多模态生成与编辑

Many rare genetic diseases are associated with recognizable craniofacial features. However, traditional approaches for describing facial morphology rely largely on qualitative clinical observation and free-text descriptions, which are often subjective, non-standardized, and difficult to reproduce across observers and institutions. Although the Human Phenotype Ontology (HPO) provides controlled terms for describing facial features, these terms are typically categorical rather than quantitative and may vary depending on examiner experience and interpretation. Here, we present FaceKit, a computational framework for quantitative facial phenotyping from frontal facial photographs. FaceKit extracts standardized measurements of facial landmarks and derived 120 morphological features, then reports feature-level z-scores representing deviation from population reference distributions. The reference distributions are built from the FairFace dataset spanning diverse ancestral groups. We evaluated FaceKit on a curated subset of the GestaltMatcher Database covering 50 rare-disease cohorts. In addition to quantitative facial analysis, FaceKit includes synthetic facial image generation to support rare disease model development and data augmentation. We also performed privacy evaluation to assess whether synthetic images reveal identifiable information from real patient photographs and could compromise patient privacy. Across disease case studies, FaceKit-derived quantitative measurements captured known facial features associated with rare genetic disorders and provided objective support for clinical phenotyping. Together, these results establish FaceKit as a useful tool for quantitative phenotyping, and has the potential to improve rare disease diagnosis, support genotype-phenotype studies, and enable more reproducible clinical characterization across diverse patient populations.

Physical world modeling requires predicting how interactions change a scene, not merely generating coherent motion. We propose STRIKE, a framework that separates visual state transition learning from dense video generation. We construct event-aligned supervision by extracting observed states from training videos and pairing them with transition descriptions and temporal offsets. An image-based transition model learns to predict the next scene configuration from the current image, a local transition specification, and elapsed time. At inference, a pretrained vision-language planner predicts time transition specifications, and recursive application of the learned transition model produces a sequence of future visual states. A separately trained dynamic model then generates the complete rollout conditioned on these states and their temporal locations. Experiments on Physics-IQ Verified, PhyGenBench, Pisa-Experiments, and RoboTwin2.0 show improvements of STRIKE over the corresponding video-backbone baselines in benchmark measures of physical consistency and manipulation-video fidelity. These results support learned visual state transitions as an effective intermediate representation for physical world modeling.

We introduce QuadTok, a novel framework for visual tokenization and autoregressive image generation. Compared to traditional approaches using 2D grids or 1D token sequences, we propose a hierarchical quadtree structure, bridging the gap between 2D spatial binding and 1D sequence-level flexibility. The QuadTok tokenizer dynamically allocates representational capacity to visually intricate areas while leaving homogeneous regions at a coarse resolution. Compared with a fixed 256-token grid, our ImageNet-trained tokenizer saves approximately 10% of tokens on ImageNet and 9% when transferred zero-shot to the COCO dataset, while maintaining comparable reconstruction fidelity. Furthermore, the natural causality introduced by the tree structure seamlessly enables autoregressive image generation. Conditioned on a quadtree topology supplied before generation, our 947M GPT-style generative model achieves a 2.08 gFID on the ImageNet $256 \times 256$ benchmark. Additionally, leveraging the strong spatial correlation preserved by the quadtree structure, the QuadTok generator enables zero-shot spatially controlled image generation capabilities. Code: https://github.com/myc634/QuadTok.

Many applications of physical AI run within finite or closed physical worlds with a limited set of physical laws governing object behavior. Examples include robots working in a warehouse and agents moving around in a video game. In order to better organize, filter, and curate data for physical AI applications, we propose a new approach centered on the unique settings and physical laws of individual datasets. We train LeCuration, a small world model intended to serve as a data curation tool for a separate, larger downstream model. To build this model, we choose LeWorldModel (LeWM)as our latent encoder and predictor, adding a diffusion transformer (DiT) decoder to add visuals to autoregressive gameplay rollout. We find that the embeddings of this model can be used as an anomaly detection signal and as a content-based clustering heuristic, and that auto-regressively predicting the game state with this model allows us to qualitatively check for action-state consistency. This paper presents a qualitative, proof-of-concept case study on CS:GO gameplay data; we do not yet report quantitative curation metrics or downstream training results, which we identify as the key next step.

Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typically share parameters, and we find that their gradients exhibit distinct patterns and systematic negative alignment, hindering the joint optimization of visual quality and temporal consistency. We introduce Self Gradient Forcing Plus (SGF+), which assigns separate parameters to context writing and denoising while preserving their interaction through causal attention. Both roles are jointly optimized using the original generation objective without auxiliary losses, with context writing supervised through its contribution to future predictions. This simple change improves visual quality and long-horizon consistency over the evaluated baselines in both framewise and chunkwise generation, without additional video training data or a longer training horizon. Trained on only 5s rollouts, SGF+ supports continuous generation for up to 24 hours without long-video fine-tuning. These results highlight role-specific parameterization as an effective design principle for high-quality autoregressive video generation and native long-horizon extrapolation.

Rapid and accurate prediction of urban wind and temperature fields is important for urban microclimate design and climate adaptation. Large-eddy simulation (LES) effectively resolves these instantaneous fields, but its application is limited in iterative design of urban microclimate applications due to high computational cost. Existing regressive data-driven models offers quick outputs, but they produce only deterministic point predictions that inherently fail to represent turbulent stochasticity. This paper adopts a novel generative framework of Conditional Flow Matching (CFM) that uses building geometry and mean flow as guidance to generate plausible three-dimensional instantaneous velocity and temperature fields for urban microclimate in seconds. To overcome the GPU memory bottleneck of pixel space 3D generation, the model operates in parallel on overlapping pixel space through a shared-noise initialization that preserves high spatial continuity of flow structure across the entire domain. Against reference LES data, the CFM surrogate can rapidly and accurately restore the first-order statistics with Normalized Root Mean Square Error (NRMSE) of 2.99% for wind and 1.77% for temperature, second-order turbulence metrics with NRMSE of 7.17% for wind and 8.84% for temperature, turbulent kinetic energy with NRMSE of 7%, probability density function and vertical profiles in representative locations. Wind engineering application of local gust prediction demonstrate that the speed and accuracy of CFM, supporting the use of generative AI for making turbulence-aware resilient urban design and climate adaptation more computationally feasible.

Camera trajectories control viewpoint changes in video generation, scene reconstruction, and robotic perception. Generating them from language requires both scene geometry and target-aware framing. We introduce OmniCam, an autoregressive model that generates camera pose sequences from a single panorama and textual trajectory descriptions. Its geometry-grounded pose token learning combines three components: a panoramic point-cloud encoder for omnidirectional geometric context; hybrid absolute-rotation and relative-translation tokenization with temporally consistent quaternion signs; and separate geometric and semantic conditioning streams with an explicit 3D target anchor. We also construct OmniCaT, containing 267,700 trajectories across four camera behaviors. On the reported OmniCaT evaluation, OmniCam reduces trajectory errors by 28--47% and collision rate by 65.8% relative to GenDoP retrained on OmniCaT. Against the best baseline for each metric, the ATE and collision reductions are 43.0% and 62.3%, respectively. Component ablations support the use of geometric and target-aware conditioning, while downstream experiments examine camera-controlled video generation and robotic active perception.

We introduce MUNITE, a latent-variable framework for flexible any-to-any multimodal generation that treats encoding and latent generation as the same inference problem under different amounts of observed evidence. Given any subset of modalities, MUNITE models the conditional distribution over the latent representation associated with the complete observation. Full observation recovers deterministic encoding, no observation recovers the latent marginal, and intermediate subsets define conditional latent inference, all within a single conditional flow model. A shared latent sample captures variation that must remain consistent across generated targets, while modality-specific generative decoders model the remaining uncertainty independently. To learn these conditional distributions from incomplete training examples, we extend conditional flow matching through self-distillation: predictions conditioned on richer available observations supervise the same model conditioned on smaller subsets at the same intermediate latent state. When the richer-evidence trajectory follows the exact conditional flow, this provides the same expected learning signal as full-target denoising. Across PolyMNIST-D-Q, FFHQ64, and image-text-audio, MUNITE achieves competitive or better generation quality and source-target alignment, with higher joint-generation coherence. In particular, it attains the highest coherence in all one-to-many and unconditional image-text-audio comparisons, showing the effectiveness of unified latent inference across diverse multimodal settings.

