多模态生成与编辑

Generative world models for autonomous driving face two unresolved tensions: heterogeneous control injection, where free-form language, HD-maps, trajectories, and camera poses reside in incompatible representational spaces, and post-hoc cross-view fusion, where per-camera latents fail to encode global 3-D geometry. We trace both to a single root cause: the absence of a shared symbolic interlingua aligning language, geometry, and pixels at the latent-token level. We present DRIVE-CHOREO, an LLM-choreographed multi-agent world model that recasts controllable multi-view video generation as latent choreography. Three Qwen2.5-VL agents - a Director parsing user intent into a structured WorldScript, a Cartographer grounding it into spatially-anchored layout tokens, and an Auditor feeding cross-view critiques back as auxiliary supervision - jointly author a single position-aware token sequence. This sequence is co-compressed with the multi-view video via a view-time permutation that enforces inter-camera geometry within the convolutional receptive field of a 3-D VAE. On nuScenes, DRIVE-CHOREO sets new state-of-the-art multi-view consistency and BEV mAP (21.6) with competitive FVD (45.7); a detector trained purely on our synthetic data gains +2.4 NDS on the real validation split, validating downstream utility.

World models are transitioning from passive visual generators to foundational, operational infrastructure for Physical AI: they must natively acquire world knowledge from heterogeneous experience, maintain persistent states over long horizons, and execute efficiently within real deployment constraints. We introduce Kairos, a native world model stack designed around these requirements. (1) Kairos learns the world by pioneering a Native Pre-training Paradigm governed by a Cross-Embodiment Data Curriculum, which organizes open-world videos, human behavioral data, and robot interactions into a progressive developmental pathway. (2) Kairos maintains the world by unified world understanding, generation, and prediction within a Native Unified Architecture equipped with Hybrid Linear Temporal Attention, where sliding-window attention captures local dynamics, dilated sliding windows capture mid-range dependencies, and gated linear attention maintains persistent global memory. We establish formal theoretical bounds demonstrating that this temporal factorization strictly limits error accumulation, mathematically guaranteeing state propagation across extended horizons. (3) Kairos runs the world by incorporating a Deployment-Aware System Co-Design to support low-latency rollout generation on server and consumer-grade hardware for real-world observation-action-feedback loops. Experiments on embodied world-model, long-horizon, and action-policy benchmarks show that Kairos achieves top level performance while offering a strong efficiency-capability trade-off. Together, these results position Kairos as a cohesive operational foundation for future self-evolving physical intelligence.

We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence. With natural language as a unified action interface, it predicts physically grounded future visual trajectories from current observations across robotic manipulation, autonomous driving, indoor navigation, and human-to-robot transfer. This unified formulation provides three promising application directions: synthetic data generation for policy training augmentation, scalable virtual environments for policy evaluation, and language-guided planning signals for downstream robot control. This is achieved through a three-part design: a) Double-Stream MMDiT with MLLM Action Encoding, where a 60-layer double-stream diffusion transformer couples frozen Qwen2.5-VL semantics with video-VAE latents through layer-wise joint attention; b) Embodied World Knowledge (EWK), an 8.6M video-text corpus (200M+ frames) with action-language mapping over 20+ embodiments and 500+ action categories; and c) General+Expert Progressive Curriculum, a two-stage training strategy that first learns general visual priors and then injects embodied specialization under a shared language interface. Extensive results show strong competitiveness: ranks 1st overall on EWMBench and DreamGen Bench, outperforms all open-source models on WorldModelBench and PBench. Additional zero-shot analyses on RoboTwin-IF benchmark further support robust generalization and multi-view consistency.

Diffusion and flow-based generative policies provide a powerful policy class for reinforcement learning by inducing rich stochastic exploration through iterative action generation. However, the stochasticity of diffusion policies is not suitable for stable and precise control in high-dimensional robotic systems, where small action variations can accumulate into inconsistent motion and reduced robustness. To address this issue, we propose SteerGenPO, a latent-space reinforcement learning framework that steers a trained generative policy into a robust deterministic robotic controller. The key idea is to replace stochastic latent sampling of the trained generative policy with a learned latent actor that predicts a state-dependent latent input for the generative policies. This separates exploration and control: stochastic generative sampling provides diverse action proposals during policy learning, while deterministic latent steering provides stable and adaptive control at deployment. We evaluate SteerGenPO on six Isaac Lab benchmarks and a Unitree G1 locomotion task. The results show SteerGenPO improves over both classical RL and generative RL baselines, while its deterministic latent steering produces more stable inference-time behaviors and more reliable command responses.

