每天知道
你的领域
出了什么

Evaluating end-to-end autonomous driving under rare, safety-critical vehicle-pedestrian interactions requires photorealistic, sensor-level scenarios. However, trajectory-based scenario generators cannot synthesize raw visual observations, whereas video-based approaches lack controllability. To bridge this gap, we present ControlPed, a novel framework that combines trajectory-level conflict synthesis with 3D Gaussian Splatting (3DGS) to generate photorealistic, motion-controllable safety-critical scenarios. Built upon HazardPed, a dataset derived from 10,352 traffic videos comprising 422 conflict trajectories, HD maps, and 857 annotated 3D human motions, ControlPed first generates conflict trajectories, lifts them into 3D human motion sequences via text-conditioned motion diffusion, and finally renders multi-view sensor observations using animatable 3DGS avatars. Safety evaluation in 88 rendered photorealistic scenarios reveals that seven leading end-to-end driving models suffer a severe performance drop, with their mean HDScore plunging from 88.8 to 47.4, exposing major failure modes under dangerous pedestrian behaviors. The dataset and testing benchmarks will be released to facilitate safety assessment of vehicle-pedestrian interactions.

World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay, packet loss, reordering, and actuator buffering. We study how asynchronous execution changes the action semantics assumed within world-model controllers, rather than treating it only as an external control disturbance. Through controlled interventions, we identify two architecture-dependent failure modes: planning-based controllers such as TD-MPC2 suffer from a future-action timeline mismatch between imagined and executed action sequences, while recurrent world models such as DreamerV3 can attribute observed transitions to commands that were not actually applied. Our analysis shows that TD-MPC2 requires the correct future action sequence during latent dynamics rollout, whereas DreamerV3 requires timely attribution of each transition to the action that generated it. Based on these findings, we introduce two lightweight execution-consistent interfaces, Future-Sequence for TD-MPC2 and Applied-Action Feedback for DreamerV3, that correct these mismatches without modifying the pretrained world models. Experiments across delays, packet loss, reordering, multiple control domains, measured network traces, and a process-separated asynchronous stack consistently support both diagnoses and the corresponding architecture-specific corrections.

Methods for generalization in model-based reinforcement learning typically assume that an agent cannot recover the latent context governing the environment dynamics from its own experience, and therefore supplies it externally. We formalize and test this assumption with predictive sufficiency, which quantifies what access to the context adds to next-step prediction under the visitation distribution an agent induces, and separates that quantity into a history-recoverable part, a residual requiring the true context, and the deficit added by a finite model. We classify context-aware algorithms by the predictive risk their conditioning set can target and demonstrate across environments of increasing identification difficulty that the headroom does not follow the MDP class. The same task under different priors leaves predictive headroom in one setting and nothing distinguishable from zero in another, where the agent's behavior implicitly identifies the context and any benefit of such a mechanism cannot be attributed to missing information. Where headroom persists, the learned state exposes it only partially, and adding the true context still lowers the risk. Our contribution is a practical criterion for matching contextual mechanisms to the information available to them, estimated from the ordinary trained agent without a reference policy.

While existing camera-controllable video generation models can produce visually compelling sequences, preserving intrinsic 4D spatiotemporal coherence remains challenging. To address this limitation, we propose ChronoWorld, an "Observation--State--Reflection" framework that leverages spatiotemporal causal cues and reconstruction priors to generate globally consistent, free-view 4D scenes. Given a context video, we introduce a Spatiotemporal Epipolar Causal Attention mechanism that enforces multi-view epipolar constraints and temporal causality throughout the generation process. In addition, we develop a reconstruction-driven geometric reflection pipeline with a 4D retrieval strategy to enable dynamic self-assessment and correction of generated outputs, improving consistency and accuracy. Extensive experiments show that ChronoWorld achieves state-of-the-art performance in spatiotemporally consistent, cinematic-quality 4D scene generation, with strong generalization and high-fidelity geometry across diverse scenarios.

