Zhenjie Liu, Binyan Chen, Hao Chen +2

University of Science and Technology of China Hefei, China

Video Generation Keyframe Selection Appearance

Jul 20, 2026cs.CV

Thinking in Video: Can Video Generators Really Reason About the Real World?

Recent advances in world models and video generation have given rise to an emerging reasoning paradigm that leverages video generative models to simulate, predict, and reason about real-world dynamics. We redefine this paradigm as Thinking in Video, where video is not merely an output artifact but a medium for constructing, extending, and verifying causal thought. However, this promise remains unverified: convincing rollouts may reflect memorized appearances rather than causal understanding, while existing metrics separate perceptual fidelity from semantic logic. To evaluate whether video generators support such reasoning, we introduce the Causal-Generative Dual-Judge (CGDJ), auditing World Model Consistency from two perspectives. Explicit Causal Perception tests whether a generator reads a video scenario as a reasoning problem through spatio-temporal flattened visual question answering, while Implicit Generative Perception-Prediction Gap evaluates whether it renders the causal consequence as a consistent future video. Applying CGDJ to representative open- and closed-source generators reveals a clear Perception-Prediction Gap: open-source models produce plausible dynamics despite near-zero explicit causal perception, whereas advanced closed-source systems show stronger but still limited alignment between reasoning and generation. Further analysis exposes audio-visual misalignment, where models verbalize correct causal logic more reliably than they render it, challenging the "world simulator" narrative.

Yongheng Zhang, Guang Yang, Ruihan Hou +12

Central South University · Tencent · Tsinghua University

Generative Video Models Video Generation Reasoning Skills Real-World

Jul 19, 2026cs.CV

The generator is the tracker: Multi-object tracking by painting persistent identity colours

Multi-object tracking (MOT) is conventionally decomposed into detection followed by association, with object identity maintained as external state: track buffers, motion models, and appearance embeddings. We ask whether a video generator can maintain that state in pixels. We fine-tune a 22B text-to-video diffusion model (LTX-2.3) with a lightweight in-context LoRA to translate an RGB clip into an ID-map clip, a video in which every person is painted a flat, distinct color that persists over time: same color, same identity. Long videos are generated as chained windows, where each window is conditioned on the cleaned tail of the previous one. A brief continuation fine-tune teaches the model to extend a given coloring, after which identity flows through the chain with no tracker, no motion model, and no re-identification module. On the DanceTrack test server, our system, to our knowledge the first generative tracker evaluated there and the only entry with no detector and no tracking stack, reaches 40.3 HOTA. This is well below today's specialist state of the art (>=70 HOTA), but with a unique, inverted error profile: its association score (AssA 44.1) exceeds every tracker of the original benchmark suite while detection remains the sole deficit. Controlled comparisons show the mechanism matters: the same generated windows linked by classical post-hoc association score 2x worse (18.2 HOTA), and frame-to-frame IoU association fragments tracks that the generator's colors keep whole. On 383 mined occlusion events, the generator re-acquires identities after gaps at a 42% conditional rate where appearance-embedding baselines score zero, including gaps longer than its temporal context, evidence that the generator's color assignment functions as an emergent re-identification signal. We release code, checkpoints, and the full pre-registered experimental log.

Haiyu Yang, Miel Hostens

Cornell University

Re-Identification Video Generation Generators

Jul 17, 2026cs.CV

PE-Field 4D: Video Generation Models as Canvas

Diffusion Transformers have recently achieved strong performance in video generation, yet controlling scene geometry under viewpoint changes and camera motion remains challenging. In this work, we revisit the role of positional encoding in video diffusion transformers and show that it provides a useful spatial bias for geometry-aware control. Specifically, if reference tokens are encoded according to their projected locations in the target view, the denoising model is encouraged to retrieve content from position aligned regions of the input video. Building on this observation, we introduce a geometry-aware cross-attention mechanism that enables target video latent tokens to attend to structured context tokens derived from reference images or frames. To establish correspondence between the reference content and the target camera trajectory, we equip the context tokens with a projected positional encoding scheme that combines target-view 2D reprojection with depth-aware disambiguation. At the same time, we preserve the original spatiotemporal positional encoding of the generated video latent, allowing geometric guidance to be injected while maintaining consistency with the video model's native latent structure. The resulting framework provides a simple and effective approach for controllable video generation. It improves spatial controllability in viewpoint-dependent editing tasks, including camera re-trajectory, novel-view video synthesis, and geometry-aware video editing, while preserving the generative prior of the underlying video diffusion model. The code is available at: https://github.com/MTLab/PE-Field.

Yunpeng Bai, Haoxiang Li, Qixing Huang

University of Texas at Austin, USA · Pixocial Technology, USA

Video Generation Camera Trajectories Positional Encoding 4D

Jul 16, 2026cs.CV

PhysPlan: Grounded Physical State Reasoning and Graph-Guided Optimization for Physically Plausible Video Generation

Video diffusion models (VDMs) synthesize photorealistic content, yet they often fail to follow the course that a physical phenomenon should take within a given scene. Recent training-free methods let a vision-language model (VLM) plan the phenomenon and guide a frozen VDM toward the plan; however, such plans are derived from the prompt and consumed as whole keyframes or trajectories, which leaves unspecified where the consequences land in the observed scene and turns incidental visual details into optimization targets. We observe that a phenomenon specified in words unfolds as sparse, local changes to the physical state of the observed scene. Building on this observation, we present PhysPlan, a training-free image-to-video framework that represents a phenomenon as a grounded state graph and uses this graph to decide what, where, and when the guidance constrains. Grounded Physical State Reasoning decomposes the phenomenon into physical deltas, each stating which objects change, to what state, and by which physical rule, and translates each delta into graph edits, verified by deterministic checks, that leave all other objects unchanged. Graph-Guided Test-Time Optimization renders a keyframe for each state, measures the denoised estimates only along the properties selected by the edits, and concentrates the update on the edited objects. On PhyGenBench and Physics-IQ, PhysPlan raises its base model from 0.52 to 0.77 and from 27.1 to 38.2, surpassing the strongest prior I2V method (0.60 and 34.6), and lowers FVD by over 20%. Project page: https://physplan.github.io