Post-training quantization (PTQ) enables efficient deployment of deep networks using a small set of data. Its application to visual autoregressive models (VAR), however, remains relatively unexplored. We identify two key challenges for applying PTQ to VAR: (i) large reconstruction errors in attention-value products, especially at coarse scales where high attention scores occur more frequently; and (ii) a discrepancy between the sampling frequencies of codebook entries and their predicted probabilities due to limited calibration data. To address these challenges, we propose a PTQ framework tailored for VAR. First, we introduce a shift-and-sum quantization method that reduces reconstruction errors by aggregating quantized results from symmetrically shifted duplicates of value tokens. Second, we present a resampling strategy for calibration data that aligns sampling frequencies of codebook entries with their predicted probabilities. Experiments on class-conditional image generation, inpainting, outpainting, and class-conditional editing show consistent improvements across VAR architectures, establishing a new state of the art in PTQ for VAR.

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

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

Flow Matching (FM) is a powerful approach for behavior cloning in multimodal action spaces [Jiang et al., 2025], but because it is not trained to directly maximize expected return, there is still room to improve how FM policies act at test time. This work investigates whether a learned world model can improve FM policies by enabling Model Predictive Path Integral (MPPI) planning over candidate action sequences proposed by the policy. Building on TD-MPC2 [Hansen et al., 2024], I introduce FlowMPC, a framework that combines an imitation-learned FM policy with a learned world model for test-time planning in ManiSkill manipulation tasks [Tao et al., 2025]. Across PickCube and PickSingleYCB, adding the world model improved performance over the FM policy alone, with especially clear gains in end-of-episode success. These results suggest that world-model-based planning can effectively complement flow-based imitation policies without modifying the FM training objective.

Visual world models (VWMs) synthesize interactive, action-conditioned rollouts from a single context image. However, it remains an open question how robust these models are to adversarial perturbations. Standard adversarial attacks fail to assess this vulnerability because attackers lack ground-truth future videos and cannot predict subsequent user controls. We introduce BadWorld, a label-free adversarial framework tailored for autoregressive VWMs that systematically overcomes both constraints. First, to bypass the need for future supervision, we propose a self-supervised velocity attack that directly disrupts the early denoising dynamics of the model. Second, to ensure the attack generalizes across unpredictable user actions, we formulate a trajectory-adaptive bi-level optimization that actively mines hard control sequences to forge control-agnostic perturbations. Evaluated on representative VWMs with continuous and discrete controls, BadWorld exposes severe structural fragility. Visually indistinguishable adversarial images reliably trigger catastrophic degradation in future rollouts, leading to incomplete denoising, structural collapse, and control inconsistency. These findings reveal critical risks for deploying VWMs in safety-critical systems while highlighting a practical mechanism for privacy protection.

World models are widely used in robotic and agentic engineering control systems due to their ability to learn latent dynamics for planning and decision-making. As these systems are increasingly deployed in safety-critical settings, understanding their robustness under adversarial conditions has become essential. However, existing evaluations lack a unified benchmark for testing adversarial threats across the policy, value, and latent-dynamics levels of world-model agents. To fill this gap, we present ARB4WM, a unified evaluation framework for pre-deployment robustness and risk assessment of world-model agents under visual perturbations. ARB4WM defines five white-box loss objectives across these three levels and studies their effects when combined with single-step or multi-step perturbation strategies and temporal attack modes, including full-frame, half-sequence, and sparse-frame exposure. Specifically, we evaluate four Dreamer-style agents across 20 tasks from MetaWorld and the DeepMind Control Suite under different loss objectives, perturbation strategies, and temporal attack modes. Results show that attacks targeting value estimation, latent representations, and RSSM dynamics can be as damaging as direct policy disruption, and that early or frequent perturbations are especially harmful, while input-level defenses provide limited recovery under adaptive attacks. These findings suggest that safety, risk, and reliability assessment for world models should cover multiple component-oriented attack objectives and temporal exposure protocols rather than relying solely on action-space robustness. Source code is available at https://github.com/zaoanguai/ARB4WM.

