每天知道
你的领域
出了什么

Recently, AI-driven video generation has attracted considerable attention. This surge increases the demand for reliable video quality assessment (VQA) metrics to evaluate AI-generated content (AIGC) videos and guide model optimization. Existing studies assess video quality through visual harmony, video-text consistency, and domain-specific alignment, yet lack quantitative metrics for measuring fidelity to physical laws. To address this limitation, we present a novel benchmark that evaluates the quality of AIGC videos based on their compliance with physical principles by quantitatively measuring geometric consistency across frames extracted from generated sequences. This serves as a proxy for estimating the extent to which generated videos conform to real-world physical rules. Specifically, GeoCon-Bench captures global motion through translation estimation, fits homography or fundamental matrix models using background correspondences, and reports complementary metrics, including inlier ratio and geometric error. We also release a dataset containing 20 scenes across six motion categories. Experiments on state-of-the-art AIGC models demonstrate the reliability of GeoCon-Bench as a video quality assessment metric.

Text-to-music generation has advanced rapidly, but current systems still rely primarily on global text prompts, leaving the structural organization of generated music implicit and difficult to inspect, control, or revise before audio generation. To address this issue, we introduce MusicLayout, an explicit intermediate representation for controlling musical structure in text-to-music generation. MusicLayout describes a musical piece as a time-aligned layout of sections, textures, repetitions, variations, and instrument-level arrangements, serving as an interpretable planning layer between textual intent and the generated music. We integrate MusicLayout into a text-to-music framework built on a unified autoregressive formulation, where the model first generates a MusicLayout representation and subsequently predicts audio tokens conditioned on this representation within a single sequence. The resulting MusicLayout can be inspected and modified prior to audio generation, providing a mechanism for layout-level structural control. We evaluate MusicLayout through layout-conditioned generation, layout manipulation experiments, and matched-data ablations, providing evidence that explicit layout planning can improve long-range structural organization and support layout-level control.

Image-goal navigation with latent world models requires not only accurate future prediction, but also a planning cost that reliably ranks candidate action sequences. We define the cost as the cosine distance between the predicted future embedding and the goal embedding, and show that poor cost ordering can mislead sampling-based planners such as Cross-Entropy Method (CEM). To address this, we propose a latent world model built on a frozen DINO-family encoder and train it with two complementary objectives. An autoregressive rollout loss reduces the gap between training and multi-step planning rollouts, while a Monotone Cost Ranking (MCR) loss directly encourages increasingly perturbed action sequences to receive higher planning costs. We also study InfoNCE-based action-contrastive training and find that temporal permutation negatives distort the latent geometry and degrade planning performance. On the GNM navigation dataset, our method outperforms Navigation World Models (NWM), DINO-WM, OmniVLA, and NoMaD, achieving state-of-the-art image-goal navigation performance while reducing orientation error by $2.7\times$ over the same-encoder DINO WM baseline. We also deploy the model zero-shot on a physical robot, where it follows goal-directed paths in unseen indoor and outdoor environments.

Reconstructing 3D shapes from a single image remains a fundamental yet challenging problem in computer vision. Traditional monocular 3D generation pipelines typically synthesize multiple views from a single input image before applying Neural Radiance Field (NeRF)-based reconstruction. However, inherent projective ambiguities often produce visual discontinuities across generated viewpoints, leading to inaccuracies in reconstructed 3D models. Current solutions either incur significant additional computational burdens or fail to adequately resolve practical inconsistencies between synthesized views. To address these limitations, we propose a novel viewpoint-adaptive neural rendering framework that enables robust 3D reconstruction even when given partially inconsistent multi-view inputs. Our approach introduces view-adaptive neural renderers that independently correct viewpoint-dependent errors while simultaneously sharing a global feature backbone to preserve structural coherence. Furthermore, we propose a self-attention fusion module that adaptively integrates multi-view information, ensuring geometric consistency without relying heavily on indirect regularizations or computationally intensive methods. Through extensive experiments, we demonstrate that our method consistently improves 3D reconstruction fidelity. Importantly, our approach achieves near state-of-the-art performance without diffusion-based SDS supervision, relying primarily on photometric rendering loss with lightweight attention regularizers. This balance between accuracy and efficiency makes the proposed framework highly practical for real-world applications.

