多模态生成与编辑

Driving scene reconstruction and rendering, especially with 3D Gaussian Splatting, has become an important component of autonomous driving simulation. However, rendered views often degrade under extrapolated ego trajectories and scene edits, producing blurry structures, temporal flicker, and foreground-background misalignment. Existing refinement methods are commonly designed for a specific setting, such as image-level novel-view repair or object-editing correction. In this paper, we introduce SPVC, a structured and panoptic video fixing framework for cross-dataset driving scene rendering. The name summarizes four design principles. (1) Structured fixing denotes the use of explicit spatial conditions, including camera pose, 3D bounding boxes, and HD maps, to guide the repair process and reduce uncontrolled hallucination. (2) Panoptic fixing refers to correcting both background rendering artifacts, such as distorted roads, buildings, and lanes, and foreground vehicle artifacts introduced by scene editing, such as inconsistent object appearance. (3) Video fixing means that the model operates on driving sequences rather than isolated frames, allowing temporal cues to be used during artifact correction. (4) Cross-dataset fixing means that a single shared network is trained and applied across multiple driving datasets, reducing the need for dataset-specific or scene-specific fixers. Concretely, we construct paired degraded-clean training data by simulating under-constrained 3DGS rendering and foreground vehicle insertion artifacts, and train a two-stage controllable video diffusion model that first addresses video-level appearance and then refines scene layout with structured controls.

Audio-driven avatar generation requires realistic lip-sync, expressive motion, and real-time streaming. Recent work achieves the latter via self-forcing with Distribution Matching Distillation (DMD), but this paradigm suffers from a critical failure that has not been systematically characterized: dynamic collapse, where the student model converges to a near-static optimum with high perceptual quality but severely suppressed temporal dynamics. We trace this to two causes: the reverse KL objective in DMD, which biases toward low-motion modes, and unanchored self-conditioning, which creates a feedback loop that amplifies collapse. This is especially harmful for avatars, where even subtle motion loss breaks lip-sync and expression. To address this, we propose DynaForcing, a training framework with three complementary strategies applied at different levels. Specifically, Hybrid Forcing anchors rollouts to ground-truth dynamics at the data level to break the feedback loop. Dynamics-Aware Reward Regularization introduces explicit motion rewards via the RL interpretation of DMD to counteract the reverse KL bias at the loss level. Reference Perturbation perturbs reference images to decouple identity from static details, forcing the model to rely on audio for motion at the conditioning level. We further introduce computation graph pruning and gradient replay, reducing the GPU footprint of self-forcing by over an order of magnitude. Experiments show that DynaForcing recovers dynamics to teacher-comparable levels (Dyn-Deg: 0.31 -> 0.73, Sync-C: 7.03 -> 7.68) while improving visual quality, resolving the quality-dynamics trade-off throughout training without early stopping.

Unified multimodal models (UMMs) are motivated by the hope that understanding and generation reinforce each other but controlled ablations repeatedly find that adding a generation objective leaves understanding flat. Joint-training studies cannot settle the disagreement: with overlapping supervision, a gain cannot be attributed to the architecture rather than the data. To further investigate the relationship between the two directions in UMMs, we separate them by construction. A novel visual entity, a rendered 3D asset paired with a pseudo-word screened for absence from the frozen model's behavior, is bound through exactly one task direction, and the untrained direction is then measured. We find that the channel is real in both directions, but the directions differ in kind: generation training installs a name the model can only match among candidates; understanding training installs one it can also produce. What governs cross-task usability is where the binding enters the shared computation. An alignment probe predicts export across 36 configurations (Spearman $ρ= +0.68$). That objective's alignment term, maximized in closed form over activations with every weight frozen, makes a concept drawable when injected at layer 7 of 28 and is indistinguishable from the base model from layer 14 on, while the weight-based version of the same edit peaks at layers 10-14. In an observational series of four models, this window appears only where the understanding pathway is a semantic vision encoder, suggesting that unified weights are not enough: the two directions must share a semantic format at the entry point. Exploiting the rule, a mid-stack alignment objective acquires the concept for a $0.1%$ relative loss of the model's general text-to-image ability, against $41%$ for the standard generative route. Our code is at https://github.com/Zane-ZYQiu/entry-point-umm.