Unified Multimodal Models (UMMs) have emerged as a critical direction for general-purpose multimodal intelligence, integrating understanding and generation into a single framework. However, existing UMMs face prominent challenges: (1) the inherent learning conflicts between visual understanding and generation tasks, leading to suboptimal modeling in both tasks; (2) different understanding and generation visual spaces impeding scalability; (3) over-reliance on task-specific data that neglects the duality of text-image understanding and generation. To address these challenges, we propose UniDDT, which leverages a Noisy ViT encoder along with an LLM to unify semantic encoding for visual generation and understanding tasks, while employing a separate diffusion decoder to decouple diffusion decoding from text decoding. With this Noisy ViT encoder, UniDDT is able to leverage the latent space as a unified visual representation, enabling seamless compatibility between understanding and generation tasks. Thus, the scalability within the generation tasks and the semantic expressiveness within understanding tasks can be balanced. Also, we construct dual data structures from the same image-text pairs, fostering interdependence between the generation and understanding data to exploit their inherent duality. Extensive experiments demonstrate that UniDDT achieves effective unification of multimodal understanding and generation with enhanced semantic consistency and scalability. For visual generation tasks, our UniDDT achieves 0.87 GenEval score and 86.9 DPG overall score. For multimodal understanding tasks, our UniDDT achieves 1699.5 score on MME benchmark and 76.5 overall score on SEEDbench.

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

We present SLS^2, a framework for safe feedback motion planning from pixels using robust model predictive control (MPC) in learned latent world models. Our approach trains an action-conditioned joint-embedding world model with compact Markovian latent states, enabling efficient gradient-based trajectory optimization through learned latent dynamics. To enforce safety for the true system despite imperfect latent predictions, we inform a GPU-accelerated system level synthesis (SLS) robust MPC scheme with conformal prediction to obtain calibrated latent error bounds and robust latent-space constraint sets. We further learn and conformalize a latent constraint checker, allowing the SLS planner to impose probabilistic safety constraints during closed-loop execution. We evaluate our method on vision-based control tasks, where it improves both goal-reaching performance and safety over latent world-model and safe-planning baselines.

The success of generative models in language and visual generation has inspired extensive applications to generative robot planning. However, most existing works either focus on single-robot planning, or generate multi-robot trajectories in a sequential manner with iterative post-processing to resolve inter-robot conflicts. In this work, we investigate whether coordinated multi-robot trajectories, as a special spatiotemporal distribution, can be learned and generated with a generative model in a feed-forward manner. We propose Robots as Tokens (Roken), a unified diffusion transformer that directly generates multi-robot trajectories that satisfy both (individual) safety and (global) connectivity constraints. The core design of Roken is to represent each robot as a discrete token, allowing them to naturally interact with each other through self-attention, and cross-attend to map tokens for environment layouts. We further introduce several auxiliary tasks based on Bayes' theorem to provide multi-scale spatial-temporal supervision for efficient learning of the conditional distribution. In training, Roken absorbs diverse expert trajectories from different team sizes. During inference, Roken behaves as a versatile multi-robot planner that can handle single-robot planning, coordinated multi-robot trajectory generation, and conditional trajectory generation by fixing some robot tokens as conditions. Experiments in diverse cluttered environments show that Roken can generate coordinated multi-robot trajectories to perform connectivity-constrained goal navigation tasks with high success rates, outperforming the baseline method used to generate the training dataset. Roken also demonstrates good scalability after training with mixed team sizes, and shows generalization to unseen or partially observed environments, verifying its potential to learn from diverse data and perform versatile tasks.

Mechanistic interpretability seeks to explain neural network behavior by decomposing model computations into interpretable features and circuits. While transcoder-based circuit tracing has recently enabled detailed causal analyses of large language models, multimodal diffusion transformers for image generation remain comparatively opaque. We still lack tools for understanding how semantic information propagates across denoising steps and how text and image representations interact within double-stream MM-DiT architectures. Existing methods provide only partial insight: attention maps expose a limited view of token interactions, while sparse autoencoders can discover interpretable features but do not directly reveal how these features are transformed and composed through nonlinear MLP layers. In this work, we extend transcoder-based circuit tracing to multimodal diffusion transformers. We train timestep-conditioned transcoders that faithfully approximate the input-output behavior of MLP sublayers in FLUX.1[schnell]. By replacing MLPs with transcoders and linearizing the remaining computation, we obtain exact feature-to-feature attribution and recover compact, interpretable circuits. Empirically, our transcoders match or slightly outperform sparse autoencoders on the sparsity-faithfulness tradeoff. The resulting circuits reveal mechanisms underlying attribute binding and cross-stream semantic propagation, and provide causal explanations for systematic generation errors. Moreover, circuit-guided interventions are substantially more precise and effective than standard SAE-based steering. Our results demonstrate that transcoder-based circuit analysis is feasible for state-of-the-art diffusion transformers and provides a powerful framework for understanding and controlling multimodal generative models. The code is available at https://github.com/Artalmaz31/DifFRACT