Text-to-music systems produce increasingly convincing audio, yet evaluation reveals little about whether the result matches user intent. A global text-audio relevance score can overlook the implicit intent in underspecified prompts and mask failures in specific requirements, such as instrumentation, structure, rhythm, or mood progression. To bridge this gap, we formulate text-to-music intent alignment as satisfying a per-request rubric of independently verifiable items covering both a request's explicit requirements and its implied musical intent. Scoring items individually makes evaluation diagnostic by intent source and musical dimension, rather than a single opaque score. We instantiate this as MuRA-Bench, a benchmark of real-world platform requests curated by music experts. We further propose MIRA (Musical Intent Refinement Agent), a test-time agent that first grounds a request's intent into rubrics, then searches over prompt revisions for a black-box generator under a bounded budget, iteratively generating music, verifying it against the rubrics, and using this feedback to guide a trajectory-aware tree search. Experiments across open-source and commercial backends show that MIRA improves intent alignment, enabling an open-source generator to achieve performance comparable to representative commercial systems (e.g. Suno and Mureka). Project page: https://mirareview.github.io/.

Prior artisan mesh generation works largely predict face tokens autoregressively, which makes inference slow. Recent methods instead flow match continuous latents built by Variational AutoEncoders (VAEs), but reconstruction quality drops significantly when geometry and topology are jointly encoded, and further when the latent space is compressed. We present MeshCarve, a flow matching method that generates entirely in compact latent spaces, generating vertex positions and edge connections separately and sidestepping the difficulty of a joint compact latent. To shorten the token sequence, we propose a hierarchical sparse transformer backbone, instantiated as VertexVAE and EdgeVAE. Instead of encoding fields over the surface voxels, both VAEs anchor on discrete vertices in their latent spaces, which drastically reduces the token sequence length, and our spatial-aware compression shortens it further without costing reconstruction. VertexVAE directly encodes vertex occupancy. For connectivity, we propose vertex-link encoding, which turns arbitrary connectivity between vertices into fixed-length continuous per-vertex embeddings and recovers complex artistic topology faithfully. MeshCarve combines these VAEs with an anchor generator and flow matches on the shortened token sequences. It shows advantages over state-of-the-art autoregressive and flow matching methods on Objaverse and generalizes to Toys4K. To the best of our knowledge, it is among the first artisan mesh generation methods whose every generative stage runs in a spatially compressed latent, with a token sequence only a fraction of the most compressed previous autoregressive and flow matching works.

Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string rendering improves, evaluation must test sustained performance across more demanding scenes. We introduce UltraText Bench, a bilingual benchmark for prompt-only generation of dense visual text. It contains 432 prompts spanning 24 real-world scene categories and three difficulty levels, split equally between English and Chinese. Each human-reviewed prompt supplies exact strings for four to twelve text regions, paired with structured references for their content, placement, and visual attributes. We use the Q-Judger vision-language model to assess each image against the complete reference, reporting text fidelity, text clarity, spatial quality, and scene quality. Across 24 model configurations, these dimensions reveal different strengths: Z-Image-Turbo gains 3.81 clarity points over Z-Image-Base while losing 14.76 fidelity points under the reported settings. Performance also varies with workload; Qwen-Image-2512's English composite falls from 86.50 at L1 to 42.86 at L3. Ten participants took part in human evaluation of the automatic scores. Repository: https://github.com/LINs-lab/UltraText_Bench.

Multimodal representations enable zero-shot classification and retrieval, but aligning independently trained models usually requires large amounts of paired data. Yet, the Platonic Representation Hypothesis suggests that models trained on different modalities may converge spontaneously toward a shared representation geometry. But then, do we even need paired examples for cross-modal alignment? Remarkably, we show that paired examples are unnecessary for coarse cross-modal alignment. Our simple Wasserstein Procrustes method with a coarse geometric initialization aligns two disjoint embedding sets by estimating a single orthogonal map without seeing any pairs. Across datasets, modalities, and unimodal models, we show that we can consistently align independently trained representations without pairs, and standard geometric alignment metrics accurately predict when this is possible. Nevertheless, we can naturally benefit from paired examples. In the very few-pair regime, our method substantially outperforms existing ones, while staying competitive with pair-based methods with more added examples. Finally, we demonstrate that the resulting alignments can enable text-to-image generation without paired examples. These results show that independently trained models often share enough geometry to establish cross-modal correspondence with little or no paired data.