Electrical circuit analysis requires more than recognizing components in an image. A solver must ground symbols and labels, recover latent topology, select a physical model, formulate coupled equations, propagate intermediate quantities, and preserve units, signs, directions, and phase conventions. We introduce \benchmark, a benchmark of 1,000 authentic textbook problems for evaluating this complete long-horizon visual-to-symbolic reasoning process. Each problem pairs one or more circuit diagrams with a self-contained question, a typed or semantically specified answer, and a reference worked solution. An evidence-first construction pipeline aligns questions, figures, and solutions, while a reasoning-oriented taxonomy organizes problems by circuit type and dependency depth. Evaluation combines conservative typed scoring with identity-blinded multi-model semantic consensus, retaining every problem in the denominator. Across three commercial chatbot systems and six open-source multimodal large language models, the highest-scoring system reaches 84.8% accuracy. However, performance consistently deteriorates on long-horizon problems, and qualitative analysis exposes persistent failures in topology-to-target binding, physical conventions, and late-stage output propagation. \benchmark{} provides a focused testbed for measuring whether multimodal models can transform technical visual evidence into sustained, physically valid symbolic reasoning. Code are available at GitHub - CircuitReason/CircuitReason1K.

Magnetic field strength is a major source of domain shift in magnetic resonance imaging (MRI), affecting signal-to-noise ratio, tissue contrast, spatial detail, and the visibility of anatomical boundaries. The MRIxFields 2026 challenge investigates this problem through cross-field MRI translation across acquisitions at 0.1T, 1.5T, 3T, 5T, and 7T. Its three tasks, Any-to-7T, 0.1T-to-High, and Any-to-Any synthesis, require the generation of target-field image characteristics while preserving subject-specific anatomy. This problem is particularly challenging because paired acquisitions of the same subject across multiple field strengths are rarely available for training. We propose a 3D unpaired cross-field MRI translation framework based on field-conditioned content-style pretraining. The proposed framework first learns controllable field-to-field translation across all available field strengths by disentangling anatomical content from field-dependent contrast characteristics. The pretrained backbone is then adapted to task-specific target domains. Our model comprises a 3D content encoder, a 3D style encoder, a field-conditioned style generator, an AdaIN-modulated decoder, and a multi-field discriminator. Adversarial learning encourages realistic target-field appearance, while cycle-consistency, identity, content, style, and diversity constraints promote anatomical fidelity and controllable translation. We evaluate the proposed method on MRIxFields data spanning five field strengths and three MRI modalities. Experiments on paired test data demonstrate that the framework can adapt to the three challenge settings while preserving three-dimensional anatomical structure in the synthesized volumes. The implementation code is publicly available at https://github.com/Idea89560041/3D-MRI-Field-Translation.

Audio Description (AD) is a verbal narration of key visual content in videos, enabling access for visually impaired audiences. Unlike standard video captioning, AD is a structured editorial task: descriptions must be inserted into gaps in dialogue and must convey only what is needed to understand the narrative being told. However, existing approaches formulate AD generation in an artificial setting where both the content and timing of descriptions are pre-specified, reducing the task to clip-level captioning. They further rely on noisy transcription and alignment pipelines, and lack the rich parallel data required for modeling narrative context. We introduce a new formulation of AD generation in which models must jointly decide what to describe and when to do it. To support this, we present REFRAMED, a high-quality dataset of 2,023 videos that span 3,302 scenes from 206 movies, with professional AD transcripts (both American and British versions), professional subtitles and aligned screenplays. We also provide a manually curated challenge set that pairs full movies with multiple AD references, together with evaluation protocols that leverage dialogue gaps and multi-reference comparisons. Experiments with state-of-the-art AD systems and multimodal LLMs show that they outperform trivial baselines but fall far short of expert human performance. Our dataset and benchmark establish a new foundation for research on video understanding.

Vision-language-action policies rely on large multimodal backbones to jointly perform perception, language conditioning, and action generation at every control step. Much of this capacity supports open-domain semantics, whereas continuous robot manipulation primarily requires compact representations of observations, actions, and the transitions induced by actions. Pixel-level world models provide another route, but predicting visual details irrelevant to control can be unnecessarily expensive. We propose SLIM (Self-supervised Latent Interaction Model), a compact 0.5B-parameter latent interaction policy. SLIM learns action-grounded predictive latents that capture both action-conditioned future transitions and the actions that explain observed changes. SLIM learns these representations through self-supervised masked trajectory prediction, combining action reconstruction with future-latent prediction. A compact Mixture-of-Transformers (MoT) backbone models interactions between observation latents and action tokens. The resulting policy is trained with flow matching for language-conditioned action generation. Across simulation benchmarks and real-world evaluation, SLIM matches or exceeds representative large-scale VLA and world-action-model baselines with fewer parameters, no additional embodied pretraining, lower inference latency, and substantially lower GPU memory usage.

Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling. Based on this insight, we propose REST (Reward-Enhanced Scored-Trajectory Distillation), a single-stage RL-distillation co-training framework that attaches a decoupled student to an arbitrary RL teacher. The student learns segment-wise from the teacher's evolving rollout trajectories while leaving the original teacher optimization unchanged. To prevent uniform imitation from preserving undesirable low-reward behaviors, we further introduce Advantage-Modulated Distillation (AMD), which transforms rollout advantages into signed weights over a base distillation loss. AMD strengthens supervision from preferred trajectories and mildly repels the student from low-reward ones. The resulting framework is lightweight and plug-and-play, requires no extra image rollouts, no separate distillation dataset, and no adversarial training. Experiments on compositional generation, visual text rendering, and human-preference alignment show that REST enables few-step CFG-free inference that matches or surpasses its 40-step RL teacher, with an overall additional training cost below 25% over pure RL. REST improves DrawBench PickScore over RTDMD by 0.82 while requiring only one-fifth of the training iterations.

Recent advances in speech synthesis and audio generation have made high-fidelity acoustic forgery low-cost and difficult to attribute, enabling a realistic attack scenario in which speech and background audio are independently manipulated over otherwise authentic video. Yet existing research either focuses on visual manipulation, addresses speech detection in isolation, or conflates speech and non-speech audio as a single undifferentiated audio stream, overlooking the distinct forensic challenges posed by background audio. This conflation is consequential: the two acoustic components arise from fundamentally different generative mechanisms, exhibit distinct artifact profiles, and pose different challenges to detection systems. We introduce MADBench, the first benchmark that treats speech and environmental audio as distinct acoustic components, enabling component-aware evaluation of audio deepfake detection across independently manipulated forgery sources. We benchmark representative state-of-the-art detectors and multimodal large language models under a unified protocol. Our experiments reveal that environmental audio manipulation is more detectable than synthetic speech across general-purpose encoders, while existing pretrained detectors fail on both acoustic components, and manipulated environmental audio asymmetrically degrades speech deepfake detection, findings entirely invisible under the single-label paradigm of prior benchmarks. MADBench establishes a rigorous foundation for future research into robust, component-aware audio deepfake detection.

Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployment cost. Existing latent WAMs avoid explicit future generation, but often compress predictive representations or separate predictive modeling from the representations used for action generation. We introduce JEPA-WAM, a latent WAM built in a pretrained V-JEPA space, which couples latent transition prediction with continuous action generation through a shared predictor. JEPA-WAM predicts a spatially structured joint current-future target that captures task-shared visual temporal structure between current and future observations, while preserving dense patch-level correspondence. Through the shared predictor, transition supervision directly shapes the backbone, from which dedicated representations are extracted for action prediction. The same design can also be instantiated in pretrained VLA policies while preserving their original perception and action pathways. On LIBERO-Plus, JEPA-WAM achieves 79.2%, the best result without large-scale robot-policy pretraining, while its pretrained $π_{0.5}$ instantiation reaches 86.3%, achieving the best overall performance. Experiments on RoboTwin 2.0 and real-world bimanual manipulation further demonstrate strong generalization under visual and spatial shifts.

Image super-resolution (SR) with large generative models has recently achieved remarkable perceptual quality, yet maintaining fidelity to the LR observation remains challenging. In particular, we observe that diffusion transformers (DiTs) built on latent representations suffer from a critical limitation: the compression bottleneck of the VAE weakens fine-grained spatial information, leading to hallucinated details that are weakly grounded in the input image. In this work, we revisit generative SR from a representation perspective and propose a pixel-grounded super-resolution (PGSR) framework that preserves LR-observed pixel evidence before VAE compression and reuses it throughout restoration. Instead of relying solely on the compressed latent condition, PGSR extracts pre-VAE pixel evidence from the upsampled LR image and reuses it at two stages. First, Condition-Side Trajectory Guidance fuses LR-derived pixel evidence with the latent LR condition to guide the latent restoration trajectory. Second, Decoder-Side Pixel Grounding injects multi-scale pixel features into the frozen VAE decoder to ground the final rendering with LR-observed cues. To efficiently adapt large pretrained DiT models, we keep the latent autoencoder and main flow-matching backbone frozen, and train only lightweight restoration modules. We further study an efficient local-window attention variant for improved high-resolution efficiency and scalability. Extensive experiments demonstrate that PGSR improves the realism--fidelity trade-off and produces more faithful, visually convincing results than existing latent generative SR approaches.