Minh-Loi Nguyen, Xuan-Vu Le, Trung-Nghia Le +3

University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam · University of Dayton, Dayton, Ohio, US +1

Video Generation

Jul 16, 2026cs.CV

MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation

Large-scale video diffusion models (VDMs) deliver strong generation performance, but full fine-tuning for downstream tasks incurs prohibitive computational costs. Existing parameter-efficient fine-tuning (PEFT) methods have two critical flaws on billion-scale models: they still require substantial trainable parameters, and reward-based training suffers from noise-induced optimization instability in condition-guided tasks. We propose MagicPrompt, a lightweight framework that achieves extreme parameter efficiency and stable reward optimization. It first adopts Attention-Embedded Prompt Tuning, which steers generation via lightweight soft prompts with orders of magnitude fewer parameters while preserving pre-trained knowledge. It further introduces Dual-Space Reward Feedback Optimization, which uses self-supervised latent objectives to improve condition-guided reward training. Experiments show MagicPrompt reaches competitive performance with less than 1% trainable parameters and notably reduces training costs.

Yinhan Zhang, Dinwei Tan, Xianghao Kong +3

HKUST · Tencent · HKUST(GZ)

Video Diffusion Models Video Generation Soft Prompt Tuning Prompt Engineering

Jul 15, 2026cs.CV

VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation

Recent video generation models (VGMs) have made substantial progress in visual fidelity, yet their ability to follow long, compositional instructions remains insufficiently evaluated. Existing evaluation protocols often rely on prompts that are short and semantically shallow, with limited atomic constraints and weak spatio-temporal dependencies. They also frequently depend on costly human evaluation or handcrafted vision pipelines, while providing little diagnostic insight into which instruction constraints succeed or fail. To address this gap, we propose VGIF-Score, a highly automated and interpretable framework for evaluating instruction following in video generation. VGIF-Score consists of two complementary components: an objective completion branch that parses prompts into a Spatio-Temporal Directed Acyclic Graph (ST-DAG) and performs dependency-aware QA with short-circuit diagnostics, and a subjective satisfaction branch that uses instruction-conditioned AutoRubric to assess cinematography, visual purity, motion smoothness, and physics adherence. Together, these components produce a unified score that captures both objective completion and perceptual satisfaction. We instantiate this framework on VGIF-Bench, a benchmark of 223 long, structurally entangled prompts paired with approximately 4.3K fine-grained evaluation items. Experiments on 14 proprietary and open-source VGMs across more than 3K generated videos show that VGIF-Score provides reliable, interpretable, and diagnostically useful evaluation of video generation instruction following. The code will be available at https://github.com/PRIS-CV/VGIF-SCORE.

Songyu Xu, Xin Wang, Qiang Chen +6

Beijing University of Posts and Telecommunications, Beijing, China · China Telecommunications Group Co., Ltd., Beijing, China

Video Generation Visual Fidelity Instruction Completion Temporal Dependence

Jul 15, 2026cs.CV

Bring Music The Horizon: Music-Driven 360 $^\circ$ Video Generation

Music visualization offers a powerful way to enhance listeners' understanding and experience of music by translating auditory signals into visual forms. However, most existing approaches either rely heavily on lyrics or generate flat, non-immersive videos similar to conventional music videos, which limits their ability to convey the emotional dynamics of music and provide an immersive listening experience. We propose Bring Music The Horizon, an emotion-aware pipeline for music-driven 360

^\circ

video generation. Given an input song, our work first estimates its emotional trajectory by predicting valence-arousal values at the level of every four bars. These values are then converted into emotion-aware visual guidance using EmotiCrafter, and these guidance vectors can be manipulated by the SEGA framework, which provides fine-grained semantic control for keyframe generation. Finally, image-to-video models are applied to the generated keyframes to synthesize temporally continuous 360

^\circ

videos for immersive music visualization. Our pipeline generates 360

^\circ

music visualization videos that reflect the emotional progression and temporal structure of the input song. We demonstrate its capability using songs from different genres and provide qualitative comparisons with From-Sound-To-Sight, a representative audio-to-visual generation baseline, on our project page at https://etoile-et-toi-mp3.github.io/BMTH_Project_Page/.

Kai Hsu Tsai, Yong Wei Fu, Hung I Yang +1

Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan

Dance-To-Music Generation Audio-Video Generation Video Generation Long Videos Horizon

Jul 14, 2026cs.CL

Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation

Sign language is a primary communication channel for millions of Deaf and hard-of-hearing people, yet text-to-signer video generation remains costly because video diffusion models are expensive to train and evaluate. This paper presents Text2Sign, a text-conditioned diffusion model for short sign-language clips that runs on a single NVIDIA L4 GPU. It combines a frozen vision-language text encoder with a 3D encoder-decoder and factorized spatiotemporal attention to reduce the cost of full-video attention while preserving motion coherence. We compare convolution-only and transformer-style backbones, frozen pretrained and task-specific text encoders, and factorized versus full attention. On a signer-disjoint How2Sign split, the best short-run ablation reaches a validation loss of 0.0648, while a longer-run checkpoint reaches 0.00999. On a compact evaluation slice, the latter achieves an SSIM of

0.2403 \pm 0.0238

, a PSNR of

15.11 \pm 0.42

dB, and temporal consistency of

1.0000 \pm 0.0000

using 8-step DDIM sampling with a guidance scale of 5.0. It generates a 32-frame,

64 \times 64

clip in 12.60 seconds, or 2.54 frames per second, with peak inference memory of 3.12 GB. A held-out denoising audit shows only weak prompt sensitivity: removing text increases late-timestep loss from 0.9875 to 0.9891, while shuffled prompts perform similarly to correct prompts. Frozen text conditioning therefore improves short-budget validation loss, but prompt-specific separation remains limited. The system is restricted to low-resolution, short clips and lacks expert linguistic evaluation, so it should be viewed as a single-GPU research baseline rather than a complete sign-language production system. Code is available at https://github.com/xiaruize0911/text2sign.