We introduce Semantic Task Completion Video Generation, an outcome-oriented video generation task. Under this formulation, success requires both achievement of the intended outcome and semantic grounding. Semantic grounding characterizes the correspondence between the reference image and the generated outcome in terms of high-level semantics relevant to the task. Evaluation focuses on the generated outcome and requires neither the presentation of a complete sequence of intermediate task steps nor conventional appearance consistency with the reference image. To support systematic evaluation, we construct SemComp-Data, an evaluation dataset covering six domains. Each instance comprises a reference image, a detailed instruction, a brief instruction, and an outcome-centric video clip. A scalable four-stage curation pipeline converts raw videos into standardized SemComp-Data instances. We further introduce SemComp-Bench, an evaluation protocol that uses a vision-language model (VLM) to answer structured binary questions. SemComp-Bench reports the OA Score and the GR Score for Outcome Achievement and Generation Reliability, respectively. Experiments on representative video generation models show that achieving intended outcomes while maintaining task-relevant semantic grounding in reference images remains challenging.

In this paper, we tackle the problem of performing consistent, unified modifications to a multi-shot video sequence. This task is particularly challenging because multi-shot videos consist of discontinuous temporal segments that vary significantly in viewpoint, camera scale, and subject pose, leading to severe identity drift and cumulative error propagation. Achieving coherent edits requires establishing reliable cross-shot semantic awareness to maintain stable subject appearance and visual continuity across these disjointed boundaries. To address this, we propose MSEditor, the first framework designed specifically for consistent multi-shot video editing. To overcome the scarcity of high-quality multi-shot training data, we repurpose existing multi-view video datasets to provide robust cross-shot supervision. Architecturally, we introduce a Supervisory Adapter that injects this cross-shot information into the diffusion backbone, enabling the model to learn identity-consistent representations. Furthermore, to effectively mitigate cumulative errors and ensure long-range temporal coherence, we design a Cross-Shot Packing strategy that dynamically aggregates information from semantically related shots within the self-attention window. Extensive experiments demonstrate that MSEditor significantly outperforms existing methods on our curated multi-shot video editing benchmark in terms of identity preservation, temporal stability, and overall visual quality.

The quality and diversity of instruction-based video editing datasets are steadily improving, yet existing datasets mainly focus on single editing operations and fall short in supporting compositional instruction-guided video editing. In particular, multiple editing intents must be jointly understood and faithfully executed within the same video. To address this issue, we introduce CoinVE-200K, a large-scale, high-quality dataset for Compositional Instruction-Guided Video Editing. CoinVE-200K contains 1080p video-editing pairs of up to 201 frames, covering diverse compositional scenarios where each sample involves 2 to 5 atomic editing operations. The instructions target humans, objects, and backgrounds, and cover edit types such as addition, removal, modification, and stylization. All samples are built through a carefully designed generation and filtering pipeline to ensure instruction faithfulness, visual quality, temporal consistency, and compositional diversity. We also introduce CoinVE-Bench, a benchmark for compositional-instruction video editing across diverse subjects, operation types, and instruction complexities. Furthermore, we present CoinVE-Edit, a 22B compositional video editing model built upon Wan2.1-T2V-14B and Qwen3-VL-8B-Instruct. CoinVE-Edit disentangles region-aware attention for different editing instructions, enabling precise multi-region editing while preserving irrelevant content and temporal coherence. Experiments on CoinVE-Bench show that CoinVE-Edit achieves strong performance in instruction following, compositional editing accuracy, visual quality, and temporal consistency.

We introduce Hydra-0, a generalist world model conditioned on action flow, which represents robot actions as pixel motion. This shared visual interface enables generalist world modeling and control by learning action consequences across embodiments, tasks, environments, and video-generation backbones. Our best configuration achieves 90.4% lower robot-motion error and 60.2% lower object-motion error than our action-conditioned baseline, while supporting zero-shot composition and data-efficient adaptation. On the RoboLab benchmark, Hydra-0 achieves a Pearson correlation of r=0.96 between replayed and reference success rates. Finally, we uncover an emergent inverse mode of this interface: a world action model that predicts compatible robot motion from desired object flow transferred from a human demonstration. A trained action head maps the resulting latent features to executable actions without requiring task-specific expert robot demonstrations. Together, these results demonstrate the potential of action flow as a shared control interface connecting heterogeneous training data, open-loop policy evaluation, and robot control.