Reliable and practical audio-visual DeepFake detection requires benchmarks that reflect diverse linguistic contexts and modern data synthesis pipelines for visual as well as audio manipulations. However, existing datasets predominantly contain footage of English-speakers, often include outdated manipulation types, or overlook the audio modality. Further, many datasets feature individuals who did not consent to be used in DeepFake creation. We introduce BabelFake, a multilingual audio-visual DeepFake benchmark recorded with consenting participants. BabelFake contains 399k clips (1,323 hours) from 496 individuals spanning five languages (English, German, Italian, French, Spanish). Our modular data generation pipeline pairs 11 modern video manipulation methods with 4 voice cloning engines, distinguishing visual-only (face swapping) and joint audio-visual manipulations (lip synchronization and portrait animation). By benchmarking state-of-the-art detectors, we show that detection difficulty depends on the audio-visual generation pairing, with substantial performance degradation when authentic audio is preserved. Cross-language/demographic evaluation reveals sensitivity varying across detector architectures and training data, while human evaluation reveals that perceived realism and machine-detection difficulty do not necessarily align.

Image editing should change only the attributes specified by an instruction while preserving everything else, yet current methods often make unintended changes. We treat this minimal-change principle as an optimization objective for instruction-based editing. Latent L1 regularization is a poor proxy for output locality in modern nonlinear generators and often requires supervision unavailable at scale. We instead optimize edit outcomes with reinforcement learning. An agentic vision-language reward model audits each source image, instruction, and edited image for two failure types: unimplemented requested changes and unintended changes. A group-level rubric merges and verifies these issues to provide consistent rewards across candidate edits without per-instruction human annotations. On FLUX.1 Kontext-dev, ARRO raises average EditScore from 5.21 to 5.88 across MinEval, MagicBrush, AnyBench, and Emu-Edit. On 600 evaluation examples, it reduces off-target pixel change by 8.4% relative to the base editor. Reward and SFT controls, blinded human evaluations, and transfer to OmniGen2 provide complementary evidence. Code: https://github.com/Showwwwwwwww/ARRO

Engineering design often starts from a 2D sketch that fixes style and proportions, yet the subsequent 3D shape optimization relies on learned generative priors to keep the geometry valid. However, these priors are agnostic to the sketch: while they admit a valid design by correcting a drifted proposal back to its training distribution, they often correct it towards the high-density region, ignoring the specified design. We introduce AnchorGen, a rectified-flow framework trained unconditionally on the concatenated shape and sketch latents of paired data. The learned manifold represents the joint distribution of shape-sketch pairs, so constraining the sketch component restricts the iterate to the sub-manifold of shapes consistent with a target style. Since training employs no conditioning signal, the constraint is imposed at inference: gradient descent optimizes the shape latent to minimize a differentiable drag surrogate, while constraining the sketch latent to remain close to the target sketch via a token-wise cosine penalty. A single model thereby supports design-preserving optimization, dimensionally explicit design edits, and sketch-only synthesis.

We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is trained separately against the frozen teacher. It has 10x fewer parameters and needs 15x less compute. We first synthesize a corpus with the teacher and keep its durations, pitch, energy and phoneme features. We then train a small text side to predict these values, and a small decoder to turn the teacher's saved values into the teacher's audio, first with spectral losses and then adversarially. Finally, we connect the two halves and quantize the weights to int8. It needs no alignment learning and no joint training, and it runs on one laptop. Stored in int8, Paradee is 8.5 MB, runs 25x faster than real time on one CPU thread, and scores 4.41 on UTMOS against the teacher's 4.52. The student initially kept a slight buzz, which we trace to the phase of voiced speech between 2 and 8 kHz. A phase-locking filter applied after synthesis removes most of it, with no training and no extra parameters. Code, model files and audio samples are at https://github.com/sahilmahendrakar/paradee

Generative speech enhancement models can produce cleaner and more natural-sounding speech than conventional discriminative approaches, but may hallucinate by changing speech content or speaker identity, even with transcript conditioning. We present AuraSE, a flow-matching framework that addresses hallucination through complementary modality and inference designs. First, a double-stream-to-single-stream multimodal Diffusion Transformer (MMDiT) allows transcript and acoustic representations to interact while preserving a dedicated pathway for the degraded input. Second, we find that the best decoder configuration, governed by guidance scale, sampling temperature, and step count, varies substantially across utterances. This observation motivates Inference Policy Optimization (IPO), an online, on-policy preference optimization method. IPO generates multiple candidates from the current model under different inference configurations, ranks them with a multi-objective reward, and learns from their relative preferences. AuraSE-IPO ranks first on 11 of 12 metrics across the synthetic test sets and obtains the highest DNSMOS and blind-listening scores among the evaluated systems on the real DNS blind test set. At deployment, it uses a fixed $10$-step ODE decoder without classifier-free guidance (CFG) or per-utterance configuration search.