Ruize Xia

Independent Researcher

Sign Language Translation Online Signature Verification Video Generation Text-Conditioned Diffusion Model Diffusion Models Frozen Vision-Language Models

Jul 13, 2026cs.CV

Controlling Motion Transfer in Diffusion Transformers via Attention Heads

Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results. However, extending them to motion transfer, which requires following reference motion while aligning with a target prompt, remains challenging due to limited understanding of motion and structure representations within DiTs. We analyze video DiTs at the attention-head level and identify distinct heads specialized for motion and spatial structure. Based on this insight, we propose a head-aware controllable motion transfer framework that requires no parameter updates. Our method refines motion cues from motion-specialized heads via semantic correspondence guidance and preserves structure through selective feature injection. This head-level control not only enables accurate motion transfer but also provides an interpretable foundation for controllable video generation with DiTs.

Sunyoung Jung, Jiwoo Park, Yoonseok Choi +3

Yonsei University · LG Electronics · University of California, Merced

Diffusion Transformers Video Generation Transformer Architectures Motion

Jul 12, 2026cs.CV

AU-Guided Synthetic Video Generation for Micro-Expression Recognition

Micro-expression recognition is limited by the small scale, narrow demographic coverage, and restricted emotion labels of existing datasets. We introduce EquiME, a synthetic micro-expression dataset built from AU-guided image-to-video generation. EquiME contains 75K videos generated from 15K source face images across five target emotions, together with automatically inferred demographic metadata and video-quality measurements. We evaluate EquiME using frame-pair similarity, spatial variation, and no-reference perceptual-quality metrics, together with cross-dataset MER experiments on SAMM and CASME II. Models trained on EquiME achieve competitive cross-dataset performance on SAMM and CASME II and show comparatively low variation across the four evaluated architectures. This paper focuses on the dataset design, the structured AU-conditioning pipeline used for video generation, and the empirical evidence needed to assess EquiME as a synthetic MER resource. Project page: https://kirito-blade.github.io/me-vlm/

Pei-Sze Tan, Sailaja Rajanala, Yee-Fan Tan +2

CyPhi AI Lab, Monash University Malaysia

Video Dataset Video Generation Automatic Identification System Perceptual Quality Demographics

Jul 10, 2026cs.RO

GenVid2Robot: From Video Generation to Robot Manipulation via Rigid-Geometric Consistency

Generated videos provide useful visual motion priors for robot manipulation, but their visual plausibility does not imply physical executability. A generated video usually lacks metric geometry, grasp grounding, robot kinematic feasibility, and execution-time feedback, which makes direct trajectory replay unreliable in real-world manipulation. This paper presents GenVid2Robot, a rigid-geometric consistency framework that converts generated video motion into executable real-robot manipulation trajectories. Given an initial RGB-D observation and a task instruction, GenVid2Robot samples task-relevant semantic anchors from the real first frame, tracks these anchors through generated video candidates, and verifies whether the resulting 2D motion can be explained by first-frame RGB-D anchors under a sparse relative

SE(3)

model. In this way, generated videos are treated as uncertain visual motion hypotheses rather than direct robot demonstrations. Only geometrically consistent motion is transferred to the robot. The accepted relative motion is then applied to the real grasp-time TCP pose selected by mask-constrained grasping, producing a grasp-conditioned execution trajectory that is consistent with both the visual motion prior and the physical grasp configuration. To reduce execution mismatch caused by RGB-D noise, calibration residuals, and small contact-induced displacement, a bounded depth-compensation module corrects local depth-direction errors without assuming full online replanning. Real-robot experiments demonstrate that GenVid2Robot improves the reliability of generated-video-guided manipulation by grounding visual motion priors with sparse metric geometry, grasp constraints, robot feasibility checking, and bounded execution feedback.

Haohui Huang, Xi Yuan, Panpan Liao +4

School of Automation, Guangdong University of Technology, Guangzhou, China · University of Liverpool, Liverpool, U.K. · Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China +1

Robotic Manipulation Camera-Conditioned Video Generation Video Generation Rgb-Depth Cameras

Jul 10, 2026cs.CV

Video Generation Models are General-Purpose Vision Learners

Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models. What, then, is the equivalent catalyst needed to achieve a general-purpose model in computer vision? In this paper, we contend that large-scale text-to-video generation serves as a strong pre-training paradigm for computer vision, providing the necessary spatiotemporal priors, vision-language alignment, and scalability required for general visual intelligence. We introduce GenCeption, which leverages a pre-trained video generative diffusion backbone to define a feed-forward perception model, capable of performing various vision tasks steered by text instructions. Empirical results demonstrate that GenCeption achieves state-of-the-art performance across a diverse suite of tasks, including depth, surface normal, and camera pose estimation, expression-referring segmentation, and 3D keypoint prediction, often matching or surpassing specialized models (e.g. DepthAnything3, SAM3, D4RT, VGGT-Omega, Sapiens, David, Genmo, and Lotus-2). Furthermore, the video generative pretrained backbone outperforms alternative pretraining paradigms (e.g., V-JEPA, and Video MAE) under comparable settings. Importantly, GenCeption exhibits preliminary data and model scaling properties along with exceptional data efficiency, where it achieves comparable performance with leading models like D4RT and VGGT-Omega with 7 to 500 less training data. Finally, GenCeption also exhibits intriguing emergent behaviors: a model trained exclusively on synthetic human videos generalizes to real-world footage and out-of-distribution object categories (e.g., animals and robots). These findings suggest that video generation is not merely a synthesis tool, but a foundational path toward generalist vision intelligence for the physical world. Project page: https://genception.github.io