Quadruped robots are capable of traversing a wide range of complex terrains with high flexibility. As highly mobile ground-based intelligent platforms, they can be equipped with modules for navigation control, environmental perception, and intelligent interaction, thereby serving as real-world mobile deployment platforms for various algorithms. In this paper, we introduce Y-BotFrame, an extensible embodied platform that turns a robot into an intelligent ground assistant. Y-BotFrame integrates multimodal perception capabilities, including speech, vision, and LiDAR, and employs a large language model as the cognitive core for environmental understanding, contextual reasoning, and task planning. The system maps user natural-language instructions into executable embodied task units that can be carried out by the robot. Y-BotFrame supports natural interaction through voice commands and visual feedback, removing the need for a remote controller and enabling efficient human-robot collaboration. With a highly extensible framework, Y-BotFrame supports plug-and-play integration of new functional modules as well as modular upgrades and iterative development, offering a reference implementation for the real-world deployment of general-purpose, instruction-driven embodied agents.The supplementary video is available at https://xdei-group.github.io/Y-BotFrame/.

Code-writing large language models (CodeLLMs) generate executable code policies for embodied agents by translating natural language goals and environmental constraints into structured control programs. However, policy generation in open-domain embodied environments suffers from two fundamental limitations: (i) delayed decoding caused by repetitive prefill computation over long prompts, and (ii) limited robustness due to fully generative decoding, which often produces API mismatches, missing safety guards, and unstable control logic. To address these limitations, we present FCGraft, a Functional Cache Grafting framework. FCGraft maintains a library of function-level validated code skeletons and their associated prompt-level Transformer key-value (KV) caches, and synthesizes new policies by retrieving relevant functions and grafting their KV caches when a new task is provided. Given retrieved function caches, FCGraft performs cache grafting via stitching, which composes cached function segments into a composite policy, and patching, which locally adapts only the necessary code regions to satisfy task-specific parameters and constraints with minimal additional decoding. By eliminating redundant prefill computation, this approach reduces generation latency, while reusing validated control structures improves robustness over prompt-level caching methods RAGCache, achieving 18.31% higher task success rate and 2.3x faster policy synthesis.

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

Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving. Existing systems assign each request a fixed parallel configuration throughout its lifetime. However, DiT workloads exhibit substantial heterogeneity across requests, execution stages, and system conditions, making static parallelism inefficient and often leading to poor GPU utilization and degraded service quality. This paper argues that DiT serving should treat GPU parallelism as a first-class schedulable resource. We present GF-DiT, a policy-programmable runtime for elastic DiT serving that dynamically adapts the parallelism of running requests according to workload demands and service objectives. GF-DiT introduces an asynchronous execution abstraction that decomposes requests into independently schedulable trajectory tasks and enables online GPU reallocation. To make elastic parallelism practical, GF-DiT further proposes group-free collectives, a lightweight communication abstraction that supports low-overhead online formation and reconfiguration of arbitrary execution groups. We implement GF-DiT in vLLM-Omni and evaluate it on representative image and video diffusion workloads. Compared with fixed-pipeline execution with static parallelism, GF-DiT improves throughput by up to 6.01$\times$, reduces mean latency by up to 95%, lowers SLO violation rates by up to 90%, and reduces communication-group setup overhead from 778 ms to approximately 60 $μ$s.