Human videos offer scalable manipulation data, but the embodiment gap between human hands and robot manipulators limits their direct use. Existing video-editing methods replace hands with rendered robots, yet inaccurate interaction reconstruction and compositing can produce inconsistent grasps and implausible robot-object occlusions. We address these failures from two complementary physical aspects: interaction geometry and scene visibility. First, an interaction-aware contact reconstruction module combines hand-object segmentation with mesh-level contact prediction to recover dense 3D contacts, then converts them into temporally stabilized grasps for parallel-jaw grippers. Second, a depth-aware compositing module uses scene and robot depth to enforce physically consistent robot-object occlusions. The resulting videos preserve the interaction structure of human demonstrations in a robot-compatible form and are co-trained with robot demonstrations. Using identical human videos and robot data, we compare against robot-only training and the original Masquerade pipeline. Across four RoboTwin tasks and two Diffusion Policy visual encoders, our method achieves the highest average success rates, with especially strong gains under out-of-distribution scene variation. Real-world deployment further shows that the proposed co-training approach improves robustness to visual distractors when the task geometry is observable, while performance on depth-sensitive grasps remains limited by the single-camera setup.

In daily life, each person exhibits unique speaking habits, leading to subtle yet consistent lip-shape variations even when pronouncing the same word. Although recent talking head generation methods have achieved impressive visual fidelity and lip synchronization, they largely overlook user-specific customization, especially the motion patterns that characterize individual speaking habits. These habits are difficult to model and capture, as their motion patterns are highly fine-grained and often similar across individuals. As a result, many approaches produce overly uniform facial motions and fail to capture diverse, person-specific articulation patterns. To address this, we propose TalkLikeYou, an efficient framework that imitates how a target person speaks in talking head generation. Our method models habit in motion-space and achieves real-time performance through Flow Matching with only one sampling step during inference. We further adopt a two-stage imitation learning strategy to capture subtle distinctions between habits, allowing users to specify a target habit through either a preset style from the dataset or a reference video. In addition, we introduce a new metric PLAD that projects mouth motions onto representative articulation axes to evaluate imitation accuracy and generation diversity. Extensive experiments demonstrate that TalkLikeYou generates high-quality talking heads in real-time and significantly improves speaking habit imitation compared with prior methods. The code is available at: https://github.com/BQ-Wang0511/TalkLikeYou

World models, which learn how environments respond to actions, are emerging as a powerful paradigm for planning through imagined futures, transforming decision-making across games, robotics and autonomous driving. Bringing this capability to manufacturing could enable process decisions on timescales inaccessible to high-fidelity simulation. Here we introduce a generative world model for localized highly dynamic laser melt pool that predicts evolution from histories of temperature and phase morphology under candidate actions. Its generative latent dynamics capture the effects of unresolved melt flow, enabling more accurate recursive rollouts than deterministic regressors under transient laser inputs. Because the learned dynamics are differentiable, the model can serve directly as a predictive control plant. Gradients through imagined futures optimize laser schedules that regulate melt-pool depth over previously unseen geometry, path, initialization. We further distil this optimization into an amortized policy that produces control actions in a single forward pass, providing a proof of concept for real deployment on machines.

Modern text-to-speech (TTS) systems can clone a target speaker from a short reference clip or be fine-tuned on a target voice, yet their behaviour on morphologically rich, lower-resource languages such as Turkish remain under-characterised. We present a systematic benchmark of four contemporary systems (Chatterbox, CosyVoice, OmniVoice, and VoxCPM2) evaluated across fine-tuned and zero-shot configurations, contrasted with a conventional VITS baseline and anchored to natural gold speech. Each configuration is scored with eighteen complementary objective metrics spanning learned naturalness predictors (UTMOS v2, DNSMOS-Pro, SCOREQ, WhisQA, AudioBox-PQ, NatScore, SpeechLMScore), intelligibility and signal-quality estimators (SQUIM PESQ/SI-SDR/STOI, Brouhaha), speaker similarity, distributional fidelity (TTSDS) and low-level acoustic descriptors. We further analyse how quality varies with utterance length and quantify long-form temporal consistency through speaker-identity and naturalness drift over chunked utterances. We release our evaluation code to support reproducible TTS evaluation.