Letian Wang, Chuhan Zhang, Rishabh Kabra +9

Google DeepMind · University of Toronto · University College London +3

Generative Video Models Video Generation Pretraining Feed-Forward

Jul 9, 2026cs.CV

OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce long videos with low latency, but still suffer from error accumulation and weakened motion dynamics during long autoregressive rollout. OPSD-V reduces long-horizon degradation while preserving the original few-step inference path. The key idea is to introduce real long-video data as temporal context during training and use it to provide dense trajectory-level supervision. Specifically, the student follows the exact inference-time rollout, generating each chunk conditioned on its own previously generated KV cache. In parallel, the teacher is evaluated at the same student-visited denoising states, but uses a cleaner AR-consistent temporal cache in which older history can be replaced by real-video context. This provides dense denoising-level corrective targets under on-policy AR cache dynamics, without changing the sampler, number of denoising steps, or inference-time cache mechanism. We apply OPSD-V to representative few-step AR video models, including Self-Forcing and LongLive. Experiments show consistent improvements in visual quality, motion dynamics, and VBenchLong scores. A user study with 10 participants comparing 20 video pairs shows that OPSD-V is preferred over the base models in 66.0% of overall-preference judgments (82.5% excluding ties).

Hongyu Liu, Chun Wang, Feng Gao +6

Meituan · HKUST · City University of Hong Kong

Autoregressive Video Diffusion Models Autoregressive Video Generation Video Diffusion Models Video Generation Autoregressive Rollout

Jul 9, 2026cs.CV

OpenCoF: Learning to Reason Through Video Generation

Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reasoning path distinct from previous Chain-of-Thought (CoT): reasoning can unfold through temporally connected frames, known as Chain-of-Frame (CoF) reasoning. However, existing video generators are primarily trained on general video corpora, still lacking diverse supervision and dedicated designs for CoF reasoning. To address this gap, we introduce OpenCoF, a framework comprising the OpenCoF-17K dataset, a reasoning video dataset spanning 11 task families, and Wan-CoF, a fine-tuned video model for studying whether diverse temporal supervision improves CoF behavior. Across four video reasoning benchmarks, Wan-CoF achieves considerable gains over the Wan2.2-I2V-A14B baseline. Building on this, we empirically explore more advanced designs for CoF capabilities, i.e., equipping the model with visual and textual reasoning tokens. This mechanism respectively captures low-level visual cues and high-level semantic priors for spatial and temporal reasoning. Through performance comparisons and attention analysis, we examine how these tokens contribute across model depth, denoising steps, space, and time. Our results suggest that stronger video reasoning requires both broad temporal supervision and explicit mechanisms for organizing intermediate reasoning state. We open-source the dataset, model, and code to facilitate future research on reasoning-oriented video generation.

Xinyan Chen, Ziyu Guo, Renrui Zhang +2

ByteDance Seed · CUHK IMIXR · CUHK MMLab

Video Generation Video Understanding Video Dataset Reasoning Skills Chain-of-Thought Reasoning

Jul 9, 2026cs.CV

SAGA: Stable Acceleration Guidance for Autoregressive Video Generation

Autoregressive video diffusion enables efficient streaming and long-horizon video generation, but repeatedly reusing generated latents as causal context can amplify temporal errors, resulting in flickering, motion jitter, and structural drift. In this paper, we investigate this failure mode from a spectral kinematic perspective and identify discrete latent acceleration as an effective signal for revealing unstable high-frequency temporal perturbations. To this end, we propose SAGA, a training-free \textbf{\textit{s}}table \textbf{\textit{a}}cceleration \textbf{\textit{g}}uidance approach for \textbf{\textit{a}}utoregressive video generation. SAGA integrates an acceleration domain spectral guidance objective based on finite-window Slepian projections with a structured autoregressive noise initialization strategy that suppresses short-range temporal correlations while preserving long-range motion structure. Without retraining or modifying the backbone, SAGA can be directly applied to existing chunk-wise autoregressive diffusion models, which is the prevalent setting for high-quality generation. Extensive experiments show that SAGA consistently improves temporal quality across multiple autoregressive diffusion models. On Self-Forcing, SAGA improves Temporal Quality from 97.30 to 97.91 and Image Quality from 69.60 to 70.51. Moreover, spectral analysis and human preference studies demonstrate that SAGA reduces temporal instability while maintaining visual fidelity.

Thanh-Nhan Vo, Trong-Thuan Nguyen, Trung-Hoang Le +2

University of Science, VNU-HCM, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam · University of Dayton, U.S.A.

Autoregressive Video Diffusion Models Autoregressive Video Generation Video Generation Geometric Guidance Acceleration

Jul 7, 2026cs.CV

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 Models Video Generation Video Captioning

Jul 7, 2026cs.AI

A Definition and Roadmap for World Models

World models -- internal simulators that learn the structure and dynamics of an environment -- have become one of the most actively debated concepts in AI. From model-based reinforcement learning and video generation to embodied robotics and ultimately, physical AI, researchers across AI subfields are building systems that they call "world models", yet there is no consensus on what a world model fundamentally is, what it should predict, or how it should be built. This perspective article provides a scientific definition of world models, discussions of their key technical aspects, and a staged roadmap for developing effective world models.

Xinyuan Chen, Haoyu Guo, Shi Guo +10

Shanghai Artificial Intelligence Laboratory

World Models Roadmap Model-Based Reinforcement Learning Artificial Intelligence Systems Video Generation

Jul 6, 2026cs.CV

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

Lighting Illumination Variations Video Generation Star-Vae In-The-Wild Videos

Jul 5, 2026cs.MM

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 Models Video Generation Audio-Video Generation Energy Resources Scaling Laws Camera

Jul 4, 2026cs.CV

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

\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

\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

\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

\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.