Recent single-stage 3D generative models commonly adopt VecSet representations, encoding 3D shapes as unordered sets of latent tokens. However, compared with two-stage methods that provide explicit positional guidance, these models must implicitly infer token positions throughout denoising, limiting their generation quality. We observe that, despite the absence of explicit positional conditioning, VecSet tokens retain recoverable spatial correspondences. Building on this observation, we propose Position Forcing, a position-based self-conditioning framework. During denoising, Position Forcing recovers token positions from the current clean latent estimate, quantizes them at progressively finer resolutions according to the denoising stage, and feeds the resulting positional encodings back into the diffusion Transformer. This progressively refined positional feedback provides spatial guidance at a granularity appropriate to each denoising stage, guiding shape generation along a coarse-to-fine trajectory and substantially improving generation quality without a separate position generation stage. Experiments demonstrate that Position Forcing achieves strong performance among single-stage 3D generative methods and outperforms several competitive multi-stage approaches.

Multimedia editing requires generative models to interpret complex, compositional instructions and modify only the desired elements across modalities, a capability largely beyond existing systems. Current approaches are typically limited to simple, single-attribute edits within one modality, since diverse, high-quality editing pairs are hard to obtain, especially for cross-modal tasks where aligned audiovisual (AV) data is scarce. We present CrossEdit, a unified omni-modal editing model for images, audio, and video that performs AV movie scene edits zero-shot through cross-modal transfer. Our key observation is that complex instruction-following, once learned in any modality, generalizes to others. We exploit the additive nature of acoustic signals to procedurally generate large-scale audio editing pairs with compositional instructions, and show that fine-tuning on this synthetic data and self-supervised AV masked reconstruction, alongside a targeted set of curated cross-modal tasks, induces instruction-following that transfers zero-shot to unseen modality and instruction combinations. To evaluate this capability, we release CrossEditBench, a human-annotated benchmark of AV edits on movie scenes, and propose AV-FES, a metric that jointly scores instruction following and consistency. We show that our proposed techniques improve performance on zero-shot AV movie scene editing, while maintaining or improving performance on lip-synced speech editing and standard image, video, and audio editing benchmarks. Demos are available at https://wanchichen.github.io/crossedit/.

Pretrained text-to-speech (TTS) models can generate expressive speech, but reliable inference-time emotion control remains challenging: prompts and reference audio offer coarse, inconsistent control, whereas specialized conditioning and model adaptation require costly training. We present SteerSpeech, a lightweight activation-steering framework that controls emotion by injecting steering vectors into hidden activations. For each target emotion we train a lightweight low-rank transform, using a multi-expert objective that encourages monotonic emotion control while preserving speaker identity and linguistic content, constraining steering drift, and keeping the TTS backbone frozen. To optimize through discrete speech tokens, we introduce a two-pass generation-and-replay pipeline using a straight-through estimator to backpropagate expert supervision through sampled tokens. At inference, a target-emotion steering direction is optimized with its respective transform and injected into the base TTS model. Objective and subjective evaluations with Qwen3-TTS across seen, unseen, and accented speakers show stronger continuous emotion control with limited speaker and content degradation. SteerSpeech achieves 1.08x-7.12x baseline target-emotion scores and for a representative emotion subjectively, it receives 78.1%-96.8% intensity preference and 1.43x-1.46x speaker-identity preservation at high steering strengths.

Multi-subject image generation requires rewards that verify whether requested attributes, actions, and relations hold for the specified reference subjects. Subject presence alone does not establish that the correct subjects participate in a requested interaction. We present reference-bound Visual Jev rewards that turn these visual decisions into generator training signals. Each subject-related question receives a positive label only when the requested condition and the relevant reference identities hold jointly. We construct fixed questions offline, train a Qwen3.5-4B verifier with binary supervision, and directly read Yes probabilities from its language-model head. Their mean supplies a GRPO reward while retaining individual judgments for inspection. Using 200 MICo-150K training tasks and 30 updates, the framework raises a GPT-5.4 composite score from 41.78 to 52.50 on a manually selected 897-task MICo-Bench subset; direct 27B rewards yield 51.84. Each reward is tested in one GRPO run, and offline human evaluation does not establish a statistically significant advantage over direct scoring. The study provides an initial implementation and evaluation of Visual Jev as a reference-bound reward for multi-subject image generation.