Text-to-image generative models can produce highly realistic imagery but also raise concerns about harmful misuse. While safety mechanisms exist, systematic evaluations of their effectiveness against realistic attacks remain limited. We present a systematic evaluation of harmful content generation across five open text-to-image models using an automated pipeline that transforms legitimate news captions into unsafe prompts targeting sexually explicit content, violence/gore, harmful stereotypes, self-harm, and hate speech. We evaluate both standard models with built-in safety mechanisms and community fine-tuned variants that bypass content restrictions. A human evaluation of 1,500 generated images shows high harmful-content generation rates: 89.2% for gore-related prompts, 47.6% for sexually explicit content, 43.6% for harmful stereotypes, 46.0% for hate speech, and 34.5% for self-harm, predominantly through graphic violence. Models show substantial capability for generating violent and stereotypical content, while community fine-tuned variants are particularly vulnerable to sexually explicit prompts. Generation quality is largely preserved under harmful prompting, producing imagery of sufficient fidelity to pose risks for disinformation and abuse; FLUX.1-dev produces clearly realistic harmful images in 30.9% of cases. We further evaluate automated moderation systems and find substantial detection gaps that allow unsafe images to evade filtering. Finally, we assess synthetic image detectors and show that models trained only on benign datasets perform worse on explicit content, while more diverse training data improves detection, highlighting semantic distribution gaps in current approaches. These findings expose limitations in current generation safeguards, moderation systems, and synthetic image detection, highlighting the need for stronger defenses against misuse at scale.

Recent Text-to-Image (T2I) models achieve remarkable visual image generation performance, but they can still generate NSFW (Not-Safe-For-Work) contents, including violent or explicit images. Existing safety checker mechanisms are largely confined to pre-generation filtering (e.g. prompt-level text classifiers) or post-hoc moderation applied after an image is completely synthesized. However, adversarial attack methods operate over a much broader space. This imbalance highlights the need for a safety mechanism that intervenes during the generation process. We propose an in-generation safety framework that monitors the denoising trajectory and detects emerging NSFW signals from intermediate representations. Rather than merely detecting NSFW generations, our method applies reinforcement learning to generate safe images from NSFW prompts. By coupling in-generation detection with controllable steering, our approach mitigates unsafe trajectories even when NSFW signals emerge after generation has already begun. Experiments results show that our method consistently outperforms existing safe image generation methods across both standard and adversarial evaluation sets, while preserving perceptual quality and prompt fidelity. Code will be released upon acceptance.

Sliders provide an intuitive interface for continuous image editing. In current generative approaches, however, the slider is simply a rescaling of the method's strength parameter, such as an adapter coefficient, a prompt weight, or an interpolation factor. This strength relates poorly to perceptual change. The image can partially revert as the slider moves, long stretches of the range produce no visible difference, and short intervals transform the image abruptly. Remapping the strength could fix this uneven pace, but only if the trajectory is monotone, which current methods do not enforce. We therefore distinguish the slider from the strength, and require perceptual distance from the input to grow linearly with the slider value. We introduce UniSlider, a lightweight LoRA trained on a few-step editing backbone so that its strength approximates this ideal slider. Few-step sampling lets us impose this objective in pixel space without intermediate ground truth, and the backbone's output is preserved at full strength. However, a low-rank adapter cannot make the strength fully uniform. Our slider is thus an inference-time remapping of the strength, obtained by adaptive sampling. Since training optmizes to make the trajectory monotone, this remapping closes the remaining gap without extra training or parameters. On a new benchmark of 300 continuous edits evaluating uniformity, monotonicity, edit fidelity, and identity preservation, UniSlider outperforms all prior methods and is preferred in a user study.

Rapid progress in video generation has led to a plethora of models that differ substantially in capability and generation cost. This raises a natural question: can each request be efficiently routed to an appropriate model? We find that even when the consensus of the other annotators is used as an oracle, it agrees with each annotator's own favorite only 34-55% of the time. Motivated by this observation, we introduce TasteRoute, a personalized video-generation router that selects a generator jointly based on the input request, user preferences, and available generation budget. Across text-to-video and image-to-video settings, TasteRoute is competitive with strong simple baselines on preference routing while reducing average generation cost. The cost saving increases under higher budget caps. Finally, we release TasteRoute-3k, a human-annotated dataset containing multi-model video comparisons, quality judgments, preference rankings, and user-profile signals to facilitate future research on personalized and cost-aware video routing.