Camera-Conditioned Video Generation Video Generation Human Motion Generation Generative Models Video Latents Training-Free+1

Jul 2, 2026cs.CV

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

Diffusion Transformers Quantizer Video Generation

Jul 1, 2026cs.CV

Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation

Recent advances in Image-to-Video generation allow a single image to be animated into a convincing video under text guidance, raising serious copyright and privacy risks. We propose Anti-Prompt, an image protection approach that injects imperceptible perturbations into an image, inducing visible inconsistencies and structural failures in text-guided I2V generation. Our method is motivated by a simple empirical observation. When text guidance is removed from modern I2V models, generation quality degrades markedly, not only in motion realism but also in subject preservation, structural coherence, and temporal consistency. Building on this insight, Anti-Prompt exploits the model reliance on textual guidance by attenuating text-conditioned interactions during denoising while strengthening visual-only pathways. To further systematically evaluate protection effectiveness, we introduce a Video-LLM-assisted evaluation protocol that provides interpretable, frame-grounded analyses of generation artifacts and inconsistencies. Experiments on two representative I2V architectures demonstrate that our method achieves strong protection performance while improving efficiency and cross-model transferability.

Yeonghwan Song, Chanhui Lee, Jinsoo Park +1

GIST · POSTECH

Text-To-Video Generation Model Video Generation

Jul 1, 2026cs.CV

Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models

Recent 3D generative models can synthesize high-quality geometry but often struggle to reproduce intricate textures from reference images, largely due to the scarcity of large-scale 3D training data with rich surface appearance. In contrast, visual generative models are trained on datasets several orders of magnitude larger and excel at modeling complex visual patterns. Motivated by this gap, we introduce Ink3D, a framework that bridges 3D generation with large-scale video generative models to synthesize extremely complex textures. Ink3D first reconstructs a white-mesh geometry using an off-the-shelf 3D generation model. It then employs OrbitPainter, a conditional video generative model, to produce dense orbit-scan videos capturing object appearance across viewpoints. To convert these views into coherent textures, we introduce TextureOptimizer, a neural baking module that integrates dense multi-view observations while mitigating geometry inconsistencies arising from video generation. By decoupling geometry and texture synthesis and leveraging large-scale pretrained video priors, Ink3D enables significantly richer and more faithful texture generation than prior approaches.

Yue Han, Chong Li, Zhening Liu +5

ZGCA & ZGCI · Zhejiang University · Microsoft Research +1

3D Generative Models 3D Assets Texture Generative Video Models 3D Generation Video Generation+1

Jul 1, 2026cs.CV

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

In

\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

\textbf{FlashAttention}

offers a promising path toward hardware acceleration, existing low-bit quantization methods overlook two critical challenges in this setting:

\textbf{1)}

applying online rotation matrices -- a widely used technique for mitigating outliers in Queries (

Q

) and Keys (

K

) -- is difficult to reconcile with

\textbf{RoPE}

; and

\textbf{2)}

the non-negative attention matrix

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

Q

and

K

are strongly affected by the dimensional partitioning of

\textbf{3D RoPE}

. Based on this finding, we propose

\textbf{RotateAttention}

, an efficient

\textbf{mixed-precision INT4 FlashAttention}

framework tailored for

\textbf{DiT-based video generation models with 3D RoPE}

, using selective

\textbf{FP16 fallback}

for accuracy-sensitive attention blocks and denoising steps. RotateAttention introduces two core techniques:

\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

Q

and

K

; and

\textbf{2) Range-optimized

P

Quantization}

, which uses fixed scales and zero-points to fully exploit the

\textbf{INT4 numerical range}

with minimal computational overhead. Experiments show that

\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

Block Sparse Flash Attention Video Diffusion Models Video Generation Video Latents Dynamic Rope Manipulation Rectification

Jun 30, 2026cs.RO

DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation

Video-based embodied world models provide an appealing substrate for robotic manipulation by predicting future states, yet current approaches remain limited by a fundamental entanglement: accurately modeling dynamics typically requires low-level temporal reasoning, while producing high-resolution frames demands expansive visual synthesis according to high-level semantics. This entanglement results in slow inference speed for iterative planning or too coarse predictions to retain contact-rich details. To solve this dilemma, we present Disentangled Video Generation World Model (DVG-WM), an efficient framework that explicitly decomposes world modeling into dynamics learning and visual synthesis. Conditioned on an initial observation and a language instruction, our model first generates a plausible sequence of intermediate visual states to preview the physical interaction and refines them to obtain high-fidelity videos. Furthermore, an efficient cascading mechanism is proposed, where DVG-WM uses flow matching to directly map the dynamics to video latents, and introduces a latent degradation mechanism to regenerate contact-rich details. Experiments on LIBERO and real-world platforms demonstrate improved video quality with up to 3.97 times acceleration, validating that disentangled video generation can be an efficient embodied world model for robotic manipulation.

Ziyu Shan, Zhenyu Wu, Xiaofeng Wang +2

Nanyang Technological University, Singapore · Beijing University of Posts and Telecommunications, Beijing, China · GigaAI

Video World Models Video Generation Robotic Manipulation World Models Entanglement

Jun 30, 2026cs.CV

World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration

The fundamental obstacle to industrial grade video generation is the lack of controllability: existing models treat video as a pixel distribution sampling problem, bypassing the explicit, instance level

4D

(3D + T)

physical world. Consequently, content creators cannot specify geometry, motion, camera parameters, or lighting in a deterministic, quantitative way, leading to the infamous ''gacha'' loop that makes professional content creation prohibitively inefficient and expensive. To address this, we introduce the World Narrative Model (WNM), a paradigm that decouples what to render -- the structured physical narrative -- from how to render -- the pixel generation process. WNM replaces end-to-end black-box sampling with orchestrated

4D

pre-visualization for media generation. Collaborative agents translate sparse multimodal inputs, including text, reference videos, and sketches, into a fully editable world representation with scene geometry, object layouts, character/animal skeleton motion, trajectories, camera motion, and lighting at quantitative, physically meaningful granularity. This representation acts as a deterministic structural blueprint that drives existing video foundation models, either frozen or lightly adapted, to render final footage, turning the base model into a faithful neural shader. Built on this engine, our human-AI platform supports automatic world generation and pre-visualization aligned with professional filmmaking pipelines, while director consoles enable seamless human refinement. Experiments show that WNM greatly reduces probabilistic ``gacha'' calls and produces videos whose layout, motion, and cinematography closely follow creator intent. The framework is open and modular, allowing each component, such as world representation, control agents, and adapters, to be independently improved. Project website: https://glassroom.sjtu.edu.cn/WNM/.

