多模态生成与编辑

Photorealistic Style Transfer (PST) aims to transfer the color and tonal style of a reference to a content image while strictly preserving its structural integrity. However, existing deep learning-based methods inherently suffer from semantic entanglement caused by pre-trained image encoders, leading to unnatural spatial distortions. Moreover, current pixel-level mapping paradigms often ignore color gamut topology, resulting in color banding, while also lacking the multimodal capability for intuitive text-driven control. To address these bottlenecks, we propose StatLUT, an innovative multimodal framework for 3D LUT generation. First, we bypass traditional encoders and introduce a Lab-Extractor to derive spatially-agnostic statistical features, fundamentally decoupling color distributions from structural semantics to ensure artifact-free rendering. Second, we formulate LUT generation as a Transformer-based Seq2Seq translation task, utilizing a Multi-dimensional Residual Mapper (MR-Mapper) to predict topologically smooth 3D LUTs. Finally, to break the single-modal barrier, we propose the H-Diffuser, a lightweight Diffusion Transformer that directly synthesizes statistical features from natural language prompts, enabling flexible text-driven color grading. Extensive experiments on standard benchmarks demonstrate that StatLUT significantly outperforms state-of-the-art methods in both visual quality and quantitative metrics, pioneering a highly robust and flexible paradigm for multimodal photorealistic style transfer.

Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While recent offline motion generation approaches offer precise control via text and kinematic constraints, they lack the inference speed required for interactive settings. Conversely, existing online methods enable real-time synthesis but often sacrifice controllability or struggle with complex text semantics and long-horizon goals due to limited context windows. In this work, we introduce ARDY, a streaming generation framework that bridges this gap by enabling high-fidelity motion generation controllable via online text prompts and flexible kinematic constraints. ARDY employs a hybrid representation that combines explicit root features with a latent body embedding, balancing precise trajectory control with efficient generative learning. We propose a two-stage autoregressive transformer denoiser that features variable history context and supports conditioning on flexible, long-horizon kinematic constraints. By training on a large-scale motion capture dataset and being directly conditioned on text labels and kinematic constraints sampled from ground truth poses, ARDY natively learns controllable generation that supports online prompting and flexible long-horizon goals. Extensive evaluations on the HumanML3D benchmark and the large-scale, high-fidelity Bones Rigplay dataset demonstrate ARDY's high motion quality and constraint adherence, validating the efficacy of our key architectural decisions. Finally, we demonstrate the method's practical versatility through an interactive demo featuring dynamic text control, diverse keyframe pose constraints, path following, and interactive locomotion control via mouse and keyboard. Supplementary video results, code, and model releases can be found at https://research.nvidia.com/labs/sil/projects/ardy/.

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{s}table \textbf{a}cceleration \textbf{g}uidance approach for \textbf{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.

Semantic audio applications increasingly require controllable generation on commodity and embedded hardware rather than through framework-heavy datacenter stacks. We present aria, a dependency-free native runtime that runs the complete text-to-music pipeline of Stable Audio~3 (SA3) on ordinary GPUs, CPU-only machines, and a Raspberry~Pi~5, with no Python or deep-learning framework underneath. Our main contribution is a study of quantization: running the model at lower numerical precision to fit tight memory budgets, saving memory in place rather than adding to it. Because the runtime owns every internal tensor, it also exposes activation steering, a low-cost way to steer what the model generates. We judge the quality cost with three independent measures of the output (prompt adherence, overall audio quality, taste preservation), each compared against the ordinary variation between random seeds. Eight-bit precision shows no measurable quality loss on any measure while sharply cutting memory, and it is the fastest mode on the GPU; four-bit adds a small, bounded cost but shrinks the footprint enough to run the $1.2$-billion-parameter model on an $8$\,GB Pi. Against the official implementation, aria matches or exceeds generation speed and starts about seven times faster. A case study of the steering interface generates music carrying taste associations (sonic seasoning), with genuine but bounded control for a subset of attributes. These results make a compact, quantized runtime with built-in control a practical basis for on-device semantic audio in Internet-of-Sounds settings. The aria runtime is released at https://github.com/matteospanio/aria.

