多模态生成与编辑

Autonomous robots operating in dynamic environments require behaviour planning systems that combine reactivity, interpretability, and adaptability. While Large Language Models have been successfully integrated with Behaviour Trees for dynamic replanning, Finite State Machines, despite their widespread adoption and computational efficiency, remain unexplored for generative approaches. We propose a Generative Partially Specified Finite State Machine (GPSFSM) neurosymbolic architecture that utilises the symbolic and semantic structure of FSMs, including states and event-triggered transitions, to implement Behaviour Planning. This paper introduces the first GPSFSM framework for robotics, featuring Fabric, an FSM engine that parses, validates, and executes behaviour plans that contain Sequential, Recovery, Parallel-Any, and Parallel-All control structures. We extend the Capabilities2 package in ROS2 with an asynchronous event system for behaviour chaining and runtime parameter injection for configurable execution, addressing the ad-hoc function representations that limit current generative systems. PromptTools provides a unified ROS 2 interface to local and cloud LLMs, with prompt buffering, enabling dynamic asynchronous composition of task and context information. Together, these components enable standardised semantic capability descriptions for robot-agnostic development. Experimental evaluation on navigation tasks demonstrates that our GPSFSM approach achieves consistently higher plan-generation success rates than the state-of-the-art BTGenBot system, particularly excelling in zero-shot scenarios where BTs typically struggle, while maintaining comparable or lower planning latency to frontier LLMs. We also demonstrate that our system can generate complex behaviours. We release an open-source ROS2 stack that makes generative FSM planning practical and reproducible for robotic systems.

Visual grounding with multimodal large language models is commonly formulated as autoregressive coordinate generation, where a model outputs bounding-box coordinates as text given an image and a referring-expression prompt. While this interface is simple and compatible with instruction following, it introduces a mismatch between training and evaluation: training optimizes token-level likelihood over coordinate strings, whereas grounding quality is measured by geometric overlap. We propose IoUPD, an IoU-aware privileged distillation method for coordinate-generating multimodal large language models. IoUPD uses ground-truth boxes not only as coordinate targets, but also as privileged training-time guidance. During training, the student receives the original image and prompt, while a frozen teacher receives a box-marked image and an augmented prompt that indicates the marked region. The student is trained with a supervised fine-tuning anchor and a privileged distillation loss whose token weights reflect both geometric importance and teacher reliability. At inference time, IoUPD requires no box overlay, privileged hint, teacher branch, or additional prediction module. Experiments on standard referring-expression grounding benchmarks show consistent region-level improvements over strong coordinate-generating baselines, demonstrating that ground-truth boxes can provide useful privileged guidance beyond serving as coordinate labels.

Current world models operate at a single level of abstraction, with most prioritizing perceptual fidelity while lacking the spatial reasoning and semantic understanding required for real-world downstream tasks. We present a hierarchical driving world model that factorizes future prediction across two levels operating at distinct temporal and abstraction scales: a high-level predictor that forecasts coarse scene structure over extended temporal horizons, and a low-level generator that produces detailed predictions conditioned on the high-level output. This decomposition yields high perceptual fidelity while also capturing strong spatial and semantic representations. We further show that pretraining with a diffusion forcing objective yields substantially richer internal representations than the standard teacher forcing objective, while teacher forcing — predicting only the next frame from clean context — produces more stable autoregressive rollouts. We therefore introduce a generic two-stage training paradigm that pretrains the model with diffusion forcing and fine-tunes with teacher forcing, combining the representational benefits of the former with the rollout stability of the latter. Our approach achieves state-of-the-art results across the standard suite of driving world model evaluations on established benchmarks, including long-horizon generation fidelity, steering responsiveness evaluated on counterfactual scenarios, and internal representation quality. Project page with code, demo, checkpoints and qualitative results: https://lmb-freiburg.github.io/orbis2.github.io/

Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such a design forces the denoiser to simultaneously perform relation-dependent cue selection, cross-modal semantic alignment, and structure-aware entity generation, which introduces noisy and semantically inconsistent conditions for diffusion and consequently leads to suboptimal completion performance. To address this limitation, we propose MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts (MGDT), a novel MKGC framework built on an align-then-diffuse paradigm. MGDT first employs a Relation-Adaptive Semantic Routing Mixture-of-Experts (RASR-MoE) module to select relation-relevant multimodal semantic transformation paths and suppress irrelevant modality interference. MGDT then uses a frozen Multimodal Large Language Model (MLLM) as a semantic anchor to align the routed multimodal representations into a unified latent space and reduce cross-modal semantic heterogeneity. Finally, a Knowledge Graph Diffusion Transformer (KGDT) performs graph-conditioned denoising generation in the aligned space to produce the missing entity representation. Experiments on three benchmark datasets show that MGDT consistently outperforms strong baselines.