How can we verify whose music contributed to an AI-generated output? This paper demonstrates how input-based attribution can provide verifiable evidence of which audio sources were used in a generation and whether they shaped the output. To do so, we condition the generation solely on audio without any text input, then trace the inputs behind each output, and establish their musical effect. In prompt adherence tests and controlled input swaps, the stems generated by our generator, MixAudio, follow the prompt audio in timbre and the context audio in harmony. Yet these outputs may still reproduce training data not supplied as inputs. We therefore audit memorization with our musical version identification model, musicDNA, and find few reproductions outside the input records. On human-judged cases within the flagged pool, it achieves higher precision and recall than the other tested memorization detectors. The two evaluations suggest that input records and output analysis provide complementary evidence for attribution, on which rights-holder reporting and compensation can draw as the AI music economy takes shape. Audio examples are available at https://neutune.github.io/attr2027demo/

World models can enable autonomous ultrasound scanning by predicting the outcomes of probe motions from local observations. Learning this action--observation relationship typically relies on synchronized video--pose pairs, which are costly to collect at scale and largely unavailable in routine clinical recordings. Reliable action following further requires modeling ultrasound's cross-sectional sampling geometry. We present UltraWorld, a self-distillation recipe that transfers priors from clinical ultrasound videos into interactive world models without real action annotations. Starting from clinical videos, we adapt a video foundation model into an ultrasound generator conditioned on reference images and anatomical masks. Anatomical masks sampled along programmable trajectories through 3D anatomy provide spatial guidance for synthesizing action--video pairs. We then use these synthetic pairs to self-distill the generator into a world model that predicts future observations from local observations and actions, without requiring anatomical masks or other 3D assets at inference time. To further improve action following, we introduce the Acoustic Sampling Map (AsMap), which represents probe poses and imaging settings as pixel-wise 3D sampling positions, beam directions, and depths. Experiments demonstrate improved prediction fidelity and action following. Across nine simulated closed-loop local planning episodes, UltraWorld reduces the mean final distance to the goal and orientation error by 29% and 38%, respectively, compared with visual servoing. Project Page: https://ultraworld-project.github.io/.

Surgical video generation holds substantial potential for surgical education, simulation, and data augmentation, yet generating surgical videos with realistic and clinically plausible motion remains challenging. Most existing methods rely on auxiliary conditions, such as masks, trajectories, depth, or reference videos, to achieve visually plausible synthesis. Yet, these auxiliary conditions typically require additional manual annotation or specialized acquisition, making it difficult to scale such methods beyond small, curated datasets. This motivates the need for a reference-free architecture capable of generating high-quality surgical video without requiring auxiliary visual conditions at inference time. We propose FLAIR, a Flow-guided LatentAction Injection framework for Reference-free surgical video generation. FLAIR learns action priors from optical flow of real surgical videos, dynamically predicts corresponding latent action representation from an input prompt, and injects it into a frozen base model to generate surgical videos with improved action consistency. We further construct SurgActionClip-30K, the first large-scale surgical vision dataset comprising action-centric segmented clips and structured caption labels, addressing the persistent lack of fine-grained, action-centric surgical datasets. Lastly, we introduce SurgMetrics, the first surgical domain-specific evaluation metrics for quantifying the quality of generated surgical videos, addressing the persistent absence of clinically grounded evaluation standards in this domain. Extensive experiments demonstrate that FLAIR enables generating high-quality surgical videos using text-only inference without auxiliary conditions, and validation in SurgMetrics demonstrates its strength in alignment with human perception compared to traditional metrics.