Embodied world models predict the visual consequences of candidate actions before execution. However, existing action-conditioned world models often adopt uniformly weighted visual generation objectives that can be misaligned with embodied prediction needs. Even with explicit motion conditioning, these objectives can underemphasize spatially sparse changes that are critical to interaction. We propose KineWorld, a transport-aware world-modeling framework that extends robot kinematics from motion conditioning to the spatial allocation of generative supervision. Kinematic Transport Lifting (KTL) constructs renderer-derived, camera-aligned transport fields from commanded robot motion. Transport-Aware World Diffusion (TAWD) calibrates their motion support on the video-latent grid and reweights future-RGB flow matching through a normalized mixture of uniform and transport-focused distributions. We train KineWorld using ALOHA-AgileX bimanual manipulation data from RoboTwin 2.0. KineWorld achieves an EWMScore-P of 68.95 in single-view evaluation and a TWB-Score of 54.82 in multi-view evaluation. These results support a shift from appearance fitting toward action-consequence modeling for embodied decision-making.

Sound morphing, generating intermediate sounds that transition from one sonic identity to another, can be a powerful tool for musical sound design. Existing diffusion-based morphing approaches entangle temporal structure and timbral identity, offering no mechanism to hold one fixed while transforming the other. We present smorph, a training-free guidance framework that preserves how a sound behaves over time while transforming what the sound is, allowing users to morph, for instance from brass to strings at a fixed pitch. We demonstrate across three morphing modes: prompt-to-prompt, audio-to-prompt, and audio-to-audio. Evaluations across diverse datasets show that smorph effectively produces smooth morph trajectories while substantially improving temporal-structure and source preservation over baselines, albeit with more conservative target-ward transformation in some settings. In an exploratory case study, musicians found smorph trajectories to be expressive and playable, suggesting structural anchoring can serve as a productive constraint for instrumental interaction.

Diffusion models have greatly advanced instruction-guided image editing, while also raising concerns about unauthorized image manipulation. Image immunization addresses this risk by adding imperceptible perturbations to an input image to disrupt subsequent edits. Since editing requests are unknown at image release, protection should remain effective beyond the instruction used to construct the perturbation. Existing immunization methods either require costly full-trajectory backpropagation or use intermediate objectives whose effects may be weakened by subsequent denoising. Meanwhile, a single inference path provides limited feedback about alternative denoising continuations. To address these challenges, we propose \textsc{SPIN}, a framework for image immunization via one-step projection over local stochastic trajectory neighborhoods. Starting from an early denoising state, \textsc{SPIN} generates stochastic neighboring states under the same instruction and predicts their clean latents through one-step projection without full unrolling. We then optimize a bounded input perturbation to maximize the average deviation of these predictions from a clean-edit reference, encouraging the perturbation to disrupt multiple possible editing outcomes. Experiments on two image editors demonstrate substantial gains in protection performance, with \textsc{SPIN} outperforming compared methods across all six metrics under seen instructions and in the more challenging unseen instruction setting.

Neurons of the brain exhibit a rich repertoire of electrophysiology dynamics with the same repeated stimulus eliciting very different voltage responses from the same cell. One common approach in biophysically detailed models is to capture this variability through ensembles of deterministic parametrizations, at a cost of hundreds of thousands of CPU hours. Existing machine learning surrogates inherit the same limitation, where a stimulus is mapped to a single voltage response. We address this challenge by learning a conditional generative model for single-neuron electrophysiology, using flow matching with a velocity field conditioned on the input current. On biophysically detailed models of two human cortical interneuron types, the generated responses closely reproduce the electrophysiological feature distributions, spike-time structure, and excitability profiles, even matching the experimental recordings from the corresponding human cortical neurons. Near the firing threshold, firing and non-firing responses coexist at the same stimulus amplitude, and at high amplitudes, ensembles may split into low- and high-firing modes near depolarization block. We show that our model recovers both modes in each case, while a neural operator baseline suppresses spiking near threshold and blurs the gap between modes at depolarization block.

Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimodal attention, forming dynamic contextual tokens whose function is not well understood. In this work, we introduce a framework for reading this contextual space through natural-language interrogation. We train a lightweight bottleneck network that maps intermediate contextual tokens into the input space of a frozen Large Language Model (LLM), allowing the LLM to answer questions about the emerging image directly from these hidden representations. Our reader reveals that contextual tokens encode a rich, global representation of the emerging scene: generation-specific semantics, including attributes left underspecified by the prompt, are accessible surprisingly early in denoising, while increasingly fine-grained details become readable over time. Remarkably, this information remains decodable even when the MM-DiT receives an empty prompt, showing that contextual tokens accumulate substantial image-specific information from the evolving visual representation itself. We further find that generations with more readable contextual representations tend to receive higher human-preference scores. Building on these observations, we introduce Contextual Alignment, a training technique that explicitly reinforces the visual-semantic information encoded in the contextual tokens, improving generation quality and distributional coverage. Together, our results establish contextual tokens as both an interpretable view into the internal dynamics of MM-DiTs and an effective target for improving generative models.

Compressive Synthetic Aperture Radar (SAR) imaging, typically formulated as an inverse problem and solved with traditional iterative optimisation methods, can be very computationally expensive. We investigate the use of denoising diffusion probabilistic models (DDPMs) for compressive SAR image reconstruction, where the diffusion model is guided by a poor initial reconstruction from sub-sampled data obtained via standard imaging methods. We augment this data-driven method with model-driven interleaved refinement processes, inspired by traditional compressed sensing (CS) methods, to enhance sparsity and heavy tails in SAR images. Experimental results on real ERS-1 SAR datasets demonstrate consistent improvements over baseline DDPM and state-of-the-art methods, with notable gains in reconstruction fidelity and structural similarity, while incurring only modest computational overhead. The proposed hybrid framework effectively combines the representational power and efficiency of diffusion models with the interpretability and robustness of model-based optimisation, enabling accurate compressive SAR imaging.

Modern graph generative models typically operate directly in the discrete graph space, explicitly generating node and edge variables, which can become costly as graphs grow. In this paper, we perform generation explicitly on latent representations of entire graphs obtained from a pretrained Variational Autoencoder with high reconstruction fidelity. The generated representations, obtained through flow matching, are then decoded only at the final step. Across molecular benchmarks of increasing size, our approach achieves strong validity and FCD while offering a favorable quality-efficiency trade-off compared with state-of-the-art explicit graph generative models. One of the main advantages of this formulation is that the graph representation only needs to be learned once, after which the same one can be reused across multiple generative objectives without retraining. We demonstrate generation guided by molecular properties and further introduce validity-aware generation though a classifier learned directly in latent space. All code will be made available upon acceptance.

Deep learning has revolutionised weather forecasting in recent years, especially through atmospheric foundation models, which offer competitive skill for a fraction of the computational costs of classic physics-based models. However, most existing foundation models are deterministic, limiting the generation of large ensembles for accurate uncertainty quantification, extreme weather risk assessment, and long-range weather forecasting. Furthermore, these models incur a large, often prohibitive, computational overhead to train from scratch. To address these shortcomings, we turn a pretrained deterministic prior model, namely the Aurora foundation model, into a generative ensemble-prediction model. To that end, we introduce a novel generative method, Denoising Stochastic Interpolants, combined with a replay buffer for Stochastic Differential Equation (SDE) rollout, enabling probabilistic training of SDE trajectories. Our stochastic foundation model, Xaurora, is finetuned from the small Aurora version, yet it approaches the state-of-the-art on global ensemble metrics and is competitive with the large version of Aurora. Our method is parameter and sample efficient, and generates skilful 15-day forecasts in 13 minutes. Our results demonstrate that deterministic foundation models can be efficiently extended into even stronger stochastic models.

Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-distribution data from procedural generators, continue to violate physical laws and simple symbolic rules. We introduce Serial-to-Parallel Diffusion (S2PD), which performs autoregressive diffusion at high noise before switching to parallel diffusion at low noise. The autoregressive phase provides the serial computation needed to coordinate interdependent events and produce valid state transitions while the parallel phase jointly refines the entire video and reduces sampling time relative to fully serial generation. We implement S2PD with two architectures: a pixel-space diffusion transformer trained from scratch and a pretrained video model adapted through LoRA fine-tuning with causal attention. Across games, physical simulations, and real video, S2PD follows rules more reliably than matched bidirectional baselines and generates videos with greater temporal stability and sampling efficiency than other serial methods.