Autoregressive video diffusion models have enabled the generation of arbitrarily long videos by removing conditioning on future frames, thus greatly improving computational efficiency. Yet, they suffer from error accumulation over time, as the denoised sequence gradually drifts away from the conditioning distribution seen during training. Recent advances attempt to reduce this error by anchoring each generated frame to the learned manifold of real ones. However, even when all generated individual frames lie close to the real manifold, there are trajectories which the model lacks sufficient knowledge to continue without exiting it, thus reaching a terminal point. To prevent the model from being trapped in terminal points, we start from the hypothesis that for well-modeled future trajectories the distribution of the predicted noise should match the one of the forward noising process. To enforce such a prior at test time, we introduce Terminal points Avoidance through Noise Guided Optimization (TANGO), which uses the diffusion model as a critic of its own outputs, by predicting one step forward and requiring an isotropic Gaussian noise prediction. We use the deviation from this expected noise distribution to search for an alternative trajectory that does not lead to a terminal point. Our approach achieves a $3.1%$ absolute improvement on VBench over state-of-the-art, while reducing Fréchet Video Distance by $28.3%$ on average across $15$s videos. Our code is available on https://mever-team.github.io/tango.

Multi-reference image generation aims to synthesize images by integrating attributes from multiple reference images under textual instructions. As the number of references increases, the task necessitates complex semantic comprehension, such as correctly associating attributes with the intended subjects and planing out coherent spatial arrangement between subjects and their environments. Existing approaches, which rely solely on natural language instruction, often fail to capture these complex intentions precisely, leading to semantic misalignment and inconsistent generation. We identify two key factors behind these limitations: natural language instructions are often verbose and ambiguous, and high-quality multi-reference data is scarce. To address these issues, we propose StructGen, which employs a structured, dictionary-like format to encode multiple reference images, thereby enabling explicit and unambiguous specification of generation intentions. To support this design, we construct a structured dataset based on high-quality real images and develop a corresponding training framework, along with a dedicated benchmark for challenging multi-reference scenarios. Extensive experiments on both public benchmarks and our proposed benchmark demonstrate that StructGen consistently outperforms existing methods on both semantic alignment and detailed reference-generation consistency, especially under complex instructions with multiple references. The code is available at https://jianingpeng0382.github.io/StructGen/

Equipping humanoid robots with coherent and adaptable personas is crucial for fostering natural, engaging, and trustworthy human-robot interaction (HRI). However, existing approaches often rely on static, hard-coded identities that lack the flexibility to adapt to individual user contexts. In this paper, we present PACE (Persona Adaptation through Conversational Elicitation), a novel framework for the interactive generation and deployment of structured personas on the Ameca humanoid robot. Our system introduces an Interactive Persona Elicitation Pipeline, enabling the robot to dynamically synthesize a tailored, psychologically grounded identity through user Q&A. This elicitation process feeds into a persona prompt compilation phase, generating a structured persona prompt built upon multi-perspective dimensions. We detail the Embodied System Integration required to translate this structured specification into expressive, multimodal humanoid behaviors. Through a comprehensive empirical HRI evaluation, we assess the impact of dynamically generated personas on user trust, perceived anthropomorphism, persona consistency, personal relevance, and interaction quality compared to a generic baseline. These contributions establish a scalable pathway for deploying personalized, interactive, and reliable identities in embodied humanoid assistants. Video demo is available at: https://lipzh5.github.io/PACE/