Video relighting requires balancing long-form temporal consistency with a physically grounded understanding of light transport, which depends on accurate estimation of intrinsic scene properties such as materials, geometry, and illumination. Existing methods follow two paradigms: (1) reconstruct a video's photometric properties via inverse rendering and relight them to a target illumination via forward rendering, using physically-based rendering (PBR) or a neural renderer; these suffer from noisy reconstructions and struggle with hard-to-model effects such as global illumination. (2) Frame the task as generative video-to-video translation conditioned on relighting targets (a target environment map or text); this limits relighting control and temporal stability, since diffusion models struggle to translate long-form videos, and is constrained by the availability of input/relit training pairs. We propose LightCrafter, a hybrid pipeline that reformulates video relighting as video translation of a proxy video: rather than translating the input video directly to the target, we translate a PBR rendering of the input under the target illumination to the final target. This bakes illumination targets into the PBR proxy, removing the need to teach the diffusion model illumination concepts like environment maps, and enables more intricate lighting control while naturally providing long-form temporal consistency. We show PBR renders alone already outperform some prior art but struggle with effects like global illumination; to capture these, we leverage photometric priors in video generation models by post-training CogVideoX on synthetic video pairs and real-world unpaired videos. We outperform prior state-of-the-art on existing real-world relighting benchmarks and contribute a synthetic benchmark for further analysis. We will release our dataset, benchmark, metrics, and code.

Rapid advancements in video diffusion models and temporal editing tools have enabled the generation of highly realistic human-centric videos, posing unprecedented challenges to digital content forensics. Existing benchmarks primarily focus on either face-swapping or global text-to-video synthesis, overlooking the crucial dimensions of human-object or human-human interactions and multi-modal alignment. To address these limitations, we introduce HumanForge, a unified, large-scale, and multi-paradigm human-centric video forgery dataset. To construct and annotate this dataset without labor-intensive manual labeling or hallucinated monolithic prompts, we propose Gen2Anno, a modular active multi-agent pipeline built on LangGraph. Gen2Anno coordinates six specialized agents-ranging from source profiling to MoE-based reference analysis and closed-loop forensic verification-to generate over 18K high-fidelity video segments and produce structured, contrastive omni-annotations containing binary decisions, fine-grained artifact categories, and spatio-temporal localization. Extensive benchmarks using state-of-the-art traditional detectors and Large Multimodal Models (LMMs) demonstrate the significant challenges of zero-shot generalization and fine-grained reasoning on HumanForge. Code and dataset will be publicly released.

World models are typically trained to predict discrete-time physical dynamics with a fixed step size baked into the model weights, preventing prediction at variable temporal resolutions. This matters for hierarchical planning, sim-to-real transfer, and scientific or game-engine applications that must query the same dynamics at multiple timescales. Hamiltonian Generative Networks (HGN) offer a principled path forward, grounding predictions in a continuous-time energy function that is, in principle, independent of the observation frame rate. In practice, however, their temporal generalization breaks down in non-conservative settings. We show that in externally forced, dissipative environments, HGN rollouts at step sizes beyond the training regime fail due to distinct failure modes, including latent magnitude growth driven by an unconstrained action-force map, and global truncation error accumulation from an under-resolved integrator. We identify a targeted fix for each mechanism and demonstrate stable dynamics prediction at temporal resolutions well outside the training distribution. In a detailed analysis, we recommend several strategies for enabling temporal generalization in continuous-time video generation.

Personalizing exoskeleton assistance requires user-specific gait data across many locomotor tasks, yet collecting this data demands repeated motion capture sessions that are costly, time-intensive, and especially burdensome for clinical populations. This challenge is most acute across walking speeds, where gait changes substantially and deviates further in clinical gait. This work introduces a subject-conditioned residual diffusion framework that generates personalized lower-limb kinematics at unseen walking speeds from a subject's gait sequence at a single seen speed. Given sagittal-plane hip, knee, and ankle trajectories at a seen speed and a desired unseen speed, the model generates a residual that transforms the seen trajectory into the unseen one, using a transformer denoiser conditioned on the subject's gait and the two speeds through feature-wise linear modulation. Trained only on able-bodied data, the model achieved a mean absolute error (MAE) of 3.4° on held-out able-bodied subjects. Without any stroke-specific fine-tuning, it achieved a 6.0° MAE on out-of-training-distribution stroke subjects, retaining subject identity for clinical gait. The framework reduced the MAE by over 70% relative to supervised feed-forward baselines, and a single seen speed matched the accuracy of four speeds within 0.4°. These results demonstrate that subject-conditioned residual diffusion can synthesize personalized gait across speeds from minimal data, reducing the collection burden for downstream exoskeleton personalization.