Holistic co-speech animation is prone to averaging in both motion representation and speech conditioning. In coordinate-space diffusion, slow body posture, mid-frequency gesture strokes, and fast hand or facial details are entangled in one prediction target, often producing low-variance, over-smoothed motion. Meanwhile, dense rhythmic and acoustic cues can dominate sparse content-specific information under fixed multimodal fusion. We present DynaConTalk, a wavelet-constrained diffusion framework for long-form and controllable holistic co-speech motion generation. Diffusion operates in stationary wavelet transform (SWT) coefficient space, whose temporally aligned bands separate coarse posture evolution, gesture strokes, and fine expressive details. Our dynamic gating network preserves HuBERT and speaker identity as a base and selectively adds rhythm, mel, and transcript features through motion-state- and noise-aware residual gates. Attention pooling and learned depth routing deliver complementary conditions to each denoising stage, while a frame-resolution rhythm path preserves precise timing. A signed proposal-consensus update then reconciles these conditions with the evolving motion state. Matched-noise constraint injection uses the same sampling interface for history continuation and localized keypose repair, and extends to reference-guided control. Separate body-hand and facial denoisers, followed by inverse SWT and a pose-driven root regressor, produce holistic motion. Experiments evaluate generation quality, facial accuracy, temporal continuity, and controllable editing. Code, models, and the interactive editing interface are available at https://github.com/zhuyifeiabcd1/DynaConTalk.

Product-centric advertisement video generation aims to create promotional videos that preserve fine-grained product identity while presenting selling points through coherent multi-shot narratives. However, this emerging task remains underexplored due to the lack of large-scale advertisement-specific datasets and comprehensive evaluation frameworks. To address this gap, we introduce AdSpark, a large-scale dataset and benchmark for product-centric advertisement video generation, based on data from a major e-commerce platform. AdSpark-300K contains approximately 300K reference image--prompt--video triplets, comprising a real-world subset and a synthetic subset. Each sample provides structured advertisement annotations, including product identity annotations, selling-point descriptions, creative plans, and aligned audio scripts, enabling models to learn product preservation and advertisement-oriented visual storytelling. We further propose AdSpark-Bench, a diagnostic benchmark that evaluates generated advertisements across six dimensions, including visual quality, product fidelity, instruction adherence, temporal coherence, audio alignment, and advertisement effectiveness. Based on AdSpark-Bench, we evaluate representative models, revealing key challenges in product preservation, multi-shot storytelling, and selling-point visualization. Experiments with AdSpark-300K-finetuned models further validate the effectiveness of our dataset. AdSpark provides a unified dataset and benchmark for future research, and we will release the dataset upon acceptance.

Multimodal large language models (MLLMs) have made significant progress in visual understanding and generation. However, generating interleaved image--text content remains challenging, as it requires tightly integrated multimodal understanding and generation capabilities. Although existing MLLMs provide promising solutions, most rely on additional training with augmented data, which is computationally expensive and remains limited in preserving visual subjects, temporal consistency, and physical plausibility. In this work, we propose self-correction optimization (SCO), an effective training-free method for consistent interleaved generation. SCO treats the classifier-free guidance update as a reference and performs minimal self-correction under two complementary constraints, including new-event and state-preserving constraints. Specifically, the new-event constraint promotes temporal consistency across image--text sequences, while the state-preserving constraint maintains the coherence of visual subjects throughout subsequent generation steps. Experiments on challenging interleaved multimodal generation benchmarks demonstrate significant improvements in temporal coherence and visual-subject preservation. Furthermore, SCO can be extended to video generation and improves the modeling of physically grounded processes, including robot manipulation and long-horizon handcrafting.

Unlike autoregressive models, discrete diffusion-based models for zero-shot text-to-speech generate speech tokens in parallel and can revisit earlier predictions. Mask-and-replace training extends mask-only training by randomly replacing some tokens, and its gains are commonly attributed to self-correction, the ability to revise previously generated tokens. However, exposure to randomly perturbed context during training may itself improve generation, raising the question of whether these gains require inference-time token revision. To investigate this question, we use DeMaR, which combines mask-and-replace training with confidence-ranked mask-only sampling while preserving the total training corruption probability. Trained from scratch on LibriTTS, DeMaR achieves lower word error rates (WER) than autoregressive and mask-only diffusion baselines using the same speech tokenizer. This advantage persists when each token remains unchanged after first being unmasked. Matched training conditions on two heterogeneous speech tokenizers show that both noisy-context augmentation and replacement supervision improve WER under this restriction. These findings demonstrate training-side benefits of replacement beyond enabling inference-time token revision.