Maintaining recurring character identities across scene transitions and long temporal gaps is a central challenge in narrative long video generation. Methods targeting global consistency often retrieve memory using cues that are not aligned with character identity preservation, while recent character-centric variants still rely on coarse frame-level kv memory that entangles identity with incidental visual factors and lacks a continuous update mechanism under limited memory capacity. To address these limitations, we propose SlotMem, a character-addressable internal memory framework for multi-character narrative long video generation. Specifically, SlotMem uses a Character-Semantic Probe to localize character-relevant visual tokens from cross-attention responses, and a Memory Encoder to compress DiT tokens into compact role-wise slot memory. As generation proceeds, a Memory Writer conservatively updates each character's memory with new observations, while Character-Wise Cross-Attention retrieves the role memory and injects it only into localized tokens of the same character. Experiments on multiple narrative long video generation benchmarks show that SlotMem improves long-range character consistency over existing baselines, while maintaining comparable video quality. Our code is available at https://github.com/YilaiLiu-HKU/SlotMem.

As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI. Existing T2I evaluation metrics and multimodal judges often rely on visual-semantic representations that underrepresent implicit cultural norms, leading to biased preference judgments and the omission of fine-grained cultural cues. In addition, visual question answering (VQA)-based evaluators typically depend on autoregressive text generation, which limits their scalability for real-time reward modeling. To address these limitations, we introduce an Implicit Cultural Alignment Reward Model built upon a lightweight 4.2-billion-parameter Multimodal Large Language Model (MLLM). Our framework integrates an Implicit Cultural Probe with a Skip-connection Cross-Attention (SkipCA) mechanism, enabling late-stage semantic features to directly attend to early-stage visual representations and better preserve culturally salient details. Evaluations on 3,323 challenging and carefully curated image pairs from the CulturalFrames benchmark show that our approach achieves 80.54% pairwise accuracy, with Pearson and Kendall correlation coefficients of 0.546 and 0.377, respectively, outperforming representative vision-language metrics and MLLM-based evaluators. Moreover, by bypassing autoregressive text generation, our model processes each evaluation in 0.21 seconds under our local inference setup, achieving a $10\times$ speedup over standard VQA-based evaluators. These results suggest that the proposed reward model can provide an efficient and culturally aware scalar signal for preference optimization pipelines such as Reinforcement Learning from Human Feedback and Direct Preference Optimization.

Artistic charts make data memorable and visually engaging, but generating them faithfully demands simultaneously preserving numerical geometry, rendering exact in-image text, binding labels to correct marks, and maintaining coherent artistic style. Current text-to-image and image editing models frequently fail on these coupled constraints, producing distorted geometries, hallucinated text, misbound labels, or over-stylized marks that undermine readability and mathematical integrity. This paper introduces ArtChart, a framework for artistic chart generation with integrated text rendering, encompassing a task definition, benchmark, and evaluation protocol. This is the first work to simultaneously address mathematically faithful chart synthesis, accurate in-image text rendering, and artistic stylization of chart elements. ArtChart features a chart-specific plug-and-play module conditioned on text-free grayscale chart layouts, ensuring mathematical and logical fidelity. A RL learning strategy with OCR accuracy, layout quality, and aesthetic rewards refines generation, while a multi-expert distillation framework resolves inter-reward conflicts through specialized expert optimization. We construct ArtChart-Bench, a bilingual 2K-prompt benchmark spanning four chart types and diverse label formats. We further design ArtChart-Eval, a six-axis evaluation suite covering mathematical logic, text accuracy, text layout, aesthetics, instruction following, and readability, supporting comparison across T2I, image-editing, controllable-generation, and closed-source API models. Extensive experiments demonstrate that ArtChart consistently outperforms open-source baselines, producing charts that are both visually appealing and math faithful.

Diffusion Transformers have recently achieved strong performance in video generation, yet controlling scene geometry under viewpoint changes and camera motion remains challenging. In this work, we revisit the role of positional encoding in video diffusion transformers and show that it provides a useful spatial bias for geometry-aware control. Specifically, if reference tokens are encoded according to their projected locations in the target view, the denoising model is encouraged to retrieve content from position aligned regions of the input video. Building on this observation, we introduce a geometry-aware cross-attention mechanism that enables target video latent tokens to attend to structured context tokens derived from reference images or frames. To establish correspondence between the reference content and the target camera trajectory, we equip the context tokens with a projected positional encoding scheme that combines target-view 2D reprojection with depth-aware disambiguation. At the same time, we preserve the original spatiotemporal positional encoding of the generated video latent, allowing geometric guidance to be injected while maintaining consistency with the video model's native latent structure. The resulting framework provides a simple and effective approach for controllable video generation. It improves spatial controllability in viewpoint-dependent editing tasks, including camera re-trajectory, novel-view video synthesis, and geometry-aware video editing, while preserving the generative prior of the underlying video diffusion model. The code is available at: https://github.com/MTLab/PE-Field.

Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention reduces this cost, but adaptive Top-$p$ routing creates uneven per-head workloads under multi-GPU sequence parallelism. The resulting workload heterogeneity turns sparse attention into a rank-level straggler problem. We present \method{}, a training-free sparse-attention system that improves the distributed execution efficiency of adaptive sparse attention under multi-GPU sequence parallelism. \method{} uses Top-$p$ routing, a Top-$k$ safety floor, and video-aware block organization as the sparse-routing frontend, then repairs the materialized mask at runtime. Runtime Load Balancing migrates a small number of heavy heads via P2P communication to shorten the current critical path. Slack-Aware Sparse Augmentation fills residual non-critical-rank slack with additional high-value blocks, while overlap hides scheduling and migration overhead behind existing computation. On step-distilled Wan2.2 I2V, \method{} reduces average load imbalance from 1.34 to 1.08 and delivers a $4.41\times$ attention speedup over FlashAttention, while achieving a $2.02$--$2.11\times$ DiT inference speedup with competitive video quality.

Diffusion Transformers (DiTs) have been widely used in many tasks, including image synthesis, video generation, and content editing. However, their multi-iteration inference process leads to performance inefficiency and high energy consumption. Existing acceleration methods primarily focus on reducing temporal redundancy between adjacent timesteps, but often overlook the specific features of DiTs. As a result, these approaches either suffer from great accuracy degradation or fail to achieve high efficiency. We present DSTAR, a software-hardware co-design framework that accelerates DiT inference by reducing spatial and temporal redundancy. At the algorithmic level, DSTAR introduces a fine-grained mixed-precision quantization method for differential activations in linear operations, significantly increasing the proportion of low-bit computations. Additionally, DSTAR incorporates a sparse attention reuse mechanism to minimize redundant computation in attention layers. For architectural support, we design a specialized hardware accelerator which achieves high efficiency in both latency and energy consumption. Evaluation on seven typical DiTs demonstrates that DSTAR achieves up to 7.33x latency speedup and 41.89x energy savings compared to an NVIDIA A100 GPU, and achieves up to 2.54x latency speedup and 3.68x energy savings compared to SOTA accelerators, without accuracy degradation.

We present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation. AI for Science (AI4S) has advanced significantly through domain-specific models, tool-augmented LLMs, and scientific language models. However, model capabilities remain highly fragmented, limiting the joint modeling of heterogeneous data, scientific laws, and expert knowledge. S1-Omni addresses this gap by consolidating these capabilities into a single, coherent scientific reasoning model. The architecture of S1-Omni is built upon three core components: unified representation of scientific data, natural-world knowledge alignment, and decoding for domain-specific tasks. First, S1-Omni maps natural-language instructions and scientific objects, including CIF, SMILES, protein sequences, spectra, and scientific images, into a shared representation space. Second, it incorporates scientific laws and expert knowledge into data construction and training, enabling the model to reason from scientific evidence. Third, it performs task-specific decoding to support a broad range of applications, including property prediction, spectrum-to-molecular generation, protein site and structure prediction, and scientific image generation and editing. S1-Omni is trained on S1-Omni-Corpus, which covers 200 scientific tasks and contains millions of reasoning samples, and is evaluated on over 60 scientific benchmarks. It outperforms GPT-5.5 and Gemini-3.1-Pro on most benchmarks and matches or surpasses domain-specific models on several benchmarks. Overall, S1-Omni provides a practical path toward unified scientific modeling.