In the Code World Model paradigm an LLM synthesizes an executable world model that a classical planner searches, and the model is accepted when it reproduces sampled transitions. We ask what that acceptance certifies in continuous control. We define the pipeline's danger as an expected risk and isolate its exact factor: the probability that N i.i.d. gate rollouts all miss a critical event of probability r is exactly (1-r)^N; an independent acceptance sample adds its budget to the exponent. On three hybrid instruments the accepted mode-blind model is exploited: the planner is pinned at the mode boundary at a regret of nearly the whole attainable return. We prove a localization budget, valid at boundary points: models with Lipschitz constant at most L differing by eta at a point disagree above tolerance eps on a region of volume at least kappa((eta-eps)/L)^(d+m); the discontinuous reset modes studied pay no such budget. With real LLM synthesis, GPT-5.x repairs an omitted 1D clamp in 105 of 111 mode-containing draws — every attempt exact on 50 of 56 instrument-stream blocks (95% CI [0.781, 0.960]). On 2D regions no artifact recovers the rule (0/156); eight targeted interventions leave the failure in place, and positive controls locate it: a located rule is not induced, while given form and location the constants follow exactly. A version-space certificate proves identification is class-relative: at the widest dose the declared fit succeeds in 20/20 blocks and every sample-consistent circle is within tolerance in 18/20. We prove a class of entry rules exactly consistent with every sample yet harmless at play, so identifiability is a measurable property of the instrument. Re-scoring all 1034 artifacts on independent samples confirms acceptance certifies sample consistency and no more: where the gate is provably informative it covers about two percent of the exploited planner's queries.

Flow matching models for video generation achieve impressive performance but suffer from high computational overhead due to iterative denoising. In fact, the original model is not necessary for all denoising steps, allowing some steps to use lightweight alternatives for faster sampling. However, directly using caching or lightweight models can deviate from the original denoising trajectory, resulting in suboptimal performance. Through empirical analysis, we find that lightweight models can robustly capture the magnitude components of the original model's output, while caching provides reliable directional guidance. Building on this insight, we propose the Magnitude-Direction Decoupling (MDD) method, which adaptively employs a direction-calibrated lightweight model as a substitute for the original model to accelerate inference and effectively correct deviations in the denoising trajectory. Moreover, MDD further reduces inference costs by reusing magnitude information under classifier-free guidance (CFG). As a result, MDD offers a more reliable and lightweight solution to accelerate sampling. Experiments show that MDD outperforms existing acceleration methods, delivering promising speedups (e.g., up to 2.95x on Wan2.1) while preserving high visual fidelity and content richness.

Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for preventing harmful content. Existing adversarial probes evaluate these methods by testing whether erased concepts can still be recovered. However, existing erasure and probe methods remain largely text-centric, focusing on whether the text-to-image mapping is severed while overlooking whether the corresponding visual knowledge remains. To investigate this question from a visual perspective, we leverage diffusion inversion to probe whether a generative trajectory can reconstruct visual instances of an erased concept. Under a null-text condition, standard inversion avoids the textual pathway but amplifies approximation errors, hindering faithful trajectory recovery. To address this challenge, we introduce TINA+, a diffusion-consistent Text-free INversion Attack equipped with optimization-based inversion. We also find that unconstrained diffusion inversion may discover spurious trajectories, even allowing a randomly initialized diffusion model to reconstruct the target concept. Such trajectories may falsely indicate residual visual knowledge. TINA+ therefore introduces Diffusion-Consistent Trajectory Regularization to suppress this failure mode. By penalizing trajectories that fall far below the expected marginal energy evolution of diffusion, TINA+ suppresses spurious inversion paths while preserving its ability to recover erased concepts. Experiments across twelve erasure methods, four concept-erasure tasks, and different model architectures demonstrate that TINA+ reliably probes residual visual knowledge through diffusion-consistent visual trajectories. These results provide stronger evidence that current methods often obscure concepts by severing text-image links rather than eliminating the underlying visual knowledge.