Ye Chen, Xuanhong Chen, Yupeng Zhu +23

Shanghai Jiao Tong University

Generative Video Models Video Generation Playable Video World Generation World Models Neural Rendering Pixels+1

Jun 29, 2026cs.CV

UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image

Articulated 3D objects are essential for interactive environments in embodied AI, robotics, and virtual reality, but reconstructing their structure and motion from sparse observations remains challenging. Existing approaches remain largely constrained by lack of supervised data or lack the priors needed to reliably recover articulation, hidden geometry, and internal object structure. We present the first debate-driven agentic approach to articulated 3D object reconstruction from text or image inputs that both grounds articulation reasoning in concrete motion and exposes the occluded geometry revealed under articulation. High-level agents reason about object semantics and motion using knowledge from vision-language and video models, while low-level agents estimate articulation parameters and interaction points; together, they engage in a two-round structured debate that first exploits global--local disagreement and then grounds the agents in freely generated video. The same video prior, conditioned on the agreed articulation, then drives each part through its motion to expose occluded interiors and geometry that cannot be inferred from a single static view. By combining agentic reasoning with a video generative prior, our approach jointly infers articulation and reconstructs complete 3D articulated objects, producing high-fidelity geometry, internal structure, and motion-consistent states beyond directly observed surfaces.

Mohamed el Amine Boudjoghra, Ivan Laptev, Angela Dai

1Technical University of Munich · 2Mohamed Bin Zayed University of Artificial Intelligence

3D Reconstruction Video Generation Text Analysis and Detection

Jun 29, 2026cs.CV

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 Models Video Generation Keyframe Selection Iterative Denoising Methods

Jun 26, 2026cs.MM

A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks

Automatically generated videos from scientific papers are increasingly used for education and research dissemination. However, existing evaluation metrics mainly measure visual quality or whether key points from the paper appear in the video without assessing whether the video actually helps viewers understand the ideas. We introduce EffectivePresentationScorer, a framework for evaluating the instructional quality of scientific presentation videos. It checks whether a video explains the main ideas clearly, introduces needed background concepts, and connects technical details to the main contribution of the paper. When we apply EffectivePresentationScorer to the existing paper-to-video generation systems, we find that generated videos mention the correct topics and follow the structure of the paper but fail to explain prerequisite concepts or clarify why the method works. These failures are often ignored by existing video evaluation metrics, which focus on content presence rather than explanatory quality.

Ishani Mondal, Aparna Garimella, Ananya Sai +2

University of Maryland, College Park · Adobe Research

Scientific Figure Summarization Video Generation

Jun 26, 2026cs.CV

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-domain video generators and robot-specific data fine-tuned models can still produce physically implausible manipulations, including discontinuous motion trajectories and inconsistent robot-object interactions, which limits their reliability as world simulators. Through extensive experiments, we find that such physical instability mainly arises from two factors: deformation of moving objects and implausible spatio-temporal correlations among interacting entities, particularly during contact. Building on this observation, we propose PhysisForcing, a scalable training framework that strengthens physical consistency by focusing supervision on physics-informative regions through joint optimization of pixel-level and semantic-level features. The framework consists of a pixel-level trajectory alignment loss, which supervises DiT features using reference point trajectories, and a semantic-level relational alignment loss, which aligns DiT features with inter-region relations extracted from a frozen video understanding encoder. Extensive experiments on R-Bench, PAI-Bench, and EZS-Bench show that PhysisForcing consistently improves embodied video generation over strong baselines, improving the Wan2.2-I2V-A14B and Cosmos3-Nano base models on R-Bench by 22.3% and 9.2% (7.1% and 3.7% over vanilla finetuning), with the Cosmos3-Nano variant attaining the best overall score. Beyond generation, as a world model under the WorldArena action-planner protocol it raises the closed-loop success rate from 16.0% to 24.0% and further improves downstream policy success, indicating that physically aligned video models yield stronger representations for robotic manipulation.

Peiwen Zhang, Yufan Deng, Shangkun Sun +11

Peking University, NVIDIA

Physics Simulation Sim-To-Real Reinforcement Learning Human Motion Generation Robotic Manipulation Video Generation

Jun 26, 2026cs.CV

TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL

Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but this chunk-wise formulation makes temporal instruction following ambiguous. A single global prompt does not specify which sub-event should be realized in each chunk, while naively switching to step-wise prompts often leads to delayed reactions, blended step semantics, and error propagation across prompt transitions. These failures are difficult to address with supervised fine-tuning or distillation alone: SFT suffers from exposure bias, while rollout-based distillation still optimizes low-level denoising or teacher-distribution matching rather than directly enforcing action ordering and prompt-transition correctness. We address these challenges with TempAct, a planner--executor reinforcement learning framework that jointly optimizes temporal decomposition and step-conditioned execution for temporally plausible AR video generation. TempAct uses an LLM planner to explore span-aware step prompts that are executable by the video model, and trains an AR diffusion executor to follow these prompts under its own generated histories. Its key mechanism is hierarchical group exploration: candidate plans form planning groups, and each plan induces an execution group of multiple continuations from a shared visual context, enabling plan-level credit assignment for long-horizon temporal outcomes and executor-level credit assignment for prompt-switch behavior. We further design hierarchical rewards that combine plan-quality and full-video temporal feedback for the planner with local transition-level step-following rewards, aesthetic regularization, and KL constraints for the executor. Experiments on Self-Forcing and LongLive show that TempAct improves temporal consistency while preserving overall visual quality.