Rare concept generation focuses on synthesizing customized images conditioned on text prompts that describe objects with unusual attributes. Previous works failed to align the generated images with rare concepts, resulting in incorrect attribute rendering or inconsistent composition of concepts. Such failures, as we observed, stem from the inherent common knowledge bias in the training stage of diffusion models, where objects are strongly associated with their common attributes, making it difficult to break these associations when generating rare concepts. To address such challenges, in this paper, we propose a novel Counterfactual Inference-based Diffusion approach, dubbed CI-Diff. CI-Diff blocks the interference of the model's inherent common knowledge bias and utilizes the Natural Direct Effect to capture the independent influence of the text prompt of rare concepts on image generation so that decoupling the unusual attributes from the rare concepts. To this end, we reformulate the classifier-free guidance mechanism to highlight the atypical attributes. To the best of our knowledge, we are the first to introduce causal inference into the rare concept generation task. Extensive experiments on the RareBench benchmark validate the superiority of CI-Diff over state-of-the-art diffusion models. Our code can be accessed from https://github.com/200204jzy/CI-Diff.

Understanding driver emotion and state is critical for the next generation of intelligent in-cabin systems that ensure safety and enhance human-vehicle interaction. However, existing public datasets for in-cabin affective computing are largely limited to visual modalities and rarely include conversational information, making it difficult to capture the linguistic and interactive cues underlying driver emotion. To address these gaps, we introduce InCarEmo, a multimodal dataset for in-cabin emotion recognition and driver state monitoring. InCarEmo integrates RGB and infrared video, in-cabin audio, and dialogue text collected from scripted in-cabin scenarios designed to simulate realistic driver behaviors, covering diverse lighting conditions and driving contexts. The dataset supports three primary tasks: 1) multimodal emotion recognition, 2) fatigue detection, and 3) distraction monitoring. In addition to the original Chinese data, we construct an auxiliary English benchmark to support preliminary cross-lingual evaluation. We provide a unified benchmark with extensive baseline results across unimodal and multimodal methods, including analyses under modality-missing and noise conditions. Experimental results demonstrate the benefits of multimodal fusion and reveal remaining challenges under real-world noise and low-light conditions. By releasing InCarEmo, we aim to establish a comprehensive foundation for robust, interpretable, and human-centric in-cabin affective understanding, promoting safer and more empathetic driver-vehicle interaction.

We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persistent context in which a video unfolds, including the environment, scene, subjects, ambient acoustic conditions, voice characteristics, and other relatively stable conditions. The event stream is everything that changes over time within that world, including scene or environmental changes, subject behavior, speech, and other sounds. This yields a general-purpose pretraining task over large amounts of real video: given a world and incoming input, predict how the world moves, changes, and responds in real time. The resulting competence can be specialized to a broad family of real-time downstream tasks. We instantiate it on real-time full-duplex audio-visual interaction, where the event stream is the agent's speech together with free-form behavior. Functionally, the model's multimodal understanding process is vision-language-action-like: it maps multimodal user input to language-form speech and behavior actions. Wan-Streamer v0.3 preserves the v0.2 operating point: 640x368 video at 25 FPS, a 160 ms streaming unit, approximately 200 ms model-side response latency, and approximately 550 ms total interaction latency under a 350 ms bidirectional network budget.

Tactile image generation significantly reduces the dependency on expensive and wear-prone sensors by synthesizing high-fidelity tactile data, offering an efficient solution for tactile information acquisition in robotic perception and human-machine interaction systems. However, existing methods depend on large-scale, diverse datasets from specific sensors and lack efficient data utilization and robust generalization capabilities, struggling in vision-limited environments. To address this, we introduce VQ-Touch, a tactile generation framework that supports both cross-sensor and multi-scenario applications. Specifically, to efficiently extract complex deformation and texture features from the data, we propose DM-VQGAN, an effective tactile representation learner. Furthermore, we introduce a discrete diffusion decoder with a unified conditioning interface, supporting multimodal generation tasks such as images and labels, and enhances the model's generalization capability through few-shot mixed training, thus achieving compatibility with current mainstream sensors and their variants. Experiments show that VQ-Touch surpasses state-of-the-art methods in multiple tasks.

MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-specific objectives. In particular, DiffusionNFT offers an efficient forward-process RL framework that does not require reverse-process trajectories or likelihood estimation. However, applying such RL methods to MeanFlow remains underexplored. DiffusionNFT optimizes instantaneous velocities, whereas MeanFlow samples with average velocities. To bridge this gap, we introduce MeanFlowNFT. Inspired by the MeanFlow identity, which bridges average and instantaneous velocities, we construct an induced instantaneous-velocity predictor. We apply the DiffusionNFT objective to this predictor, making reward optimization well-defined for MeanFlow. Sampling remains based on the average velocity, preserving MeanFlow's fast few-step generation. We further prove that MeanFlowNFT inherits DiffusionNFT's strict policy-improvement guarantee. Experiments on image and video generation show that MeanFlowNFT consistently improves baselines. Moreover, it outperforms prior state-of-the-art RL-tuned few-step generators on most metrics ($6$ of $8$ on SD3.5-M), and can even surpass multi-step RL-tuned diffusion while using only a few sampling steps. For instance, on Wan 2.1, $4$-step MeanFlowNFT reaches a VBench score of $84.33$, surpassing $50$-step LongCat-Video RL ($82.57$).

Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating many rollouts quickly. This creates a bottleneck for diffusion-based world models: multistep sampling makes each rollout expensive, limiting large-scale action search at inference time. We introduce DriftWorld, an action-conditioned world model based on drifting generative models. Rather than denoising iteratively at inference, DriftWorld learns an action-conditioned drift during training, allowing it to generate future frames from the current observation and a candidate action sequence in a single forward pass at 30+ fps, which is 17x faster on average than diffusion based baselines. We evaluate DriftWorld on standard vision-based robotic manipulation benchmarks, including Bridge-V2, RT-1, Language Table, Push-T, and Robomimic. By producing rollouts that are both accurate and fast, DriftWorld achieves state-of-the-art decision-making performance with far less inference time than diffusion-based world model baselines. Beyond online control, DriftWorld can also serve as an offline simulator for ranking real-world robot policies, with rollout-based scores correlating with ground truth at up to 0.99. These results show that drifting models are a strong fit for robot world modeling, where fast, high-quality imagination directly supports planning and policy evaluation.

World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, while the world models themselves are rarely studied in isolation. We examine five representative visual world-model agents in Atari Pong: DreamerV3, DIAMOND, TWISTER, Simulus, and STORM. After reproducing their training pipelines and matching the reported agent performance, we freeze the learned world models and evaluate them with a closed-loop rollout diagnostic: a policy trained separately from the corresponding MBRL agent interacts with each frozen model, and the generated video trajectories are inspected for visual and dynamical errors. Across all five models, the rollouts contain clear failures, including ball disappearance, incorrect ball motion, and invalid ball-paddle interactions. Beyond visual trajectories, we further evaluate them with pixel-space zero-shot MBRL, where a new policy is trained entirely inside a frozen world model and then evaluated in the real environment. Across all five models, the resulting policies substantially underperform those produced by the corresponding original MBRL training pipelines. The gap is particularly large for DreamerV3, whose mean return drops from -5.5 to -20.9, near the minimum Pong return of -21. We hypothesize that insufficient modeling of task-critical concepts, such as the ball in Pong, may contribute to these failures. We therefore propose Concept-Guided Spatial Regularization (CGSReg), an auxiliary pixel reconstruction loss applied to segmented concept regions. Experiments show that CGSReg improves both closed-loop rollouts and pixel-space zero-shot MBRL in DreamerV3, DIAMOND, and TWISTER. Its effects vary across the remaining models and evaluation metrics, indicating that CGSReg alone does not address all world-model bottlenecks.

Video object removal is a fundamental yet challenging task in video editing. Despite recent progress, existing methods typically fall into two categories. Traditional approaches based on optical flow or attention mechanisms often introduce noticeable artifacts and yield unnatural results. In contrast, diffusion-based methods improve visual realism but demand multiple denoising steps, limiting their practicality. To address these issues, we propose From-Draft-to-Draft-Free (D2DF), a framework that distills the ability of transforming coarse drafts into refined videos into a one-step video generation model. Within D2DF, a teacher model is trained to refine low-quality removal results ("drafts") into high-fidelity videos by multiple steps. Then, through Prior-Privileged Consistency Distillation (PPCD), we distill this capability into a student model that performs one-step removal conditioned on the draft. To eliminate draft dependency, we introduce a Self-Guided Fast Planting (SGFP) module based on our Temporal Masked Transformer that autonomously generates scene-consistent pseudo-drafts in latent space, enabling a fully draft-free one-step model. Extensive experiments show that both draft-conditioned and draft-free versions achieve state-of-the-art performance on multiple metrics, surpassing traditional and multi-step generative methods in both quality and efficiency. The denoising process for a single video takes only about 1 second.