Safety evaluation for autonomous driving is dominated by rare, safety-critical interactions, motivating simulators that can deliberately synthesize corner cases with photorealistic observations. Corner-case generation is inherently a multi-source problem spanning visual representation, scene reasoning, and vehicle trajectory generation and control. Prior knowledge- and model-based approaches typically focus on scene or trajectory components in isolation, while diffusion-based methods attempt end-to-end generation but still struggle to ensure spatiotemporal consistency and physical realism. To unify these aspects within a single framework, we propose CARLA-GS, a modular corner-case synthesis pipeline that decouples visual representation, semantic reasoning, and physics-based execution while maintaining tight cross-module coupling. Starting from real driving data, we reconstruct an editable gaussian scene with additional geometry-consistent constraints. A multi-agent LLM then performs scene-level reasoning to identify risky interactions and generate intent-level waypoint trajectories, while the low-level motion control is delegated to CARLA, where a PID controller ensures kinematic and dynamic feasibility. The simulated vehicle states are finally re-projected into the gaussian scene for ego-centric rendering. This design enables high-level semantic reasoning, low-level physically executable motion, and photorealistic corner-case generation within a unified pipeline. Experiments on the Waymo Open Dataset show, both quantitatively and qualitatively, that our framework enables controllable corner-case generation and produces photorealistic, spatiotemporally consistent videos aligned with semantic intent and physically feasible motion.

Compact world models that condition on a language goal promise to ground relations such as ``put the red block left of the blue block'' using a sparse set of explicit reference anchors. We ask when such references actually ground a relation, and identify a trap: a goal-conditioned predictor reaches a striking $0.90$ relation-readout accuracy, yet this is instruction transcription, not perception. Withholding the goal collapses it to chance ($0.90\!\to\!0.27$, three seeds) and a counterfactual instruction makes the predicted anchors follow the false instruction $94.5%$ of the time (true scene $2.3%$; $N{=}256$). Tested across three settings and a within-task ablation, our central claim characterizes the confound: instruction leakage occurs when the scored quantity is transcribable from the instruction (when the instruction names the answer) and is essentially independent of how predictive the non-instruction inputs are. Our tabletop and the external BabyAI benchmark leak, whereas a Language-Table forward-dynamics world model whose instruction names referents does not, until the instruction is augmented to name the direction; and degrading the action never increases leakage, the opposite of what predictor-competition predicts. The diagnosis prescribes the fix: keep the goal out of the dynamics (it belongs to the planner's cost) and supervise the read path, recovering genuine, instruction-independent grounding ($0.88$, identical with and without the goal). The detection protocol and remedy apply to any goal-conditioned world model whose instruction names the scored quantity.

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

Across robotics, World Models (WMs) are increasingly used to evaluate action policies by simulating the consequences of actions in an imagined world, and returning a success or safety verdict. Yet a verdict is only as trustworthy as the WM that produced it, and the WM itself needs to be certified. In video-generation WMs, fidelity metrics such as Fréchet Video Distance (FVD) reward visual realism, but ignore whether the world responds correctly to the policy's actions, including those unseen in training. Classical simulation-based validation assumes a trusted simulator evaluating an untrusted policy, whereas generative WMs are themselves unverified learned artifacts. Hence, we argue that any WM used as a test oracle must first be accredited before its verdicts can serve as evidence. Building on credibility practices from safety-critical simulation, including Verification, Validation & Accreditation (VV&A), Safety of the Intended Functionality (SOTIF), and scenario-based testing standards, we define an admissibility ladder (L0-L4) that a WM must climb before its closed-loop verdicts are accepted as assurance evidence. Our framework is embodiment-agnostic, and is instantiated in autonomous driving (AD), where assurance methods for traditional simulation are most mature. Applied to two driving WMs, the lower rungs reveal a reversal: the model that ranks higher on visual generation quality (L0) ranks lower on action-following (L1-L2), so visual fidelity does not predict the action-robustness a closed-loop verdict depends on.