Jing Wang, Xiangxin Zhou, Jiajun Liang +5

Shenzhen Campus of Sun Yat-Sen University · Tencent Hunyuan · Tsinghua University +2

Autoregressive Video Generation Autoregressive Diffusion Video Diffusion Models Video Generation Physical Plausibility

Jun 25, 2026cs.CV

MemoBench: Benchmarking World Modeling in Dynamically Changing Environments

Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most assess consistency only while the target remains in view, and the few that force objects out of view evaluate static scenes where nothing changes during occlusion. To bridge this gap, we introduce MemoBench, a diagnostic benchmark built around the disappear-and-reappear paradigm in dynamically changing environments: a target object undergoes a physical process, disappears from view, and must be correctly recovered in its updated state upon reappearance. We curate 360 ground-truth clips spanning synthetic and real-world scenes, and design an evaluation suite combining automated metrics with VQA-based assessment across four diagnostic pillars. Evaluation of eight state-of-the-art models reveals key insights and open challenges regarding memory consistency under the disappear-and-reappear paradigm.

Haoyu Chen, Kaichen Zhou, Hang Hua +11

Harvard University · MIT · MIT-IBM Watson AI Lab +5

Long-Video Benchmarks Generative Video Models Video Generation World Models Textvqa World+1

Jun 25, 2026cs.CV

RayPE: Ray-Space Positional Encoding for 3D-Aware Video Generation

Modern video diffusion transformers position their tokens through RoPE on the (u,v,t) axes -- a description of the camera's sampling grid that says nothing about the 3D structure of the scene. We observe that the geometric relation between two camera rays is captured by the Plucker reciprocal product, which is bilinear in the two rays -- the same algebraic form as the dot product in Transformer attention. Building on this analogy, we propose RayPE, a positional-encoding extension that injects per-token 6D Plucker coordinates additively into the queries and keys of self-attention, with a query/key flip arrangement under which the symmetric identity configuration coincides exactly with the reciprocal product. The injection is additive, the resulting attention score decomposes into a content term, a geometry term, and two content and geometry cross-terms -- all of which our experiments find individually necessary. To make the encoding stable across video data with heterogeneous camera-translation scales (SfM, deep SLAM, metric), we further decouple ray direction from moment magnitude, gate the encoding by a learned function of the log-magnitude, and apply RMSNorm to align it with the QKNorm-normalized content branch. The full module adds less than 0.1% parameters to a pretrained video DiT, is zero-initialized to start from the pretrained weights, and improves camera controllability, cross-frame 3D consistency, and overall video quality on a four-dataset training mixture.

Minghao Yin, Jiahao Lu, Wenbo Hu +3

1The University of Hong Kong · 2The Hong Kong University of Science and Technology · 3ARC Lab, Tencent

Video Diffusion Models Positional Encoding Raymap-Induced Geometry Video Generation Simultaneous Localization And Mapping

Jun 25, 2026cs.CV

PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation

Developing physically aware video generation models remains a significant challenge due to the difficulty in capturing diverse physical phenomena, such as thermal dynamics, mechanics, and optics. In this work, we introduce PhysRAG, a novel pipeline that enhances physical awareness in video generation through Retrieval-Augmented Generation (RAG). To address the issue of limited high-quality data, we design a two-stage data filtering pipeline based on the WISA-80K dataset, resulting in a curated set of 7K high-quality videos for training. Furthermore, we construct a physical video database and develop a mechanism to inject physical knowledge into a video diffusion model using learnable queries. Our method achieves state-of-the-art performance in both visual quality and physical rule compliance, surpassing existing models in benchmarks such as PhyGenBench and VBench. We conduct extensive ablation studies to validate the effectiveness of our key components, including the data filtering pipeline, RAG mechanism, and method for physical information extraction. To facilitate future research, our code, data, and models are prepared for release at https://github.com/sediment1024/PhysRAG.

Kexu Cheng, Zicheng Liu, Mingju Gao +2

School of Computer Science, Peking University, Beijing, China · Institute of AI for Industries, Chinese Academy of Sciences, Nanjing, China

Video Generation Text-To-Video Generation Model Physics-Aware Models Statistical Physics

Jun 25, 2026cs.CV

NaviCache: Test-Time Self-Calibration Caching for Video Generation

Video Diffusion Models (VDMs) is constrained by immense computational costs. While offline calibration-based acceleration suffers from calibration data dependency, prohibitive calibration duration, and susceptibility to distribution shifts, offline calibration-free methods eliminate these hurdles. However, since they rely on instantaneous zero-order approximations where the mapping between input and output differences varies in real-time, they are susceptible to observational noise and ignore the intrinsic momentum within the diffusion trajectory. In this paper, we propose NaviCache, a plug-and-play test-time self-calibration method re-conceptualizing feature evolution as an Inertial Navigation System (INS) problem. NaviCache bridges the fundamental domain gap and the non-stationary nature of diffusion by modeling the relative coupling between input and output variations. We introduce a dual-state estimation architecture that adaptively tracks the feature change ratio and its latent drift, initialized via a specialized Initial Alignment phase. By integrating a time-dependent noise schedule with an uncertainty-aware Measurement Update mechanism, NaviCache provides a theoretically grounded mechanism for error-bounded computation skipping. Extensive experiments on the HunyuanVideo, Wan, and Open-Sora series demonstrate that NaviCache exhibits more accurate error judgment for computation skipping and achieves outstanding comprehensive performance.

Zheqi Lv, Zhibo Zhu, Jinke Wang +6

Zhejiang University, Hangzhou, China · Cornell University, New York, USA · Tencent Hunyuan, Shenzhen, China +1

Video Generation Accelerometer Data Inertial Navigation Systems Momentum

Jun 25, 2026cs.CV

LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration

Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs. Feature caching accelerates inference by reusing intermediate representations. Existing methods rely on historical features for implementation simplicity, yet suffer from severe error accumulation at high acceleration ratios. To address this limitation, we investigate the nature of the requisite feature correction. We demonstrate that the optimal calibration update is characterized by a shared low-rank subspace across diverse prompts. Guided by this structural insight, we propose LearniBridge, a learnable calibration mechanism for feature caching that bridges multiple timesteps through lightweight LoRA updates. This mechanism enables effective calibration requiring only 3-5 training samples. Extensive experiments on image and video generation show that LearniBridge achieves up to

5.87\times

,

5.75\times

, and

4.10\times

acceleration on FLUX, HunyuanVideo, and WAN2.1, respectively. On WAN2.1, it improves VBench by 1.28% over the previous SOTA at

4.10\times

acceleration. Our code is available at https://github.com/Iiiiiiirene/LearniBridge.