Diffusion models have achieved remarkable success in image and video generation, yet the high computational cost of iterative sampling remains a critical bottleneck for practical deployment. Feature caching has emerged as a promising acceleration paradigm by reusing or predicting intermediate features across timesteps. However, existing training-free methods apply uniform prediction strategies that cannot adapt to the heterogeneous feature dynamics, causing significant quality degradation under high acceleration ratios. We propose LinCa, a feature caching framework based on learnable invertible networks. LinCa decomposes cached features into sub-components with distinct continuity properties via a lightweight invertible network and applies differentiated prediction orders matched to each component. The strict invertibility guarantees lossless reconstruction back to the original feature space, forming a unified Decompose-Predict-Reconstruct pipeline. By training separate predictors for different models and timestep segments, LinCa adapts to heterogeneous feature dynamics. Experiments on FLUX, Qwen-Image, and HunyuanVideo demonstrate that LinCa, with less than 0.2% additional parameters, significantly outperforms existing methods and maintains near-lossless quality at 5-7x speedup. Code: https://github.com/QHR69/LinCa

Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on efficient solvers and samplers, comparatively little attention has been paid to selecting the sampling timesteps themselves. A recent line of work optimizes theoretically derived surrogates for sample quality rather than the quality metric itself. We propose Optimizing Your Sampling (OYS), which instead treats timestep selection as a black-box optimization problem, optimizing the target metric directly with Bayesian optimization. OYS outperforms both the default schedules and those of Align Your Steps on text-to-image generation, and improves over the default schedules on inpainting and other image tasks, in both quantitative and human evaluations. OYS requires no additional training, is applicable even to distilled models, and improves both simple and sophisticated samplers such as Euler and DPM-Solver++. A 5-step OYS schedule retains 89%-94% of the quality of a 50-step schedule while reducing inference cost by 10x.

High-resolution image editing is increasingly demanded in professional workflows, yet existing diffusion-based models remain constrained to resolutions below 1K due to quadratic attention complexity and prohibitive memory requirements. A prevalent workaround employs a two-stage pipeline: editing at low resolution followed by independent super-resolution. However, this approach suffers from two critical issues: information divergence, where hallucinated details contradict the original high-resolution (HR) source, and texture degradation, manifesting as over-smoothed or over-sharpened artifacts. We propose EditBridge, a diffusion bridge framework for efficient ultra high-resolution editing. Unlike conventional diffusion that regenerates from noise, we formulate refinement as structured data-to-data translation from the low-resolution (LR) edited result to its HR counterpart, explicitly conditioned on the original HR source to preserve authentic details. To efficiently incorporate HR source guidance, we introduce a prior-guided block-wise sparse attention mechanism that exploits semantic correspondence from first-stage editing to constrain cross-image interactions to spatially aligned regions, significantly reducing computational overhead. Extensive experiments demonstrate that EditBridge achieves high-fidelity editing with superior perceptual quality at resolutions up to 4K, delivering 3.6--8.4$\times$ speedup at 2K and enabling practical 4K editing in 61 seconds.

Compute-optimal scaling laws guide the training of frontier language models yet remain largely unexplored for visual generation. We present a systematic scaling law study for text-to-image diffusion models using Abra, a controlled family of flow-matching transformers trained across three orders of magnitude worth of compute ($10^{19}$ to $10^{22}$ FLOPs), reaching significantly larger compute budgets than previous works. We demonstrate that diffusion models scale just as predictably as language models but require far more data to train optimally: compute optimality occurs at approximately $200$ image tokens per parameter, ten times the Chinchilla compute-optimal prescription for LLMs. We show that unlike language models, diffusion models are robust to overtraining and that practitioners should err on the side of more data rather than a larger model. Finally, we show that this predictability extends beyond training loss to generative quality metrics, optimal CFG settings, representation quality, and even the shape of the training curves, which collapse onto a universal form.

Multimodal large language models (MLLMs) are increasingly used to interact with screenshots, scanned documents, diagrams, and other visually grounded inputs. This shift introduces a new safety risk: in many multimodal jailbreaks, neither the prompt nor the image is harmful in isolation. Unsafe behavior emerges only when the model binds an apparently benign operation, such as summarizing, translating, or following, to a localized visual target. This reveals a structural weakness in current multimodal defenses, which largely moderate the prompt-image pair as a whole even though the true security-relevant unit is the grounded operation-target pair produced during dereference. In this work, we identify and analyze this reference-dependent failure mode and show that existing defenses degrade when harmful semantics are localized, activated only after grounding, and dependent on visual reference resolution. To address this problem, we propose COMIC (Context-Operation-Modality-Image-Classifier), a reference-aware pre-generation safety gate for MLLMs. COMIC first infers the requested operation and reference type, constructs candidate targets from OCR and open-vocabulary proposals, grounds plausible referents, and evaluates safety over explicit operation-target pairs. To handle ambiguity conservatively, COMIC combines max-risk aggregation with quality-aware routing before deciding whether to forward or block a request. We evaluate COMIC across multiple open-source MLLMs, localized and broader multimodal jailbreak benchmarks, and benign reference-sensitive settings. The results show that COMIC consistently improves robustness while preserving benign utility and practical efficiency. More broadly, our findings suggest that multimodal safety cannot be enforced reliably without modeling the requested operation, the visual target to which it applies, and the confidence of that grounding.

