advertising agencies

Abstract: Visual generation requires both high-level semantic knowledge and fine-grained pixel details. We propose a learning paradigm that assigns these roles to autoregressive pretraining for knowledge acquisition and diffusion post-training for high-fidelity rendering. Within this framework, we study the objective, representation, and scaling of knowledge acquisition and rendering. Controlled comparisons identify autoregression as the stronger pretraining objective for downstream rendering, improving both learning efficiency and final generation quality. We further find that AR-only generation quality does not necessarily correlate with final performance; semantic quality matters more. This motivates a purely semantic tokenizer trained with language supervision alone, without an image decoder or reconstruction loss. We establish compute-optimal scaling laws for knowledge acquisition and rendering, and find that autoregressive pretraining lowers the fitted asymptotic rendering loss compared with pixel diffusion models trained from scratch. Guided by the laws, we train a 3B-parameter text-to-image model with only 6,600 H100 GPU-hours, achieving 86 on GenEval and 87 on DPG-Bench and validating the proposed paradigm at scale.

Abstract: Learning visual design is essential for prompt enhancement (PE) to turn underspecified user requests into coherent visual specifications for text-to-image (T2I) generation. Existing methods preserve user intent and improve overall visual appeal, with less explicit emphasis on fine-grained design dimensions. To address this gap, we introduce Qwen-Image-PE, which learns visual design through two-stage training. Supervised fine-tuning with Caption-Based Reverse Distillation (CRD) uses dense captions of well-designed images as design supervision. Reinforcement learning with Groupwise Design Reward (GDR) jointly compares all candidate images for the same request to refine lighting, composition, layout, and detail. On Qwen-Image-Bench with Qwen-Image-2.1, Qwen-Image-PE-397B improves over original requests by 7.81 points, while Qwen-Image-PE-9B outperforms all evaluated PE baselines. Further evaluations show gains in visual design, aesthetics, image quality, and human preference. We find that PE scales along three axes: training data, model size, and information density, with sufficient information density as a prerequisite for effective enhancement. Moreover, we demonstrate that Qwen-Image-PE generalizes to four additional T2I backbones, even surpassing native prompt enhancers on HunyuanImage-2.1 and FLUX 3 Image Klein. We release Qwen-Image-PE-9B at https://huggingface.co/Qwen/Qwen-Image-2.1-PE-T2I.

Abstract: Text-to-Image models reproduce societal stereotypes, and existing mitigation applies one demographic correction to the whole scene. In multi-person scene generation this creates a trade-off: global steering improves aggregate balance only by homogenizing the people within an image. Steering-based methods like Embedding Arithmetic drive the intra-image diversity below the unsteered baseline. Text- and latent-projection approaches shift the aggregate skew with only marginal gains in intra-image diversity. We present Spatially Gated Steering (SGS), which steers the demographics of each person independently by extracting per-person masks from the Diffusion Transformer's (DiT) internal attention maps at a critical denoising timestep and applying a distinct demographic vector within each mask for the remaining steps. SGS needs no fine-tuning, inversion or layout specifications, and uses a lightweight segmentor over frozen DiT attention features to localize subjects at early timesteps. On skewed occupational prompts, SGS reaches high intra-image racial and gender diversity while keeping aggregate balance competitive and image quality near baseline, a result we validate on two architecturally distinct diffusion transformers, FLUX.1-Dev and SD3.5-Large. Codebase and model weights are available at https://github.com/cvims/spatially-gated-steering

Abstract: In this paper, we formulate a novel form of conditional layout generation for graphic design, termed content-edited layout generation(CELG). CELG extends conventional content-aware layout generation (CLG), which generates a foreground layout for a fixed background image. The key distinction is that CELG treats the input image as an editable visual asset and, conditioned on a textual design intention and a foreground requirement that may be empty, produces an adapted background together with its layout. To study this task, we introduce Search-Compare-Edit(SCE), a data construction framework that supplies the paired supervision missing from existing design datasets. Starting from professional design canvases and their layouts, SCE synthesizes plausible pre-edit source images and corresponding editing instructions, yielding InstructEdit, a dataset of aligned source images, target canvases, instructions, and layouts. Based on the generated data, we train a two-flow multimodal flow matching model that couples a pretrained image editor with a layout flow transformer, enabling background editing and layout generation simultaneously within a unified framework that more closely reflects real-world design workflows. Our experiments systematically demonstrate the value of CELG as a distinct task and the performance advantages of the proposed model.