Cine cardiovascular magnetic resonance (CMR) analysis relies on multi-frame sequences capturing the full cardiac cycle. However, standard multi-frame acquisition depends heavily on electrocardiogram (ECG) gating and repeated breath-holds, posing challenges in uncooperative populations, resource-limited settings, and temporally corrupted datasets. Existing methods that synthesize full cardiac sequences either rely on explicit ECG signals to parameterize myocardium function, or employ deformable registration without physiological constraints, failing to faithfully reproduce clinically relevant dynamic metrics such as ejection fraction (EF) and ventricular contraction magnitude. We present PhaseFlow, a unified generative framework that overcomes both limitations. PhaseFlow estimates a non-linear cardiac phase signal directly from the input sequence via a segmentation-derived left-ventricular (LV) area curve, capturing the asymmetric dynamics of systole and diastole without any ECG dependency. At inference, this phase signal is provided by a pathology-specific template, informing phase-specific frame generation. A rectified flow model conditioned on the phase and slice position synthesizes the full cardiac motion trajectory in the latent space, decoded into a diffeomorphic displacement field that warps end-diastole pixel intensities directly, eliminating the reconstruction blur often accompanying the variational autoencoder. On the ACDC benchmark, PhaseFlow achieves superior physiological fidelity and image realism, with best LV volume curve $R^2$, structural similarity (SSIM) and generative quality (FID) among all baselines. Ablation studies confirm that each proposed component contributes measurably to the overall performance.

Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. We test this claim along both routes to a pixel-space backbone. We pretrain Iris-3B, a 3B-parameter pixel-space text-to-image transformer, from scratch through a $256\to512\to1024$ curriculum, after first ablating the prediction target and representation alignment at $256^2$ to decide what to scale. We also convert a pretrained latent model, FLUX.2 Klein base 4B, to pixel space. We fine-tune both families for monocular depth estimation and for image restoration/super-resolution. We find no significant improvement from using a pixel-space generative prior. Fine-tuned for depth with one matched direct-regression recipe, Iris-3B is level with the latent FLUX.2 Klein and the converted pixel FLUX.2 Klein falls behind it, and on $4\times$ DIV2K restoration neither pixel model beats a latent FLUX.2 Klein fine-tune, the converted one trailing it slightly. We document the recipes, the failure modes and the remaining confounds behind this negative result. Nevertheless, Iris-3B shows that pixel-space pretraining with the pixel-transformer (PiT) head of PixelDiT scales to 3B parameters and to text-to-image quality competitive with latent models, matching Qwen-Image on OneIG under the official evaluators at $1024^2$. We release its weights and training code in the hope that they help pave the way for further work on pixel-space generation.

Text-to-image diffusion models fail predictably on compositional prompts: attributes bind to the wrong objects, spatial relations invert, and multi-object scenes lose count. Recent architectures already augment CLIP with a T5 encoder precisely because CLIP's contrastive embedding loses compositional structure, yet these failures persist. We argue the binding problem is therefore not one of missing information but of misaligned information: a text encoder preserves compositional structure, but in a representation space shaped by language modelling rather than vision, and the denoising objective does not directly reward aligning the two. We show this correspondence can be supplied as an explicit training signal, that the relevant cross-modal information is concentrated in a low-rank subspace of self-supervised visual features, and that supplying it can be folded into diffusion training as a single auxiliary loss. Our method, ORCA (Orthogonal Residual Compositional Alignment), aligns the latent of a diffusion transformer with a low-rank target derived from a frozen visual encoder, through a predictor whose orthogonal basis is parameterised by a learned residual between T5 and CLIP embeddings, which provides a prompt-dependent signal for selecting the visual readout subspace. We prove that the cross-modal information recoverable at a given rank is bounded by the spectral mass of the visual encoder's covariance in the top components. Across three diffusion-transformer backbones (DiT-B/2, DiT-L/2, U-ViT-L), ORCA improves FID and GenEval over both vanilla and REPA baselines at zero inference-time cost; on DiT-L/2 it reaches FID 16.65 and GenEval 0.291 at 200K steps, exceeding the strongest 400K baseline at half the training cost, with the largest gains concentrated on attribute binding, spatial relations, and multi-object prompts.

Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fewer tokens. However, such autoencoders are challenging to train, since a higher compression ratio degrades reconstruction quality and recovering it requires more channels, which is known to slow the convergence of the DiT. The compressed latent also differs from the one the DiT was trained on, so the pretrained DiT must be either retrained from scratch or adapted at considerable cost. Compressing the autoencoder the DiT was trained with appears to preserve compatibility, yet optimizing it for reconstruction alone still shifts the latent away from the distribution the DiT has learned. To address this, we propose Generation-Aware Latent Compression for Efficient Video Generation (GRACE), a two-stage framework that compresses a pretrained video autoencoder while keeping it compatible with the pretrained DiT. Specifically, we keep a frozen base latent from the pretrained encoder and learn a residual latent for the information lost under stronger compression, while aligning the compressed latent with the pretrained latent in the feature space of the frozen DiT so that the autoencoder is optimized for generation. We then adapt the DiT with lightweight fine-tuning and asymmetric denoising, where the base is denoised ahead of the residual. GRACE reduces the token count of Wan2.1-I2V-14B by 8x and its latency by 11.1x at 480x832x81, while matching the generation quality of the pretrained pipeline before compression on VBench.

Diffusion models excel at image synthesis, but they remain limited in their ability to reliably satisfy structured spatial reasoning constraints. In conditional data distribution modeling tasks with implicit logical structure, such as puzzles defined by visible clues paired with consistent solutions, state-of-the-art generative models tend to approximate pixel-space distributions without learning the underlying logical rules required for inference. To address this limitation, we present a novel framework for spatial reasoning with diffusion models that leverages unsupervised object discovery and abstractions of object relations. We show that the relational knowledge derived from object-centric representations enriches diffusion models with structural primitives, allowing them to effectively guide the generative representation space during both training and inference, and enabling conditional image generation that satisfies reasoning constraints. Additionally, we introduce a large-scale generative spatial reasoning benchmark with four datasets inspired by human-solvable puzzles. Our results show that relational abstractions significantly improve reasoning capabilities of diffusion models on a variety of complex reasoning tasks, while enabling robust generalization in out-of-distribution settings.

Crowd simulation plays a central role in robot navigation, autonomous driving, and urban planning. For these applications, realistic simulation requires crowds to adapt their behavior to environmental changes and user objectives. However, existing methods that rely on predefined control settings have limited flexibility in accommodating new user-specified objectives. To address this limitation, we propose Ctrl-CWM, a multi-agent Controllable Crowd World Model that integrates crowd generation and run-time control. Our key idea is to adapt the world-model principle of planning using imagined futures to crowd simulation. To this end, Ctrl-CWM consists of an encoder that learns a representation of human motion dynamics, an actor that proposes pedestrian displacements, a critic that evaluates imagined crowd trajectories, and a planner that selects actions. We first learn human motion dynamics through trajectory prediction on real-world pedestrian videos and then freeze the encoder to preserve them. Using this representation, the actor generates imagined crowd trajectories through repeated state updates, and the planner combines the critic's scores with user costs to select actions. Repeated planning advances the simulated crowd, while additional user costs introduce new control objectives without retraining. We extensively evaluate crowd generation under varied agent arrival conditions and run-time control across avoidance and attraction scenarios. Ctrl-CWM outperforms the state-of-the-art method on most crowd realism and collision metrics, and adapts crowd behaviors to user-specified objectives introduced during simulation. The project page is available at https://jungyu0413.github.io/Ctrl-CWM

Autonomous unmanned aerial vehicle (UAV) object search involves a closed loop of perception, decision-making, and action under partial observability. Urban environments pose several challenges: large search areas and narrow egocentric views limit coverage, dense 3D geometry constrains safe motion, and open-world instructions require identifying a specific target among distractors. Many existing methods mitigate partial observability through explicit maps or memory representations, yet remain largely reactive, reasoning over past observations without explicitly predicting future states. World models enable prospective reasoning through imagined rollouts. However, image-generating world models can incur high inference latency, while spatially grounded planning remains challenging for latent world models. We propose SearchWorld, a recurrent state-space world model that connects explicit spatial memory with value-guided imagination. The model maintains BEV exploration and obstacle memory and decodes a task-aware spatial value layer to guide search. A cognition-action network uses this learned spatial value prior to improve the policy through imagined rollouts, without training a separate scalar critic. Training progresses from world-model learning to expert imitation and imagination-based exploration refinement. On UAV-ON, SearchWorld improves the success rate to 23.8% (19.5% for the strongest published agent) and raises oracle success to 35.5%, while remaining robust on unseen scenes (19.9% success rate). By grounding imagination in explicit spatial representations, SearchWorld enables UAV agents to plan prospectively rather than react.