Masked diffusion language models (dLLMs) generate text by iteratively denoising masked positions, re-predicting each token multiple times before it is committed. An autoregressive decoder exposes an answer's distribution once, at the step that commits it; a dLLM exposes it at every denoising step before commitment, and we show that an adversary can exploit this. Since an answer remains open to revision over many denoising steps, an adversary with access to internal activations can watch how likely the model is to produce a chosen answer and adjust the intervention accordingly. Building on this observation, we study targeted bias injection, an attack that steers a frozen dLLM toward a demographic answer selected by the adversary. The attack uses a simple proportional-integral (PI) controller that tracks the target-answer probability during denoising and adapts the strength of a steering vector on the fly. On ambiguous BBQ questions where the correct answer is abstention, our attack raises LLaDA-8B-Instruct's preference for the targeted group from 1.8 to 16.7 percentage points, more than three times the strongest fixed-strength steering baseline, and on SocialStigmaQA it raises the selection of stigmatizing answers from 17.6% to 58.1%. Fitted to other demographic targets, the same attack shifts answers by up to 37 percentage points, and each attack takes about 40 minutes on one GPU. On the primary target, feedback is what makes the attack work: constant steering at the same average strength over the token-committing steps produces a far smaller shift while corrupting nearly three times as many outputs, and a constant strength set separately for each example still falls well short. Our findings identify the denoising trajectory as a new control channel in dLLMs and call for bias audits that examine the serving stack rather than the frozen model alone.

We introduce a post-training method for diffusion language models (DLMs) that minimizes Maximum Mean Discrepancy (MMD) between generated and reference distributions in the feature space of a frozen pretrained DLM. To estimate MMD, we retain contextual features at individual token positions, obtaining multiple observations per sequence from a single extractor pass. We optimize this objective using policy gradients for discrete models and direct differentiation through generated latents for continuous models. In both cases, computing the loss directly from these features enables efficient post-training without full sampling trajectories or jointly trained auxiliary models. Experiments show lower generative perplexity at comparable entropy on OpenWebText and better accuracy-computation trade-offs on GSM8K. On 16B DMax-LLaDA2.0 models with hybrid masked-uniform diffusion, we increase decoding parallelism with similar or higher accuracy on math and code benchmarks.

Pretrained diffusion models provide powerful image priors for training-free posterior sampling in image restoration. To guide this sampling process, frequency-aware methods progressively incorporate measurement information across frequency bands, facilitating coarse-to-fine reconstruction. However, existing methods typically do not explicitly separate frequency activation from degradation-induced attenuation, leaving attenuation differences among inactive frequencies insufficiently modeled. In this work, we propose frequency-decoupled posterior guidance to separate frequency activation from attenuation-aware spectral regularization. Specifically, a progressive low-to-high frequency schedule determines the active measurement band, while a kernel-derived attenuation map defines a selective spectral prior over inactive components. To stabilize the sampling process, we also introduce a local trajectory regularizer that suppresses spatially irregular state-to-clean deviations. For a fixed endpoint energy, we provide a KL-regularized path-space interpretation. In practice, we construct time-dependent guidance through local energy corrections using a Tweedie plug-in approximation. Experiments on natural-image benchmarks demonstrate strong PSNR and SSIM performance across challenging non-blind deblurring settings, even at higher measurement noise levels.

In generative models, Optimal Transport (OT) is used to improve Flow Matching (FM) by reducing noise-data coupling cost. However, different noise-to-output assignments can yield nearly equal costs, raising a key question. Is cost alone sufficient to guide coupling design? We address this question by separating transport cost from routing, i.e., the destination reached by each noise sample. We show numerically how FM and OT can differ in routing while remaining close in cost. We examine its consequences in learned neural FM. Using the exact FM routing as an oracle, we further construct a routing-aware training coupling and find that it yields a directionally consistent improvement in generation over a cost-matched, cost-only counterpart. Our findings highlight what cost minimization can overlook and motivate using both cost and routing to evaluate the design of OT-based FM couplings. Code will be released upon acceptance.