Conversational image editing requires preserving not only visible content, but also content that temporarily disappears across turns. When newly added or modified content occludes a previously visible region, that region should reappear if it was never semantically changed. However, existing systems often fail to recover such occluded-but-unchanged content, producing inconsistent or hallucinated results. We introduce OCCUR-Bench, a diagnostic benchmark for temporal preservation in conversational image editing. OCCUR-Bench provides diverse occlusion-and-revelation scenarios with historical restoration references, enabling evaluation of faithful restoration rather than plausible regeneration. We also propose ReSpec, a training-free framework that makes implicit preservation explicit by pairing restoration-aware instructions with historical visual references. Given an editing history, ReSpec identifies what should persist, selects the historical image state that provides missing visual evidence, and conditions an in-context editor on the resulting instruction and reference image. Experiments show that ReSpec improves restoration fidelity and temporal consistency on OCCUR-Bench, highlighting the need to ground preservation in editing history rather than only the current image.

In text-to-image in-context learning (T2I-ICL), a model has to infer a latent compositional pattern from fewshot demonstrations for generating a query image. Recent studies show that state-of-the-art multimodal large language models struggle with this setting, particularly due to limited compositional reasoning and sensitivity to prompt construction. In this work, we propose a Tree-of-Thoughts (ToT) reasoning framework for T2I-ICL that introduces a multi-stage reasoning and selection layer that generates, evaluates, and selects among multiple candidate hypotheses before constructing the final prompt for image synthesis. By exploring alternative reasoning branches and selecting a coherent interpretation, the proposed approach mitigates prompt ambiguity and compositional errors. We implement the proposed approach in a complete ToT-T2IICL inference pipeline and evaluate it on the CoBSAT benchmark. Both qualitative and quantitative results show that structured multi-branch reasoning leads to more consistent and semantically aligned image generation compared to baseline and Chain-of-Thought prompting strategies, without any additional training or fine-tuning.

Subject-driven personalized text-to-image generation requires a pretrained diffusion model to acquire a specific subject from a few reference images while preserving subject identity, following novel text prompts, and maintaining sample diversity. Existing optimization-based methods instantiate subject adaptation through full fine-tuning, textual embedding optimization, or low-rank parameter updates; PaRa further constrains personalization from the perspective of parameter rank reduction. However, a uniform low-rank constraint or a uniform adapter strength cannot explicitly distinguish the capacity requirements of different denoising stages. Moreover, inference-time candidate selection driven mainly by identity similarity may compress the selected samples in the visual representation space. We decompose the problem into two complementary components: SPaRa denotes training-side stage-aware low-rank adaptation, DCAL denotes inference-side distribution-calibrated candidate selection, and SPaRa-DCAL denotes the combined framework. Theoretical analysis shows that timestep-dependent scaling controls the effective perturbation magnitude of a low-rank adapter, while identity-biased candidate selection restricts the radius of selected features around the reference center under explicit conditions. Auditable experiments under the SDXL and DreamBooth 30-subject protocol show that DCAL improves 1-LPIPS, CLIP-I, DINO-I, and CLIP-T on a fixed LoRA candidate pool, while revealing a clear trade-off with CLIP/DINO pairwise diversity and pairwise LPIPS. These results indicate that personalized generation should be evaluated through identity consistency, text alignment, and representation diversity rather than identity metrics alone.

Quantum diffusion models provide a physics-consistent route to generative learning by formulating noising and denoising directly on quantum states. However, applying such models to classical high-dimensional data is constrained by the qubit cost of state encoding and the computational burden of simulating large density operators. We propose a scalable hybrid generative pipeline that combines a classical autoencoder for dimensionality reduction with a mixed-state quantum denoising diffusion probabilistic model (MSQuDDPM) operating in the learned latent space. The autoencoder compresses data into compact latent codes that can be embedded into a small-qubit Hilbert space, after which the quantum diffusion model learns a generative distribution over latent density operators and decodes samples back to the original domain. Algorithmically, we simplify the reverse dynamics by predicting an estimate of the clean state $ρ_0$ at timestep $t$ and computing the one-step reverse update via an analytic backward propagation rule, rather than learning an explicit predictor for $ρ_{t-1}$. We demonstrate the proposed approach on MNIST image generation and discuss how mixed-state quantum diffusion can serve as a practical backbone for hybrid quantum--classical generative modeling under realistic qubit budgets.