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

Abstract: Video saliency prediction is inherently harder to model than static image saliency due to the additional temporal dimension. Video saliency benchmarks rest on the premise that predicting gaze on video requires utilizing temporal activity distributed across frames. Prior work has challenged this, showing that static baselines recover a significant fraction of the explainable gaze information on LEDOV, a popular video saliency dataset, and that video saliency models fail in the same places as this static baseline. We verify that this diagnosis still stands: under a more capable gold standard than the original analysis, and an updated panel of recent architectures, the strongest temporal architecture in the panel still does not substantially improve over a fine-tuned static baseline. However, it remains unclear whether the marginal gain reflects limitations of current temporal architectures or a lack of temporal patterns in the benchmark itself. We introduce SalTempto, a video saliency benchmark with greater dynamism: 224 clips of highly dynamic content, sourced from the HACS-Segments dataset so that each clip contains an event together with its lead-up and aftermath, with gaze recordings from up to 16 subjects and a training split for adapting pretrained models. On SalTempto, the static baseline recovers only about 13\% of the headroom above the centerbias, against more than half on LEDOV. A fine-tuned temporal architecture shows a substantial gain in performance over the static baseline, indicating that it does capture meaningfully more temporal information, which LEDOV fails to measure. Yet, even this SoTA model still leaves nearly half of SalTempto's headroom unexplained, indicating room for improvement in video saliency modelling. Examination of SalTempto also lets us describe human tendencies that models miss. SalTempto link: https://huggingface.co/datasets/bethgelab/video_saliency.

Abstract: Although diffusion models produce high-quality images, they also reproduce and amplify demographic imbalances in their training data. Debiasing their generation process post-training w.r.t. some sensitive attribute usually relies on classifier guidance or explicit text extra-conditioning, but this reduces methods' applicability and output diversity. Conversely, methods promoting diversity alone do not ensure fair attribute representation. In this paper, we propose a method tackling fairness and diversity jointly that is generally applicable to any diffusion model and any sensitive attribute. To this end, an adapter connects the frozen diffusion model to a pretrained vision-language embedding space, enabling fairness and diversity guidance without sensitive-attribute annotations. For fairness, pairs of text prompts define attribute directions which guide batch composition towards specific proportions. For diversity, we introduce a score measuring disagreement between the semantic estimates derived from this representation. The formulation supports unconditional and text-conditional diffusion models, while requiring no prior knowledge or data of sensitive attribute. Experiments confirm that our method improves quality and diversity scores at comparable fairness levels.

Abstract: While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a major bottleneck lies in conditioning independently generated shots to preserve consistent characters, scenes, and objects throughout a story. Existing training-free approaches typically condition target shots using retrieved historical visuals. However, these references often suffer from severe informational mismatch, either introducing irrelevant contextual redundancy or failing to provide the full combination of required elements for the target shot. To resolve this, we present Complementary Retrieval-Augmented Prompting, an agentic framework that strategically aggregates a compact set of mutually supportive historical references to achieve complete and targeted conditioning for long-form video generation without retraining or modifying the underlying generator. Specifically, our framework explicitly models the visual elements required by each target shot by parsing the narrative script into a text-grounded visual element registry that tracks characters, objects, scenes, and their shot-level states. A VLM-annotated keyframe library further maps these elements to past visual observations. Guided by the required elements, our agent retrieves complementary references that maximize target-element coverage while minimizing historical noise. Finally, the retrieved references, structured element states, and grounding instructions are assembled into a unified prompt for the frozen video generator. This element-aware process provides comprehensive conditioning while remaining fully interpretable. Quantitative and qualitative evaluations on multi-shot story generation demonstrate that our method consistently outperforms recent-frame, memory-based, and entity-level retrieval baselines in cross-shot consistency and text-controllability.