As an important subfield of cross-modal generation, synthesizing static visual content in the form of images from audio, namely audio-to-image (A2I) generation, has attracted increasing research attention in recent years. Nevertheless, despite the remarkable visual quality of modern text-to-image (T2I) models, the performance of A2I remains fundamentally limited by traditional datasets, which often lack both high-fidelity images and precise cross-modal alignment. As a result, existing methods still struggle to achieve high-quality audio-to-image generation through finetuning strong T2I models, thereby constraining practical applications in this area. Motivated by this gap, we introduce A2I-Set, a unified, high-quality tri-modal dataset consisting of 323K paired audio, images, and detailed text captions, specifically designed for audio-visual research, including audio-conditioned image generation. Besides, we developed a new mixed-source test set for the A2I task through human supervision. We further propose an A2I model, AudioCanvas, fine-tuned on our A2I-Set. Experiments show that AudioCanvas achieves more visually expressive as well as cross-modal alignment results that generally outperforming existing approaches. Our dataset and source code are available at https://github.com/gdx012/A2I-Generation.

Interactive video world models generate rollouts autoregressively under an action stream, yet they are trained and evaluated almost exclusively on factual prediction. We study counterfactual generation inside the rollout: given a trajectory the model has itself generated, what would have happened had the actions differed from step t* onward? We formalize noise-coupled twin rollouts --- a factual and a counterfactual branch sharing the generated prefix and the future exogenous noise sequence, diverging only in the action stream at an intervention point. Because the factual branch is self-generated, its exogenous noise is known exactly: the abduction step of Pearl's counterfactual procedure is exact by construction, sidestepping the approximate-inversion problem faced by editing-based pipelines. Noise coupling further turns the minimal-change principle into a per-sample verifiable property: we define a spatiotemporal locality metric that penalizes divergence outside the causal descendants of the intervention, computable against simulator ground truth without a learned judge. Forking the simulator state at t* yields ground-truth counterfactual re-renders, which we use as verifiable rewards for post-training. This note establishes the formal framework, metric definitions, and positioning; experiments are forthcoming.

Next-scale visual autoregressive models (VARs) have emerged as a powerful generative paradigm, producing high-quality images through efficient coarse-to-fine prediction. However, their potential for text-guided image editing remains largely underexplored. Existing training-free VAR editing approaches often formulate editing as target-conditioned regeneration guided or constrained by the source image, and may rely on inversion, test-time optimization, attention control, or user-provided masks. This generation-centric formulation does not fully exploit the multiscale source representations provided by VARs and may introduce additional computation or intervention. We instead take a source-centric perspective on VAR editing, in which the encoded source image tokens serve as the primary visual state and the editing process focuses on condition-induced changes. Based on this perspective, we propose EditMod, which compares source- and target-conditioned predictions under a shared autoregressive context, treats their difference as a scale-wise editing direction, and applies it as a residual update to source tokens at selected scales. Experiments show that EditMod achieves leading source-image fidelity while maintaining strong text alignment, and completes end-to-end editing of a 1K image in only 1.57 seconds on a single A100 GPU without per-image preparation.

Video coding is advancing into the low and ultra-low bitrate regime, driven by end-to-end codecs that replace the hand-crafted pipeline with jointly optimized neural networks and generative codecs that exploit the priors of video generation models. Yet the dominant metrics, LPIPS and DISTS, measure feature and texture similarity rather than content fidelity: a reconstruction that hallucinates a wrong face or blurs text into convincing strokes can still score well, even when a human rejects it instantly. To address this, we propose CodecArena, the first vision-language framework for video coding quality assessment, casting codec evaluation as source-conditioned comparative reasoning between a reference and its reconstructions. We optimize CodecArena with Facet-GRPO, a visual reinforcement learning scheme that aligns pairwise codec preferences while grounding the verdict in five fidelity facets: identity, objects, text, texture, and temporal consistency. Its facet-anchored reward uses automatically derived facet directions as weak anchors, rather than human per-facet labels, to prevent any single sub-score from dominating the holistic preference and to yield interpretable fine-grained quality judgments. To support training and evaluation in this underexplored regime, we construct two complementary resources: CodecArena-1K, a fully automatic preference dataset of 1,500 comparison groups built from traditional, neural, and generative codec reconstructions with fused vision-language and objective supervision; and CodecArena-Bench, a human-ranked benchmark with source-disjoint videos for fair out-of-domain evaluation. Extensive experiments demonstrate that CodecArena achieves state-of-the-art agreement with human judgments on source-disjoint content across diverse codecs and bitrates, surpassing perceptual metrics and prior vision-language evaluators.

Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicitly model how physical scenes evolve as a task unfolds. Recently emerging world-action models (WAMs) leverage pretrained video world models to capture spatiotemporal evolution, yet retaining future generation or a large video backbone in the control loop substantially increases inference cost. We introduce World Tokens, an embodied policy architecture built around a World Adapter that bridges visual-language understanding, world-dynamics modeling, and action generation. It uses world modeling during training to enhance the action policy while preserving efficient deployment. Specifically, the World Adapter transforms VLM features into a fixed set of world tokens, which condition a jointly fine-tuned future-video denoiser and simultaneously serve as the action expert's sole visual-language context. This shared conditioning allows gradients from future-video denoising to directly shape the representation used for action prediction, while exclusive routing prevents the policy from bypassing that representation. At deployment, the world-model branch is removed, leaving only the VLM, World Adapter, and action expert, with no online video-model inference. With a 2B backbone and no embodied action pretraining, World Tokens is highly competitive on LIBERO, attains the best reported averages on SIMPLER, substantially improves real-world R1 Pro success over a matched action-only baseline, and generates each action chunk at VLA-level latency.

Despite rapid advances in generative models, achieving pixel-level precision in sketch-based image editing remains a persistent challenge, particularly for fine-grained local deformations. This gap stems primarily from the critical shortage of high-quality, publicly available benchmark datasets that jointly provide geometric constraints and semantic instructions. To address this issue, we first introduce **SI-Data**, a high-quality dataset specifically designed for instruction-guided local sketch editing. We develop an automated pipeline leveraging Multimodal Large Language Models (MLLMs) to synthesize comprehensive quadruplets comprising original images, local geometric sketches, semantic instructions, and corresponding edited images. By providing both reliable spatial anchors and explicit semantic intent, SI-Data uniquely enables collaborative spatial-semantic learning. Building upon this, we propose a collaborative framework called **SI-Edit** that integrates semantic instructions with precise geometric constraints. Furthermore, to address the lack of standardized evaluation, we establish a comprehensive set of metrics designed to measure both structural fidelity (e.g., sketch-to-edge alignment) and semantic adherence. Experimental results demonstrate that SI-Edit provides more reliable structural control than baselines for sketch-based image editing, and achieves precise, pixel-level local refinements aligned with user intent. The data and code are released on the [project page](https://github.com/ywxsuperstar/SIEdit).

Diffusion transformer (DiT), a rapidly emerging architecture for image generation, has gained much attention. However, despite ongoing efforts to improve its performance, the understanding of DiT remains superficial. In this work, we delve into and investigate a critical conditioning mechanism within DiT, adaLN-Zero, which achieves superior performance compared to adaLN. Our work studies three potential elements driving this performance, including an SE-like structure, zero-initialization, and a "gradual" update order, among which zero-initialization is proved to be the most influential. Building on this understanding, we propose an analysis-guided initialization strategy, termed adaLN-Gaussian, which serves both as an empirical validation of our analysis and as a practical initialization method that consistently improves optimization efficiency. On the other hand, inspired by the SE-like structure, we introduce an improved conditioning mechanism called SE-adaLN-Zero. Extensive experiments following DiT on four datasets, especially on ImageNet1K demonstrate the effectiveness and generalization of adaLN-Gaussian and SE-adaLN-Zero. Beyond class-to-image generation, we also evaluate the generalization of the two improved methods on text-to-image generation.

RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in gaming industry. However, generating high-quality RGBA animations for games remains challenging for two reasons. First, most existing RGBA video datasets are dominated by photorealistic content, with limited coverage of game assets. Second, the traditional generate-then-matte pipelines estimate alpha only after RGB synthesis, so semi-transparent regions are often blurred by background, resulting in unstable matting outputs. More recently, many methods have begun to model RGB and alpha jointly, but existing approaches are mostly text-conditioned, and still have unresolved issues in efficiency and quality. To address these challenges, we introduce GameAlpha-2.4K, a 2.4K-clip game-style RGBA video dataset built with matte-friendly synthesis, multi-hypothesis alpha recovery, and compositing-based quality gates. Using this dataset, we train a reference-conditioned RGBA video generator that jointly produces RGB frames and alpha mattes in a single pass. To improve efficiency, we propose a visibility router that identifies transparent tokens in an early stage and bypasses their later DiT updates, while x_0-lock guides them along the original flow-matching schedule toward self-predicted endpoints. Our model obtains lower FVD than traditional two-stage pipelines, and the visibility router skips 35% of token evaluations in the final two DiT denoising steps, providing a 1.2x backbone speedup with negligible quality degradation compared to dense inference.

AI video generation has advanced rapidly and entered widespread commercial use. As a result, quality differences among videos produced by state-of-the-art AI video generation models~(AIVGMs) have become increasingly difficult to discern using conventional evaluation criteria, such as visual fidelity and semantic instruction following. Meanwhile, human evaluation now requires more expertise and sustained attention, substantially increasing annotation costs. This calls for automated evaluation that can reliably distinguish fine-grained differences among advanced AIVGMs with minimal human intervention. To address this challenge, we present RAVEN-Eval, a rubric-guided automated evaluation framework for AIVGMs, built primarily on the LMM-as-a-judge paradigm. Through an automatic task curation and quality-filtering pipeline, RAVEN-Eval curates 150 text-to-video~(T2V) tasks and 100 image-to-video~(I2V) tasks, and systematically collects more than 4,500 AIGVs. At its core, RAVEN-Eval adopts rubric-guided automated LMM preference judgement, in which LMM judges conduct pairwise comparisons according to task-specific rubrics. It further introduces an anchor-based model insertion approach to reduce the evaluation cost of incorporating new models. Finally, we evaluate 20 high-performance AIVGMs, as well as the judging capabilities of 13 LMM judges, and establish the RAVEN-Eval Leaderboards. Overall, RAVEN-Eval paves a scalable path for automatic and trustworthy evaluation of rapidly evolving AIVGMs.

Video world models must capture how scenes evolve over time and across viewpoints. Training them for long-horizon generation and camera control therefore benefits from long videos paired with camera trajectories and temporally grounded semantics. Existing corpora rarely offer the three together: large-scale web video provides broad visual diversity but no trajectories or time-aligned text, while pose-annotated datasets are typically short-range or reconstruction-oriented. We introduce Sekai2, a multi-source real-world video dataset that carries the world-exploration footage of Sekai toward interactive world modeling. The release contains 128,892 clips totaling 2,826 hours from 10,428 source videos across 113 countries or regions, and is deliberately weighted toward sustained observation: under a common 120-second decomposition, 43,594 segments reach the full two minutes and account for 51.4% of all footage. Every clip includes a released camera trajectory and hierarchical annotations disentangling subject motion, environment dynamics, static scene content, and camera behavior, resulting in 649,597 temporally grounded segments. Crucially, we further introduce 982 panoramic sequences captured along non-linear trajectories with loops and revisits. These revisits provide repeated observations of the same locations across time and viewpoints, offering essential supervision for learning persistent scene representations, long-term spatial memory, and geometrically consistent world models. Corpus-scale analyses demonstrate complete pose-and-caption coverage, broad geographic and semantic diversity, varied camera trajectories, and highly non-redundant temporal descriptions. Together, these properties make Sekai2 a scalable resource for long-horizon video generation, camera-controllable synthesis, and interactive world-model pre-training.