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

Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited generality, programmability, and rendering speed. We address these limitations by introducing SPEAR: A Simulator for Photorealistic Embodied AI Research. At its core, SPEAR is a Python library that can connect to, and programmatically control, any Unreal Engine (UE) application via a modular plugin architecture. SPEAR exposes over 14K unique UE functions to Python, representing an order-of-magnitude increase in programmable functionality over existing UE-based simulators. Additionally, a single SPEAR instance can render 1920x1080 photorealistic beauty images directly into a user's NumPy array at 73 frames per second - an order of magnitude faster than existing UE plugins - while also providing ground truth image modalities that are not available in any existing UE-based simulator (e.g., a non-diffuse intrinsic image decomposition, material IDs, and physically based shading parameters). Finally, SPEAR introduces an expressive high-level programming model that enables users to specify complex graphs of UE work with arbitrary data dependencies among work items, and to execute these graphs deterministically within a single UE frame. We demonstrate the utility of SPEAR through a diverse collection of example applications: controlling multiple embodied agents with distinct action spaces (e.g., humans, cars, and robots) across several in-the-wild UE projects; rendering photorealistic city-scale environments; manipulating UE's procedural content generation systems; rendering synchronized multi-view images of detailed human faces; coordinating an interactive co-simulation with the MuJoCo physics simulator; and editing scenes with natural language via an AI coding assistant.

Vision Language Action (VLA) models unify visual perception, natural-language understanding, and action generation within a single foundation model, allowing a robot to follow instructions such as fold the towel or fly to the red building directly from camera images. Because VLAs inherit world knowledge from internet-scale pre-training, they have become the dominant framework for learning-based manipulation, with bimanual coordination serving as the most demanding testbed: two arms with 7 degrees of freedom each must move in concert to fold, assemble, and reorient objects. Unmanned aerial robotics faces a structurally similar challenge: a drone must coordinate thrust, attitude, and increasingly gripper commands from visual observations under strict latency and payload constraints. This review covers 183 contributions spanning 2017-2026 and organized along seven dimensions: VLA architectures, training recipes, action representations, bimanual coordination (2022-2026), unmanned aerial vehicle (UAV) navigation and control (2017-2026), language grounding, and cross-cutting concerns including memory and world models. We show that the coordination strategies, training recipes, and action representations developed for bimanual VLAs transfer to unmanned aerial systems and identify fourteen research directions across both domains.

Evaluating end-to-end autonomous driving (E2E-AD) remains challenging, as existing driving simulation methods often trade off closed-loop interactivity (e.g., CARLA) and real-world visual fidelity (e.g., nuScenes). We present \textbf{Point as Skeleton}, a generative sensor simulation framework for state-updated autoregressive driving video generation, in which an autoregressive generator synthesizes visual observations from step-wise updated ego states, actor states, scene maps, and point-cloud skeleton conditions. To support closed-loop rollout, we introduce Reset-and-Roll, which adapts rolling diffusion inference to simulation by preventing future-conditioned latent states from being committed across simulation steps. To stabilize error accumulation during step-wise autoregressive rollout, we introduce point-cloud skeletons that decouple foreground and background assets and project them into camera-view painted-point and template-depth conditions, providing appearance and geometric cues. We further implement a nuPlan-based renderer-level closed-loop generative interface for evaluating generation under ego deviations from the original log. Experiments on nuScenes and nuPlan show that Point as Skeleton improves autoregressive generation quality during closed-loop rollout, demonstrating its potential for visually faithful closed-loop driving simulation. The code is available at https://github.com/krauwu/point-as-skeleton.

Synthesizing physically plausible human-scene interactions (HSI) remains a critical challenge in computer vision and the development of human avatars. Although recent generative models enable diverse motion synthesis, they suffer from an inductive bias referred to as semantic-geometric entanglement. Because spatial constraints often strongly correlate with specific actions in training data, monolithic models will learn the shortcut bias, aggressively overriding the semantic intent when faced with strict geometric cues. Furthermore, this entanglement exacerbates physical hallucinations, such as body-scene penetrations. To address these limitations, we propose DeSeG, a hierarchical framework that explicitly decouples semantic intent from geometric constraints. First, we introduce a Residual Semantic Planner that encodes textual instructions and canonicalized goal voxels into a compact latent space, enabling fine-grained semantic control independent of spatial trajectories. Second, we propose a physics regularized diffusion executor that incorporates differentiable repulsive potential fields directly into the diffusion objective, enforcing collision-aware motion generation. Extensive experiments on the Lingo dataset demonstrate that DeSeG achieves state-of-the-art performance, reducing mean scene penetration by 47% and improving semantic alignment by 29% over the SOTA baselines.