World modeling is emerging as a central principle for building intelligent systems capable of prediction, reasoning, and decision making. A central distinction can be drawn between explicit world models, which learn structured dynamics for rollout-based reasoning and planning, and implicit world models, which encode predictive structure within scalable learned representations. These complementary paradigms provide a foundation for physical AI in domains such as robotics and autonomous driving, enabling intelligence beyond reactive control under real-world constraints. Recent foundation models further suggest a pathway toward unified systems integrating perception, prediction, and action. Despite rapid progress, major challenges remain in hierarchical reasoning, long-horizon planning, and autonomous goal formation, which are critical for advancing toward artificial general intelligence. This tutorial presents a coherent framework in which diverse world modeling approaches are unified through shared predictive structure and differentiated by how such structure is represented and exploited.

Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift. In this paper, we propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation. TetherCache organizes the cache into sink, memory, and recent regions, and introduces two complementary mechanisms. First, GRAB (Gated Recall with Attention-Diversity Balancing) selects long-range memory frames using a gated score that combines attention-based relevance with temporal diversity, preserving informative yet diverse historical context under a fixed cache budget. Second, TAME (Trusted Alignment via Memory Editing) lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution, reducing the pollution caused by drifted historical features. Built on Self-Forcing, TetherCache consistently improves long-video generation quality on VBench-Long across 30s, 60s, and 240s settings. In particular, for 240s generation, it substantially improves overall and semantic scores while reducing quality drift from 7.84 to 1.33, demonstrating its effectiveness for stable long-horizon autoregressive video diffusion.

We present MoVerse, a real-time video world model that creates an interactively navigable scene from a single narrow-field-of-view image. This setting is challenging because the input observes only a small fraction of the environment, while interactive roaming requires a complete surrounding world, persistent geometry, controllable camera motion, and temporally coherent high-fidelity observations. MoVerse addresses this problem by separating world construction from observation rendering. It first expands the input into a gravity-aligned 360$^\circ$ panorama with topology-aware diffusion, closing the missing field of view before 3D reasoning. It then lifts the panorama into a persistent 3D Gaussian scaffold using panoramic geometry-aware residual prediction, yielding a dense and directly renderable spatial memory. Finally, a Gaussian-conditioned video renderer translates scaffold renderings along user-specified camera trajectories into photorealistic video. To make this renderer practical for interaction, we train a bidirectional diffusion teacher for high-quality conditional rendering and distill it into a causal autoregressive student for bounded-latency streaming. This design combines the controllability and long-range consistency of explicit 3D representations with the perceptual quality of generative video models. MoVerse supports real-time scene roaming at 8~FPS on a single NVIDIA RTX~4090 GPU, demonstrating a practical path toward single-image world creation with interactive video output.

Few-step diffusion distillation has become increasingly mature for 4-8-step generation, yet pushing further to 2 steps remains challenging. In this work, we introduce Z-Image Turbo++, a high-quality 2-step image generation model distilled from the 8-step Z-Image Turbo teacher. Our method addresses the central bottlenecks of increased task difficulty and limited model capacity in 2-step generation through three simple but effective design choices tailored to this regime. First, we propose Distribution-Aligned Adversarial Learning, which uses teacher-generated images rather than external real images as real samples for GAN training, providing a more attainable and informative adversarial target. Second, we adopt Step-Decoupled Parameterization, assigning independent model parameters to the two denoising steps to better match their distinct capacity demands. Third, we perform End-to-End Training with Iterative Regularization, allowing the first step to receive gradients from final image quality while preserving a meaningful intermediate generation through an explicit step-1 loss. Together, these designs substantially narrow the quality gap between 2-step and 8-step generation in both qualitative and quantitative evaluations, highlighting the potential of carefully tailored distillation strategies for improving the quality-efficiency trade-off in few-step generation.

We are entering a new era of composite model architectures that integrate diverse components such as vision encoders, language backbones, diffusion and flow heads, audio codecs, action generators, and world-model predictors. Such architectures underpin a broad class of multimodal models, including unified multimodal models, omni models, speech-language models, vision-language-action policies, and world models. However, existing model serving frameworks were built on narrow assumptions about model structure, making them ill-suited to accommodate this new architectural diversity. Here we present M*, a universal serving system for efficient serving of composite AI models. M* represents models as dataflow graphs, processing requests spanning diverse modalities and tasks as traversals over these graphs. The core insight is a modular abstraction that supports arbitrary composition of model components, flexible placement onto a physical cluster, and model-agnostic optimizations within a distributed runtime. We call this abstraction the Walk Graph and show how it can concisely capture composite models from a broad range of families. We instantiate M* on representative models and find that it achieves, on average, 20% lower end-to-end latency than vLLM-Omni for text-to-image workloads on BAGEL, while delivering up to 2.9x lower real-time factor and 2.7x higher throughput for text-to-speech workloads on Qwen3-Omni. M* also outperforms the V-JEPA 2-AC rollout baseline for robotic planning by up to 12.5x. Thus, our work paves the road towards more efficient serving of complex models with minimal developer effort.