Text-to-image diffusion models have achieved remarkable success in generating high-quality images from a given text prompt. Subject-driven generation aims to synthesize customized images to mimic the appearance of subjects in given reference images within different visual contexts specified by the text prompts. The central challenge here is that, when the reference image changes, the diffusion model cannot efficiently adapt to different visual contexts while consistently maintaining the subject identity. Existing methods either train the model with a large domain-specific dataset or fine-tune the model using the reference image for hundreds of iterations before actual image generation. In this work, we explore a new approach, called In-Loop Model Adaptation (IMA), which adapts the core diffusion model at each generation step during the actual process of image generation, without being trained on the reference image before the generation process. To this end, we establish a DDIM inversion chain that maps the reference image to a sequence of latent, as well as a text-to-image generation chain which generates the image from the text prompt only. We then introduce a masked latent consistency loss and a noise regularization loss to characterize the latent-noise difference between the diffusion model and these two chains at each generation step. This coupled latent-noise loss is used to guide the in-loop model adaptation to preserve the subject identity specified by the reference image while maintaining accurate alignment with the text prompt, resulting in high-fidelity text-to-image generation. Our extensive experiments demonstrate that our proposed IMA method significantly improves the performance of subject-driven text-to-image generation.

Unconditional diffusion checkpoint merging assumes benign sources, yet a compromised public checkpoint can transfer a dormant backdoor while clean generation appears normal. Mitigation is difficult without knowing the compromised source, trigger, or target, and broad sanitization may degrade image quality. We introduce DiffSafeMerge (DSM), which uses a small unlabeled clean set and fixed, attack-agnostic stress probes to score source blocks, shrink suspicious contributions toward a trusted reference, and select attenuation under a clean denoising-loss budget. We evaluate four attacks, two datasets, and 21 target conditions. Intended merging already has zero worst-target ASR in 10 of 14 source cases; DSM preserves these outcomes and records no target match in the remaining four over three seeds, including three with baseline ASR of 48--100%. Among methods with zero worst-target ASR on both datasets, DSM obtains the lowest case-averaged FID in the matched seed-0 comparison.

Diffusion models have enabled high-quality video generation in recent years, but the high cost of iterative sampling hinders their practical deployment. Few-step distillation alleviates this cost, yet exposes a quality--diversity trade-off between its two dominant paradigms: trajectory-level distillation (e.g., sCM) favors diversity, whereas distribution-level distillation (e.g., DMD) favors quality. Targeting extreme two-step video generation, we introduce DUET, which reconciles the two paradigms through a noise-level duet of experts: an sCM expert takes the high-noise step to lay out diverse structure, and a DMD expert takes the low-noise step to refine appearance detail. Since the two experts are trained independently with their native objectives, DUET sidesteps the optimization difficulties of loss-level combinations and delivers quality and diversity jointly rather than trading one for the other. We further identify the relay interface and the high-noise stage as the remaining bottlenecks, and address them with RL-guided expert adaptation, yielding DUET+. With the Wan2.1-T2V-1.3B backbone, DUET lifts the two-step quality of sCM close to the level of DMD while retaining nearly all of its structural diversity---about twice that of DMD---and DUET+ further improves overall quality while preserving this diversity advantage. Together, these results establish noise-level expert specialization as a simple, effective paradigm for reconciling diversity and quality in two-step video generation.

Instruction-driven editing of 3D human motion requires precise spatiotemporal localization, rich semantic grounding, and strict preservation of unmodified content. Existing methods either resort to training-free adaptation of generative models or rely solely on triplet supervision; however, adaptation often yields suboptimal control, and manually curated triplet datasets remain severely limited in scale and semantic diversity. To overcome this bottleneck, we ground motion editing directly within text-to-motion generation across data, architecture, and inference. At the data level, we develop a closed-loop synthesis-and-verification pipeline that produces Omni-MoEdit, a large-scale dataset spanning body-part, amplitude, temporal, action, and style edits. At the architectural level, we introduce UniMoFlow, a unified latent flow-matching model that shares broad semantic and kinematic knowledge between generation and editing. At the inference level, SAFE (Source-Anchored Flow Editing) complements UniMoFlow with controllable, source-anchored refinement. Furthermore, we augment standard evaluations with semantics-aware metrics to account for valid edits that inherently deviate from a single ground-truth reference. Extensive experiments demonstrate improved target-text alignment, edit effectiveness, and cycle consistency, while maintaining competitive source fidelity and text-to-motion generation quality.