Xuyue Huang, Zhe Chen, Wang Shen +1

Shenzhen Ubiquitous Data Enabling Key Laboratory, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Central Media Technology Institute, Huawei Technologies Co., Ltd., Shenzhen, China

Diffusion Transformers Diffusion Models Video Generation Cache Bridge Acceleration

Jun 25, 2026cs.CV

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

Streaming video editing has made rapid progress, yet practical deployment is still limited by two core issues: maintaining stable backgrounds and non-edited regions over time, and achieving the low latency required for real-time interactive scenarios. Meanwhile, recent streaming video generation methods are mostly developed for synthesis and cannot be directly applied to editing due to the strict preservation requirement and region-specific control. In this work, we present a novel streaming video editing framework that performs causal, frame-by-frame editing with strong content preservation and real-time responsiveness. Our key design is a three-stage distillation pipeline that progressively transfers editing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming editor, enabling stable long-horizon edits without sacrificing visual fidelity. To further support real-time deployment, we introduce an AR-oriented mask cache that reuses region-related computation across frames, substantially reducing redundant processing and accelerating inference. Finally, we establish a dedicated benchmark for streaming video editing. Extensive evaluations demonstrate that our method achieves state-of-the-art visual quality among streaming baselines while drastically boosting inference speed to 12.66 FPS, making it suitable for interactive and augmented reality applications.

Xinyu Wang, Chongbo Zhao, Fangneng Zhan +1

THU · HKUST

Video Editing Streaming Video Diffusion-Based Image Editing Video Generation Real-Time Systems

Jun 24, 2026cs.CV

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where visual cues such as arrows, sketches, and emojis orchestrate complex video dynamics with unprecedented controllability. However, these seemingly innocuous static cues can be interpreted by models as executable temporal instructions, unfolding into harmful actions in the generated videos. Despite the severity of this threat, existing safety benchmarks remain predominantly focused on text-based and content-only image-based jailbreaks, leaving implicit visual prompt attacks insufficiently explored. To bridge this gap, we present VVA-Bench, the first systematic benchmark for evaluating video generation safety under categorized vision-centric prompt attacks. Extensive experiments on VVA-Bench demonstrate that state-of-the-art models are highly susceptible to such attacks, with Attack Success Rates (ASR) reaching 100.0% on Wan 2.7 and 74.8% on Veo 3.1. To mitigate these risks, we propose VPA-Guard, a retrieval-augmented and self-evolving defense framework. By leveraging few-shot reasoning to identify latent malicious intents, our method reduces the attack ASR by 44.2% and the harmfulness score by 73.4% on average, while maintaining the model's utility for legitimate user edits. Our work provides both a rigorous benchmark and an effective defense strategy to advance safe and socially responsible multimodal generation.

Yining Sun, Haoyu Kang, Jiajun Wu +7

1Tsinghua University · 3Central South University · 4South China Normal University +3

Video Generation Jailbreak Attacks Controllability

Jun 23, 2026cs.CV

Trimming the Long-Tail of Visual World Modeling Evaluation

Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irregular interactions remains underrepresented. Although recent visual world models, including image and video generation models, achieve impressive realism on existing benchmarks, they primarily focus on simulating common physical interactions. This raises a central question: Do current visual world models internalize and generalize physical principles? In this work, we introduce Tailor-Bench, a benchmark that challenges world models to simulate irregular physical interactions. To enable systematic evaluation, we design three scenario modes that progressively challenge model reasoning: Regular scenarios reflect common tool-task pairs, Unconventional scenarios replace conventional tools with attribute-compatible substitutes to test affordance generalization, and Impossible scenarios introduce attribute-violating tools to probe constraint awareness. Additionally, we design two complementary settings under a unified evaluation protocol: predictive generation requires inferring outcomes without guidance, while descriptive generation specifies the target outcome for faithful realization. Our experimental results reveal a clear long-tail gap in physical world modeling: performance degrades from Regular to Unconventional and Impossible scenarios, indicating limited generalization beyond common interactions. Failure analysis further shows that models rely on superficial visual patterns: image models fail to realize correct state changes, while video models further suffer from temporal inconsistencies.

Bingxuan Li, Yining Hong, Cheng Qian +6

University of Illinois Urbana-Champaign · Stanford University · Columbia University

Video World Models World Affordances Video Generation

Jun 23, 2026cs.AI

Navigating User Behavior toward Personalized Multimodal Generation

Modern AIGC pipelines deliver high-fidelity images and videos but presuppose a well-formed creation instruction, while end users rarely articulate visual details, leaving generators misaligned with user demand. We study personalized content generation, which turns a user's interaction history into an executable instruction for downstream synthesis, and identify two obstacles: behavior must be encoded in a form legible to language reasoning, and the model must acquire instruction-writing skill absent from both pretraining and behavior data. We propose NaviGen, which represents each item with a dual identifier coupling a collaborative code and a textual code as a behavioral substrate and a semantic bridge in one token stream. On this representation, a two-stage SFT+RL pipeline first distills preference reasoning and instruction writing from evolutionarily searched supervision, then aligns generation with user intent through hierarchical and self-consistent rewards. Experiments across product, game, and short-video domains show that NaviGen improves personalized image and video generation, strengthens next-item prediction, and yields more specific, relevant, and visually generatable instructions. Our code is released at: https://github.com/iLearn-Lab/NaviGen.

Hengji Zhou, Yufeng Liu, Ye Liu +3

South China University of Technology · Harbin Institute of Technology, Shenzhen

Multimodal Generation Data Generation Pipelines Video Generation Analytics Short Video Bursts Menu