Scientific figures compress complex pipelines into a single canvas, yet understanding them requires paper-grounded, step-by-step narration aligned with visual highlights a capability missing from current video generation systems and benchmarks. To address this, we introduce paper-grounded figure-to-video generation: generating narrated, region-grounded walkthrough videos from a figure and its paper. We propose MINARD (Multimodal Interpretation of Narrated Architecture via Region Decomposition), a pipeline that generates paper-grounded narrations and sequentially grounds them to figure regions. We also release FigTalk, a benchmark with new sequential and component-level grounding metrics derived. On FigTalk, MINARD generates humanlike, paper-faithful narrations and outperforms narration-conditioned figure spatial grounding compared to existing approaches in both automatic and human evaluation

Reward models for text-to-video (T2V) generation guide post-training but often fail at fine-grained semantic alignment. We trace this to two structural weaknesses in existing reasoning-based reward models: they do not systematically verify every condition described in the prompt, and the visual evidence supporting each judgment remains implicit in their free-form reasoning. We propose SG-PVR, a video reward model that addresses these limitations through plan-and-verify reasoning grounded in spatio-temporal scene graphs. The verification plan decomposes the prompt into atomic claims, ensuring every requirement is checked. The spatio-temporal scene graph, encoding entities, attributes, and temporally-grounded relations, is extracted from the video and maintained as a persistent structured visual reference throughout reasoning. Each claim is verified against both the video and the scene graph, anchoring judgments in explicit visual evidence. SG-PVR achieves strong performance on semantic alignment, including fine-grained temporal semantics. As a test-time reranker, it further enhances compositional alignment in T2V generation.

Recent progress in video generation has shown impressive visual synthesis capabilities. However, open-domain customized video generation remains limited by the lack of large-scale, annotated datasets capturing diverse identity-specific attributes. To address this, we introduce PexelsCustom-1M, the first publicly available million-scale dataset for identity-preserving video generation, containing one million curated <identity, text, video> triplets across 8,000+ categories. Leveraging this, we propose CustoMDiT, a parameter-efficient framework that adapts a pretrained multimodal Diffusion Transformer into a customized video generator with only 8% additional learnable parameters. Our method surpasses prior state-of-the-art. However, benchmarks such as DreamBooth cover only 100 classes, which is insufficient for real-world applications. To overcome this, we construct OpenCustom, a new benchmark with 1,000+ categories, created via cross-dataset knowledge fusion from ImageNet and MS-COCO. Extensive experiments confirm the advantages of both our dataset and model. We will open-source the entire ecosystem--including dataset, pipeline, benchmark, and implementations--to support further research.

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

Flow Matching has enabled robust text-to-video generation via latent ODE sampling. However, velocity approximation and numerical discretization errors inevitably accumulate, causing sampling trajectories to drift. Consequently, generated videos often suffer from severe spatiotemporal inconsistencies. Nevertheless, directly correcting these drifted, noisy latents is challenging: (i) timestep-dependent noise obscures reliable structural cues; (ii) spatial interventions risk disrupting intricate local geometry while incurring heavy computational costs. To address this, we propose Spectral Lookahead Rectification (SpecLoR), a plug-and-play inference method that bypasses noise via lookahead prediction, and circumvents spatiotemporal entanglement by shifting corrections to the frequency domain, where universal statistical priors of natural videos are readily available. First, during early sampling stages, SpecLoR looks ahead to estimate the clean latent $z_{t,0}$ and computes its 3D spatiotemporal spectrum. Next, SpecLoR rectifies the amplitude spectrum to match the prior, leaving the phase intact. Finally, the corrected state is re-noised to resume ODE integration. Experiments on Wan2.2 demonstrate that SpecLoR significantly reduces physical artifacts and enhances motion coherence across multiple benchmarks with minimal computational overhead (4 additional NFEs).

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