As text-to-image generative models advance, they raise critical safety concerns, particularly the generation of Not-Safe-For-Work (NSFW) content such as violence and nudity, further exacerbated by red-teaming adversarial attacks. Existing defenses predominantly operate under white-box assumptions, relying on text encoder optimization, weight editing, or inference-time intervention, and fundamentally cannot scale to proprietary models. Black-box alternatives based on LLM prompt rewriting offer broader applicability, yet fail in a critical regime we identify as the benign adversarial problem: prompts that are linguistically safe but still trigger harmful generation due to the model's learned data distribution. We propose DiSCO, a zero-shot, strictly black-box defense that operates entirely at the prompt level as a plug-and-play module, requiring no model retraining, fine-tuning, or access to model internals. DiSCO performs distribution-guided suffix expansion via beam search, optimized through contrastive scoring over safe and unsafe image pools generated by the target model itself, with iterative adaptive feedback until safe content is produced. We demonstrate that DiSCO consistently enhances the safety of both undefended and defended models on the I2P benchmark under multiple red-teaming attacks, achieving 37.7% and 25.13% ASR reduction, respectively, while maintaining semantic fidelity and improving image coherence. As a black-box, architecture-agnostic module, DiSCO can be readily applied to any text-to-image system without necessitating any changes to the model itself.

Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events that are not yet visible in historical values. Existing multimodal forecasting methods often either ask large language models (LLMs) to predict numerical values directly or fuse text and time series implicitly, making contextual influence difficult to interpret and control. We propose SCENARIODIFF, a hierarchical contextual reasoning framework for multimodal time series forecasting under noisy and weakly aligned documents. SCENARIODIFF organizes contextual information into three levels: a Historical Context Agent extracts stepwise evidence from raw documents, a Scenario Agent produces a qualitative scenario description for the forecast horizon, and an Anchor Guidance Agent generates sparse anchor points for event-relevant future regions. These structured signals condition a Multimodal Diffusion Transformer, while Anchor Blended Sampling locally refines generated trajectories without retraining. Experiments on the Time-MMD benchmark show that SCENARIODIFF is especially effective in event-driven domains, demonstrating the value of explicit hierarchical scenario guidance for multimodal time series forecasting. Our full implementation is available at https://anonymous.4open.science/r/ScenarioDiff_ICDM-2C4C

Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-action (VLA) models make each such decision with a single forward pass, leaving no mechanism to allocate additional computation to difficult or consequential choices. We introduce $τ_0$-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem through world-model-guided test-time computation. At each inference step, the high-level policy uses execution memory to generate a subtask and, when needed, searches over alternatives before committing to its output. A low-level policy then executes the generated subtask across multiple robot embodiments. The policy is trained on 40,115 hours of heterogeneous real-world data with multimodal co-training. Across in-domain and distribution-shifted settings, allocating additional test-time computation substantially improves next-subtask prediction accuracy, and these gains translate into higher closed-loop success on long-horizon robot manipulation tasks.

Automated e-commerce poster design requires both high-quality poster generation and flexible editing of existing designs. However, most existing methods either target end-to-end poster generation or follow multi-stage design pipelines, with limited capability for flexible and precise editing of existing posters. To enable unified generation and editing of e-commerce posters, we introduce Text Patch Generation and Editing, a unified task formulation that treats text patches as atomic units and covers four operations: poster generation, patch addition, patch deletion, and patch modification, with optional reference-guided style control. Based on this, we propose PosterText, a unified model trained with a four-stage curriculum, including text rendering pretraining, instruction-following training, reinforcement learning for preference alignment, and spatial guidance self-distillation for execution refinement. We further construct a large-scale dataset with patch-level annotations and a comprehensive benchmark for evaluation. Extensive experiments demonstrate that PosterText achieves competitive performance against existing generation and editing approaches, validating the effectiveness of the proposed framework.