Deepfake image detection is currently served by three fundamentally different paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors. Despite their widespread use, these paradigms are rarely evaluated under a common protocol, making direct comparison difficult. We introduce VendorBench-100, a cross-paradigm benchmark that evaluates 36 representative models using a single adversarial 100-image corpus, a unified output schema, and a common evaluation framework. To ensure reliable assessment under the corpus's intentional class imbalance, models are ranked primarily by the Matthews correlation coefficient (MCC), with ROC-AUC reported as a threshold-independent measure of ranking ability. Rather than maximizing dataset size, VendorBench-100 emphasizes challenging real-world scenarios through a curated taxonomy of eight edge-case families, including face swaps, text-to-video stills, AI photo edits, avatar compositing, opaque-provenance images, and compressed research frames. Our evaluation shows that commercial APIs achieve the strongest median performance, followed by vision LLMs and open-source detectors. However, individual open-source models remain competitive with the best vision LLMs. More importantly, we identify a consistent divergence between ranking ability (ROC-AUC) and operating-point quality (MCC), demonstrating that strong score discrimination does not necessarily produce reliable default-threshold decisions. This metric disagreement, rather than any single leaderboard ranking, is the central finding of the benchmark. We release the complete evaluation framework and benchmark results to support reproducible future research. The source code and data are available at: https://github.com/sharayu-20/vendorbench-100

While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit end-to-end generation paradigms, resulting in coarse-grained control. In scenarios demanding precise stylistic interventions and strict temporal alignment, such as audiobook narration and video dubbing, the inability to explicitly manipulate word-level acoustic attributes remains a critical bottleneck. This limitation is primarily amplified by the severe scarcity of fine-grained annotated datasets and the architectural challenge of integrating multi-dimensional control signals into discrete autoregressive generation. To address this, we propose a unified framework for highly precise word-level control. First, we construct WordVoice-5A, a massive 4.7k-hour bilingual dataset featuring five-dimensional word-level annotations (duration, boundary, energy, pitch and tone) developed through a rigorous linguistically-guided pipeline. Second, we introduce WordVoice to transform the implicit generation process into an explicit, highly controllable paradigm. Specifically, we introduce a bound-token mechanism within the LLM to formulate an explicit ``acoustic planning'' process, enabling adaptive multi-task prosodic planning and flexible manual intervention. Furthermore, we augment the token-to-waveform stage with a fine-grained acoustic modulation module, bridging the resolution gap to strictly align word-level attributes between highly compressed discrete tokens and continuous waveforms. Extensive experiments demonstrate that WordVoice achieves superior, decoupled control over multiple acoustic dimensions while maintaining competitive zero-shot synthesis stability. The code and audio samples are publicly available at https://xxh333.github.io/wordvoice-demo/.

Game worlds have traditionally been built through labor-intensive production pipelines, making them costly to develop, difficult to customization, and expensive to modify after deployment. Recent advances in video world models offer a fundamentally different paradigm. Rather than explicitly authoring every component of a virtual environment, these models autoregressively synthesize future observations conditioned on the current world state and user interactions, enabling playable worlds to be generated online. Trained on both gameplay recordings and real-world videos, they can capture diverse visual appearances and physical dynamics, opening new opportunities for interactive applications beyond gaming, including embodied intelligence. In this paper, we present AlayaWorld, a full-stack open-source framework for building interactive generative worlds. AlayaWorld enables open-ended real-time interaction, allowing users to freely navigate and perform diverse actions such as combat, spell casting, and monster summoning. The framework unifies the complete development-from data preparation model architecture, model training, inference acceleration, and deployment-within a modular and extensible architecture. Alongside the framework, we release reproducible pipelines, reference implementations, evaluation tools, and comprehensive documentation, establishing a practical foundation for future research and real-time applications of generative world models.

Video-to-audio (V2A) generation aims to synthesize realistic audio that is both semantically consistent with and temporally synchronized to a silent video. Despite recent progress, many methods still rely on multi-stage training, resulting in high computational costs and long runtimes, or transform visual input into text to leverage pretrained text-to-audio models, sacrificing fine-grained temporal cues. To overcome these limitations, we propose Flowley, an end-to-end, single-stage training architecture that produces soundtracks by combining visual features with textual prompts. Crucially, we introduce Progressive Soft-masked Cross-Attention, which embeds audio-visual synchronization directly within its attention mechanism, adding zero additional computational cost compared to standard attention layers. We further observe that existing V2A benchmarks lack sound-oriented descriptive captions, which can potentially degrade the quality of the synthesized audio. To remedy this, we propose SoundCap, a plug-and-play pipeline for creating detailed, sound-aware captions that guide the model. Remarkably, without integrating any pretrained audio-visual alignment modules, Flowley achieves state-of-the-art performance on VGGSound across multiple metrics. Moreover, by incorporating SoundCap, we further exceed the performance of the strongest existing close-sourced methods in terms of audio quality in the zero-shot setting.

Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training. Existing methods often remove the target concept effectively, but practical unlearning also requires an equally fundamental property: the unlearned model should retain quality, diversity, and semantic coverage on benign generation. The gold standard is a retain-only model trained from scratch without the unwanted data. However, common erasure objectives do not specify which post-unlearning distribution should approximate this reference, leaving retention as an implicit consequence of the update rule. We propose TILDE, TILt-based Distributional Erasure, which formulates concept unlearning as a distributional alignment problem: the desired target is the minimum-deviation conditional distribution from the pretrained model under a forgetting constraint. This energy-tilted, anchor-free target suppresses concept-expressing images while preserving benign relative mass for each prompt. We instantiate this principle with residual $\nabla$-GFlowNet training, which learns the score correction induced by the forget energy relative to the pretrained diffusion model. Across objects, artistic styles, and characters, TILDE achieves strong forgetting while improving retention and distributional fidelity over prior baselines.

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

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.

Robotic manipulation in the open world requires not only recognizing what a scene looks like, but also anticipating how its 3D structure moves under interaction. We argue that synchronized RGB, depth, and optical flow, namely RGB-DF, provide a physically grounded representation that captures the underlying 4D dynamics of a scene. Compared to 2D pixel videos, this multi-modal synergy aligns visual appearance with geometric structure and temporal motion, creating a representation space significantly closer to the low-level end-effector actions demanded by robotic systems, thereby narrowing the gap between world prediction and policy learning. Building on this insight, we introduce RynnWorld-4D, a generative model that co-produces future RGB frames, depth maps, and optical flow from a single RGB-D image and a language instruction within one unified diffusion process. This 4D world model features a tri-branch architecture that integrates cross-modal attention with frame-wise 3D RoPE, ensuring that appearance, geometry, and motion evolve consistently. To supply training data at scale, we curate Rynn4DDataset 1.0, a massive dataset of over 254.4 million frames across egocentric human and robotic manipulation videos with high-quality pseudo-labels for depth and optical flow. We further propose RynnWorld-4D-Policy, an inverse dynamics head that consumes the internal 4D representations of RynnWorld-4D in a single forward pass, bypassing expensive multi-step denoising, to output robot actions in a closed-loop manner. Experiments show that RynnWorld-4D produces temporally and spatially coherent 4D predictions, and that RynnWorld-4D-Policy achieves state-of-the-art performance on real-world dexterous bimanual manipulation tasks, particularly excelling in tasks demanding spatial precision and temporal coordination.

Human-Object Interaction (HOI) video generation aims to synthesize realistic videos of humans manipulating diverse objects, serving as a promising avenue for AI-driven live streaming e-commerce. A primary obstacle in this domain lies in the complexity of modeling fine-grained physical dynamics and the intricate spatial-temporal coordination between human hands and objects. Existing approaches to this problem typically rely on dense temporal guidance, e.g., frame-wise hand-object pose sequences, to strictly control the interaction process. However, such dense guidance incurs high annotation costs and affects motion synthesis diversity. To overcome these limitations, we introduce SparseCtrl-HOI, a novel sparse temporal control framework for HOI video generation. It requires only a few keyframes that capture interaction states at designated timestamps. Specifically, we employ a Time-Controlled Rotary Positional Embedding (TiRoPE) mechanism to temporally anchor these keyframes while preserving their spatial integrity. Subsequently, to govern the dynamics across intermediate frames, we propose a Motion Prior Injection Module that leverages Multimodal Large Language Models (MLLMs) to extract high-level motion priors. This empowers the model to hallucinate logically and physically plausible transitions. Furthermore, we build SparseHOI-5K, a high-quality and richly annotated dataset for HOI video generation with sparse temporal control. Comprehensive evaluations confirm that our method substantially reduces annotation overhead while synthesizing superior live-streaming e-commerce videos. Both our code and dataset are publicly available at https://mpi-lab.github.io/SparseCtrl-HOI.