Large-scale video diffusion models (VDMs) deliver strong generation performance, but full fine-tuning for downstream tasks incurs prohibitive computational costs. Existing parameter-efficient fine-tuning (PEFT) methods have two critical flaws on billion-scale models: they still require substantial trainable parameters, and reward-based training suffers from noise-induced optimization instability in condition-guided tasks. We propose MagicPrompt, a lightweight framework that achieves extreme parameter efficiency and stable reward optimization. It first adopts Attention-Embedded Prompt Tuning, which steers generation via lightweight soft prompts with orders of magnitude fewer parameters while preserving pre-trained knowledge. It further introduces Dual-Space Reward Feedback Optimization, which uses self-supervised latent objectives to improve condition-guided reward training. Experiments show MagicPrompt reaches competitive performance with less than 1% trainable parameters and notably reduces training costs.

Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. This limits the diversity of images, and for person-centric prompts, can reflect or amplify demographic skew. We formalize this problem as coverage of a predefined set of semantically specified modes, which we call target-mode coverage. We then propose multi-axis max@K, a group-based reinforcement learning objective for improving such coverage in diffusion-based T2I models. Given a group of samples and one score per target category, multi-axis max@K first takes the maximum score across samples for each category and then sums these category-wise maxima. The resulting credit assignment gives a sample positive weight on a category only when it increases that category's group-wise maximum, allowing different samples to contribute to different categories. We first validate the credit-assignment mechanism on a synthetic mixture and on SD3.5-M using deterministic pixel-based color rewards. We then evaluate the same objective on perceived-appearance fairness. Across three automatic evaluators on held-out prompts, multi-axis max@K improves the Fairness Score by 0.23-0.36 relative to the base model, while maintaining image quality and text alignment.

Visual generative models inevitably absorb undesirable concepts from uncurated pretraining data, making concept erasure essential for safe deployment. Existing erasure methods, however, are often architecture-specific and struggle to remove target concepts while preserving non-target content and generative priors. We present Uni-AdaVD, a universal inference-time concept erasure framework for visual generation. Uni-AdaVD treats the value space of multimodal attention as a unified intervention space and introduces encoder-aware target representation construction to localize target semantics across heterogeneous text encoders. It further combines orthogonal value decomposition with an adaptive erasing shift to suppress target semantic directions without updating the original model weights. Extensive experiments on U-Net-, DiT-, and autoregressive image generators, as well as text-to-video models, demonstrate strong performance on single- and multi-concept erasure while preserving non-target priors. These results suggest that Uni-AdaVD provides an efficient and adaptable safety mechanism for modern visual generative models. Our code is available at https://github.com/QifanZhou/Uni-AdaVD.

State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content. Prior safety efforts range from concept erasure and prompt filtering to classifier-based gating. However, simple techniques like parameter efficient adaptations of the models easily bypass such guardrails. We introduce a unique principled approach that achieves safety by regulating the model's attention dynamics through inference-time introspection, exhibiting intrinsic robustness. Our method analyzes and rebalances attention activations throughout image synthesis, steering generations away from unsafe concepts while preserving semantic alignment. This introspective control ensures safety of deployed models. Across standard and adversarial safety benchmarks, our approach achieves remarkable safety scores while maintaining or even improving alignment and perceptual quality. Our results reveal that attention-space regulation offers a considerably more promising path to safer diffusion transformer based image generation than the existing concept erasing mechanism.Our code can be accessed at https://basim-azam.github.io/iam/

Modern generative models are increasingly trained using model-generated signals, creating both opportunities for self-improvement and risks of collapse. We study optimal self-distillation (SD) for rectified flow (RF): given a suboptimal teacher velocity field, can a student trained on a mixture of true RF velocities and teacher velocities provably improve the teacher? For linear RF with ridge regularization on fixed interpolation pairs, we prove an exact affine path identity, derive the optimal mixing coefficient in closed form, and show strict improvement in integrated velocity risk whenever the teacher risk is nonstationary along the regularization path. The optimal coefficient obeys a sign rule: positive mixing corrects under-regularized teachers, while negative mixing corrects over-regularized teachers. We also give one-shot generalized cross-validation (GCV) and validation tuning procedure that avoids grid search over mixing weights and repeated refitting. Combining this theorem with RF Wasserstein convergence bounds, we show that optimal self-distillation improves the velocity estimation terms controlling continuous-time and finite-step generation error. Experiments with Gaussian models, Gaussian mixtures, and image data show that optimal self-distillation improves velocity risk, mode recovery, and finite-step generation relative to both the teacher and pure distillation.

Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level denoising. Both paradigms struggle to achieve logical consistency and low-latency streaming for complex reasoning tasks. We propose HDR (Hierarchical Denoising for Visual Reasoning), a unified framework that integrates hierarchical latents into causal video generation for multi-step reasoning. HDR organizes video latents into a tree-structured hierarchy, enabling coarse-to-fine reasoning before streaming output. Coarse denoising layers preserve uncertain hypotheses for global planning, while finer layers progressively refine them into concrete visual states. A sparse hierarchical attention pattern (SHAP) further reduces temporal attention costs. We introduce a level-stratified multi-step video reasoning benchmark with out-of-distribution cases, covering six tasks: maze navigation, Tower of Hanoi, one-line drawing, sliding puzzle, Sokoban, and water pouring. Compared with streaming autoregressive diffusion baselines, HDR improves success from 34.22 to 60.29 (76.2% relative gain) and increases average progress from 76.00 to 89.56, demonstrating more consistent reasoning trajectories. HDR maintains low-latency streaming at 0.70 seconds per latent, achieving 54.2 times faster inference than bidirectional diffusion. It also retains 82.9% of full-data performance with only 2% training data, compared with 52.0% for bidirectional diffusion. Real-world robot experiments further demonstrate HDR's potential for physical interaction and world modeling. Project demo: https://hierarchical-diffusion-reasoning.github.io/.

Recent diffusion-based video generation models have made significant progress in multi-reference image-conditioned video editing. However, existing methods still struggle to coordinate information from multiple visual sources accurately. We identify a critical deficiency in existing approaches. Existing editing instructions lack explicit reference relationships, and most multimodal large language models (MLLMs) cannot generate them reliably. To address this problem, we propose ReBind, a systematic framework that introduces semantic instructions with embedded reference tokens as the intermediate representation for multi-reference image-conditioned video editing. Our key insight is embedding reference tokens at semantic positions to eliminate ambiguity and establish precise bindings between visual attributes and their sources. We develop ReBind-Instruct, a specialized MLLM that learns to establish explicit bindings between visual attributes and their reference sources through a two-stage progressive scheme for precise reference relationships. We further develop ReBind-Edit, which enables lightweight adaptation of text-to-video models to coordinate multiple references by binding visual attributes to their designated sources. Extensive experiments demonstrate that ReBind substantially outperforms general-purpose MLLMs in instruction quality and achieves state-of-the-art performance among open-source methods on reference image conditioned video editing. Our project webpage: https://rebind-mrv2v.github.io/.

World models, especially based on JEPA architectures, have been shown to learn robust dynamics of various environments. However, learning from visually complex real-world data remains a challenge, especially in unpredictable outdoor environments. We introduce depth as a geometric prior during training in learning more robust latent dynamics directly from robot video data and handling visual complexity. This combines depth supervision with an isotropy-inducing latent regularizer (SIGReg), maximizing task-agnostic latent diversity while constraining how that diversity is organized, with the combined objective targeting the highest-entropy representation consistent with scene geometry. To satisfy this greater complexity without increasing inference time, we also add training-only overparameterization. Training an 18M-parameter model on video from a real agricultural robot, we evaluate with frozen-representation visual odometry probes, predictor-based surprise detection, and multi-step latent rollout fidelity. Compared to the baseline LeWM, our method lowers visual odometry probe error by 33%, substantially increases surprise-score separation both in-domain and on the out-of-domain TartanGround benchmark, and improves multi-step rollout fidelity under domain shift, with gains that grow with rollout horizon. Notably, we also see improvements in surprise-score separation on physics understanding that is not directly tied to 3D geometry, such as lighting and shadows. These results show that a lightweight training-time geometric prior makes a compact JEPA world model more useful and more transferable on real outdoor data with strong underlying representations, without adding inference overhead. Our work suggests that depth as a physically grounded prior can enhance world model generalization on a variety of tasks.