Face recognition templates are compact identity representations, yet they also encode rich semantic information about facial appearance. Prior work has shown that templates can be inverted to images or indirectly manipulated through image-editing pipelines, but direct semantic editing in template space remains largely unexplored. Existing interpretability methods for face recognition often rely on manual neuron inspection or predefined attribute labels, limiting scalability and semantic flexibility. To address this gap, we propose SCOUT (Semantic Concept Discovery for Open-VocabUlary Editing of Face Recognition Templates), an end-to-end framework for discovering and directly manipulating semantic concepts in face recognition templates using mechanistic interpretability. SCOUT learns sparse template representations, generates semantic hypotheses for latent features from natural-language descriptions, and validates their stability. The resulting features act as controllable semantic directions for direct editing, avoiding costly edit--re-encode pipelines. Experiments with face recognition models using CNN, ViT, and Swin backbones show that SCOUT discovers interpretable concepts beyond standard attribute labels and enables controllable, identity-aware template manipulation with negligible impact on identity matching. We further show that edited templates can subsequently be decoded with independent inversion models for visualization and evaluation.

Meal awareness can help people reflect on hydration, chewing rhythm, and conversation-heavy meals, but many eating-sensing approaches rely on cameras, microphones, food photographs, or repeated self-logging. PPG and IMU offer a narrower sensing path by capturing physiological and motion patterns around meal-adjacent actions without raw audio, video, or photographs. We present Oto-Meal, an audio- and image-free earable prototype. Its pooled neural recognizer uses a two-stage event/rest gate and five-class behavior classifier. Separately, a within-user protocol evaluates a lightweight memory matcher built from labeled target-user examples. We invited seven volunteers and collected a seven-user dataset for mixed-user training, within-user memory evaluation, and modality ablation. The pooled model reaches 70.99% event accuracy. Under the separate memory protocol, 20% target-user calibration reaches 80.38 $\pm$ 0.84% event accuracy and 81.77 $\pm$ 0.69% cascade accuracy; with 60% calibration, PPG+IMU reaches 85.13 $\pm$ 0.57% event accuracy and outperforms IMU-only and PPG-only. These preliminary results suggest that audio- and image-free earable sensing with inspectable personalization can support low-burden meal-awareness review.

Video generation is rapidly evolving from single-shot clips to multi-shot narratives, where the human character serves as the core narrative anchor. However, existing benchmarks mainly assess character appearance or individual-shot quality, without measuring whether physical and emotional states remain coherent across cuts. They also rarely provide criterion-specific evaluation methods, although physical continuity, facial dynamics, and cinematic relations require different visual, temporal, and relational evidence. To address these limitations, we introduce PersonaShot, the first person-centric benchmark for narrative continuity in multi-shot video generation. PersonaShot contains approximately 1,000 multi-shot segments and 16 metrics spanning physical continuity, affective dynamics, and cinematic grammar. \textbf{1) Narrative Continuity Benchmark:} We evaluate character coherence across three temporal levels: within-shot states, cross-shot transitions, and sequence-level trajectories. \textbf{2) Human-Aligned Specialist Evaluators:} We distill reasoning from a large multimodal teacher into lightweight criterion-specific evaluators, each grounded in the visual, temporal, or relational evidence required by its metric, and align them with expert human judgments. \textbf{3) Systematic Evaluation and Insights:} Our evaluation reveals distinct capability profiles across state-of-the-art models and a clear gap between perceptual quality and cross-shot narrative continuity. Even visually compelling videos frequently exhibit physical-state resets, abrupt affective shifts, and broken cinematic relations across shots. Human studies further demonstrate strong agreement between our evaluators and expert judgments.

Cross-border e-commerce image translation is essential for global retail, where product images, banners, and detail pages need to be produced in different languages. Existing methods struggle to achieve accurate translation, faithful visual identity preservation, and easy-to-edit outputs, simultaneously. To address these challenges, we introduce TransAnyText, a structured visual code framework that reformulates image text translation as generating renderable HTML patches from source images and target languages. Our framework decouples semantic generation from pixel rendering: a vision-language model (VLM) handles visual understanding, cross-lingual translation, and structured visual generation, while a diffusion model performs background inpainting and pixel-level refinement, followed by deterministic rendering to synthesize the final image. Based on this formulation, we develop a three-stage post-training framework, where supervised fine-tuning (SFT) establishes the image-to-code mapping, privilege-gap weighted self-distillation (PWSD) improves the learning of style and layout tokens, and reinforcement learning with verifiable rewards (RLVR) further optimizes task-level performance. We further introduce TransAnyDataset and TransAnyBench, a multilingual dataset and benchmark for e-commerce image translation. Extensive experiments demonstrate competitive performance against cascaded pipelines, open-source end-to-end models, and closed-source image editing systems, providing an effective, controllable, and editable solution for cross-border e-commerce image translation.