Generative AI models are primarily designed to imitate the data distribution, an objective that neither corrects diversity lost by a learned generator nor defines how generation should extend beyond the diversity of the data itself. We introduce Imaginative Generative AI (IGA), a framework that makes diversity part of the target-distribution design problem: among distributions close to a reference, IGA selects one whose spectral diversity reaches a prescribed level. Diversity is measured by the von Neumann entropy of the generated distribution's kernel covariance operator in a fixed representation space, providing a reference-free representation-guided measure of how broadly probability mass occupies embedding directions. The spectral entropy of the population data distribution defines an Entropy Wall. Below the wall, IGA performs diversity repair, recovering variation that a learned generator has lost while remaining within the diversity level of the data. Beyond the wall, the data distribution itself becomes infeasible, and IGA deliberately departs from it to produce distributions with greater representation-relative spectral diversity, an operational notion of imaginative generation. These regimes form a single regularization path from imitation to imagination and define an i.i.d. target distribution at each prescribed diversity level. We develop the theory of this entropy-constrained projection and show that, under a KL anchor to a pretrained generator, the optimum satisfies a self-consistent exponential-tilt relation. This characterization leads to IGA Guidance, a retraining-free inference-time method for score-based and diffusion models, including DDPM and DDIM samplers. Experiments on synthetic and vision benchmarks demonstrate diversity repair below the Entropy Wall and controlled spectral extrapolation beyond it.

The proliferation of AI-generated images produced by Latent Diffusion Models (LDMs) has raised critical concerns regarding copyright infringement and misinformation. Although existing frequency-domain watermarking methods embed handcrafted geometric patterns into the initial latent noise prior to generation, they suffer from limited capacity and rigid pattern designs. We propose DeepFreqMark, an end-to-end learnable frequency-domain watermarking framework that replaces manual pattern engineering with a neural message encoder and decoder. To circumvent the computational bottleneck caused by Denoising Diffusion Implicit Model (DDIM) inversion during training, we introduce a Spherical Linear Interpolation (Slerp)-based attack simulation. This approach operates directly on the noise latent while strictly preserving the Gaussian variance. Extensive experiments demonstrate that DeepFreqMark achieves significantly lower Bit Error Rates (BER) than baseline methods under real-world attacks and scales to 256 bits message capacity. Our source code is available at https://github.com/chenhsiu48/DeepFreqMark.

Text-guided diffusion image editing aims to modify semantic attributes of an image while preserving its identity, layout, and background. However, naïvely switching the text condition during sampling often causes global drift, as denoising dynamics propagate changes across tokens and can disrupt unedited regions. To address this issue, we propose Asynchronous Token Decoding Edit (ATDEdit), an inference-time framework that views each sampler step as a parallel update of a globally coupled token matrix and enables token-indexed condition switching with differentiated update policies. Instead of applying synchronous target-conditioned updates to all tokens, ATDEdit estimates editable locations using token-wise conditional surprisal and applies target-conditioned corrections to the selected token set. It supplies source key/value memory at keep-token positions and projects selected keep-token latent rows back to their source values; these operations promote background preservation but do not constitute a pixel-level invariance guarantee. This approach combines local editing and background preservation without external or user-provided spatial masks and without model fine-tuning. On PIE-Bench, ATDEdit achieves the strongest reported preservation metrics, including 27.44~dB PSNR and 0.055 LPIPS, while retaining competitive semantic alignment.

Deep neural network (DNN) training with stochastic gradient descent (SGD) and its variants achieves strong empirical performance, yet classical optimization theory does not fully explain this success. This limitation arises because conventional analyses rely on assumptions such as differentiability, convexity, or smoothness, which are often violated by DNN objectives. In this paper, we establish a unified optimization framework for DNN training by generalizing classical convexity and smoothness through Legendre functions and convex conjugation. Specifically, we introduce $\mathcal{H}(ψ)$-convexity and $\mathcal{H}(Ψ)$-smoothness, which unify convex and non-convex as well as smooth and non-smooth objectives within a single formalism and reveal a natural duality between generalized smoothness and convexity. Building on these generalized properties, we introduce generalized gradient descent (GD) and generalized SGD through convex conjugation. We theoretically prove that generalized GD admits an optimal learning rate of exactly $1$, and derive rigorous gradient-energy-based convergence rates for both proposed optimizers. We further reformulate DNN training as a composite optimization problem, demonstrating that its convergence relies on jointly reducing the gradient energy and controlling the induced norm of the network Jacobian. To characterize the practical influences of network architectures and training configurations, we introduce the gradient correlation factor and model capacity risk, and quantitatively analyze how architectural designs, batch size, and model capacity shape training convergence. Extensive experiments across diverse network architectures, datasets, optimizers, and loss functions validate our theoretical bounds and demonstrate precise alignment between our theoretical predictions and empirical training dynamics.