Despite progress in instruction-based video editing, unimodal textual instructions inherently struggle to convey fine-grained textures and complex dynamics. To bridge this perceptual gap, we propose Visual In-context Editing, a new paradigm elevating video editing from textual instructions to multi-modal visual guidance encompassing single image, image pair, and video pair. To facilitate this paradigm, we curate VicEdit-400K, the first large-scale dataset for visual in-context video editing. We develop an automated pipeline to generate 400K high-quality samples across ten task types, ensuring superior visual fidelity and semantic consistency through multi-dimensional filtering. Leveraging this foundation, we introduce VicEdit, a unified framework to bridge visual and textual contexts. To adaptively extract editing semantics from heterogeneous references, we design Modality-Adaptive Semantic Distillation, which produces modality-specific semantic tokens from visual references. These tokens are then synergistically integrated with textual instructions through Dual-Context Injection, enabling the generation process to benefit from both visual and textual signals. Extensive evaluations on VicEditBench demonstrate that VicEdit achieves state-of-the-art performance across both basic instruction editing and visual in-context editing tasks, establishing visual in-context learning as a powerful and controllable paradigm for video editing.

Existing image editing frameworks predominantly follow the training paradigm of text-to-image diffusion models. However, extending this paradigm to image editing highlights two inherent discrepancies, specifically, the insufficient attention to edit concept granularity and the training inefficiency caused by sparse supervision signals. To address these issues, we establish a comprehensive hierarchical taxonomy featuring over 1,000 fine-grained edit concepts and build ConceptEdit-12M, a massive dataset of 12 million high-quality editing pairs via an improved synthesis framework. This library-driven approach effectively rectifies the distribution collapse of generated data while ensuring high data fidelity. Furthermore, we propose a dense supervision training strategy that synthesizes multiple non-interfering concepts into single image pairs. By providing richer learning signals, this strategy significantly enhances both training efficiency and overall model performance. Training results validate our strategy, significantly outperforming prior works. Finally, we present ConceptEdit-Bench, a granular evaluation suite designed to diagnose model capabilities across a vast array of real-world scenarios.

We present AnyTalk, a novel method for generating 3D speech animations for arbitrary characters without requiring any animation data. While existing audio-driven 3D speech animation methods rely on character-specific training data or laborious rigging/re-meshing, AnyTalk circumvents these limitations by leveraging recent video diffusion models trained on extensive video datasets. We first adapt a pre-trained video diffusion model to a target character through our Character-specific Fine-tuning (CsF) technique. By fine-tuning on rendered images of the 3D character paired with zeroed-out audio embeddings (representing "no motion"), we eliminate the need for animation data while preserving the motion prior of large-scale video diffusion model. We then uplift the resulting talking-head video into a 3D speech animation by estimating blendshape parameters through a proposed optimization process. AnyTalk enables lip-synced animations across diverse face meshes and blendshape configurations, significantly reducing manual effort and data requirements. We further enhance usability by distilling AnyTalk into a streamlined network, $\text{AnyTalk}_{RT}$, thereby enabling real-time performance. By leveraging talking-head video generation, our method broadens access to audio-driven speech animation technology for arbitrary characters. The code is publicly available at https://serin-yoon.github.io/projects/anytalk/.

Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors. However, the variational autoencoder (VAE) in latent T2I models may discard restoration-sensitive details, while the open-ended synthesis prior can introduce content-inconsistent artifacts. We present PixRestore, a VAE-free pixel-space Diffusion Transformer (DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining. PixRestore performs flow matching directly on patchified pixels, preserving fine-grained details while keeping the token sequence tractable. To adapt to different degradations, PixRestore learns to predict the reliability of layer features using LQ--HQ DINO feature similarity. Features from more reliable layers are fused as dense conditioning, while less reliable layers receive stronger HQ-feature supervision to encourage degradation removal. We train PixRestore on a large-scale corpus of diverse scenes and degradations, and further finetune it into a one-step generator using DINO-based adversarial objectives for efficient inference. Experiments on public benchmarks and real-world test sets show that, with only about 50M parameters and single-step inference, PixRestore achieves the best overall fidelity, perceptual quality, and robustness to degradations among competing UIR models while being far more efficient. Larger PixRestore variants can further boost performance, demonstrating the scalability of our pixel-space design. Code and the curated benchmark can be found at https://github.com/csslc/PixRestore.

Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.g., "subject composition"), which are ill-suited to this combinatorial setting and lead to fragmented coverage, uncontrolled complexity, and little diagnostic value. Recognizing that diverse multi-reference tasks share a common set of atomic operations, we adopt a capability-oriented perspective and formalize four operators: Anchor ($f$), Disentangle ($g$), Apply ($\oplus$), and Compose ($C$). Any multi-reference prompt can then be represented as a compositional formula over these operators, whose structural complexity is quantified by the number of operator slots. Building on this formulation, we construct TRACE-Bench, comprising approximately 1,600 evaluation cases across slot counts 1--8, built from 631 formula templates and around 4,000 reference images spanning diverse artistic styles and real-world subjects. The formula structure directly drives an operator-aligned evaluation protocol for per-capability scoring and a diagnostic tree analysis for recursive failure localization. Evaluating 9 leading models reveals insights invisible to holistic scoring: the primary bottleneck lies in disentanglement ($g$) and attribute binding ($\oplus$) rather than scene-level composition ($C$), with even the best model scoring only 0.74 on attribute fidelity. Project page: https://amuseum-whr.github.io/TraceBench

Instruction-based general video editing seeks to unify diverse editing operations within a single, intuitive interface. Existing approaches often rely on resource-intensive conditioning, using either heavyweight branches or costly source concatenation. Is there any efficient way to model editing intent? Thus, we introduce GRNEdit, a lightweight two-stage framework. GRN inspires our approach by encoding visual semantics through combinations of bits. Through task-specific fine-tuning, we take this representation further and recast editing semantics as local retain-or-flip decisions over individual bits. Source information is consequently modeled as coordinate-wise evidence supporting the observed binary states, while the GRN backbone remains responsible for resolving their global composition into coherent generative semantics. In Stage I, a compact encoder translates discrete source codes into continuous evidence signals, which GRN assimilates throughout binary refinement. Inspired by null-prompt training for classifier-free guidance, we further assign the null condition an editing-specific meaning: an empty instruction denotes no edit and is supervised through source reconstruction. This identity pathway not only implicitly strengthens evidence utilization and content preservation in Stage I, but also produces a source-preserving state in the same representation space as the edited state. Stage II can therefore directly compare each edited state with its source-preserving counterpart and use their discrepancy to revise unresolved target-bit decisions. Trained on only 0.6M pairs with less than 3% conditioning parameters, GRNEdit-2B and GRNEdit-8B achieve scores of 4.03 and 4.18 on OpenVE-Bench. The 2B model outperforms multiple 14B open-source editors, while the 8B model performs on par with leading open-source editors.

Video Diffusion Transformers (DiTs) spend most of their compute inside the Self-Attention operation, whose cost grows quadratically, $\mathcal{O}(n^2)$, with the number of latent tokens $n$. For the task of video generation, the token count is large, so this term dominates runtime and memory, and thereby caps the resolution and duration we can generate. Linear $\mathcal{O}(n)$ and low-rank $\mathcal{O}(nk)$ surrogates of Self-Attention trade the full softmax $QK^T$ for cheaper kernels, but rarely recover the original's expressivity, leaving a stubborn quality gap. Motivated by this, we propose SQuad, a Sub-Quadratic Attention Distillation framework that achieves a complexity of $\mathcal{O}(n\sqrt{n})$ in the resulting distilled Attention, naturally balancing the efficiency v/s expressivity trade-off. Instead of training our own Video DiT from scratch, which is prohibitively expensive, we fit a pretrained full softmax Self-Attention DiT into our proposed SQuad-Attention one by distilling the former in two stages: Flow-Matching Supervised Fine-Tuning (SFT), followed by improved Distribution Matching Distillation (DMD2) which additionally makes the sampling more efficient. On the Wan~2.2 5B text-to-video model, SQuAD matches the quadratic teacher on VBench ($83.20$ v/s $83.08$) while cutting the per-step per-block attention FLOPs by $\sim$$67\times$ and attention latency by $\sim$$11\times$, and end-to-end DiT latency by 2$\times$, all while also generating a video in only $6$ Neural Functional Evaluations (NFEs) instead of the default $100$.