Abstract: Establishing unbranding as a critical practice to prevent visual logos from acquiring negative connotations is standard in image generation. Large Language Models (LLMs) now face a parallel and emerging challenge. These models frequently generate brand descriptions within diverse contexts. This frequency introduces significant risks, such as trademark dilution, false attribution, and brand defamation. In response, we formally define the novel task of LLM Unbranding. We specifically address the complex challenge of managing trade dress within textual outputs. This involves neutralizing characteristic language, slogans, and stylistic markers that define brand identity. Crucially, these elements are less evident than explicit visual logos. To benchmark this task, we introduce a comprehensive evaluation dataset incorporating prominent brands from multiple commercial domains. We rigorously evaluate existing state-of-the-art machine unlearning models using this benchmark. This evaluation identifies their limitations in selective textual unbranding. Finally, we propose MUTE, a novel inference-time method that effectively neutralizes textual trade dress while preserving the LLM's general capabilities and utility. By leveraging an iterative refinement loop, MUTE systematically optimizes system instructions to safely eliminate brand leakage without requiring fragile parameter updates. Code and dataset: The evaluation dataset and code for LLM Unbranding are available at https://github.com/KajetanOzog/LLM_unbranding. The implementation of MUTE is available at https://github.com/KajetanOzog/MUTE.

Abstract: Most video editing methods focus on changing the appearance of the source video, while offering limited control over its dynamics. We introduce Reimagine Video Dynamics (RVD), a framework that disentangles a compact, editable dynamics token from visual context. We learn this token through self-supervised reconstruction: given the first frame as visual context, a renderer must recover the original video from the dynamics token, encouraging it to capture how the scene evolves rather than how it looks. This disentanglement allows video dynamics to be edited directly while preserving visual context. We develop a language-guided dynamics-token editor that transforms source dynamics into target dynamics, and train it with a scalable counterfactual video-pair pipeline and a two-stage training strategy. Extensive experiments show that RVD enables effective video dynamics editing, training-free retiming, and appearance-controlled re-rendering.

Abstract: Video text editing aims to replace or add text in a video while keeping the rest of the video unchanged, which requires the edited text to be correct in every frame and to move coherently with the scene. Despite the remarkable progress of video diffusion models, they struggle to reproduce exact stroke structures and often produce garbled or wrong characters, especially for characters with complex strokes. To address this, we propose a trajectory-aligned glyph rendering reference that provides explicit per-frame glyph guidance following the position and perspective of the text, and a depth-normalized recognizer feature supervision that supervises the generated text on multi-depth features of a frozen text recognizer with per-depth normalized errors, targeting stroke errors overlooked by the diffusion loss. We further build VTEdit, a benchmark of 288 real-scene clips with 440 annotated text trajectories covering text replacement and text addition, which will be publicly released to facilitate future research. Experiments on VTEdit show that our method outperforms image text editing methods, video editing methods, and commercial models in text accuracy and background preservation, achieving a sentence accuracy of 0.9408, and receives the highest preference in a user study.

Abstract: Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary video generators scale to 30 seconds and faithfully follow complex conditions, the textual prompt largely directs the production, planning how actions, camera trajectories, lighting, and sound unfold across multi-shot sequences. In this paper, we present WanPE, a 397B-parameter prompt enhancement model trained on 1.05M real-world videos to master director-level cinematic planning. WanPE formulates shot-level cinematic plans via video-grounded reverse construction and employs Semantic-Consistency GRPO (SC-GRPO) to faithfully preserve user requirements across shots and over time. To benchmark this capability, we curate WanPEval, a human-annotated testbed covering durations from 5 to 30 seconds across varying intent granularities, supported by approximately 11K blind pairwise assessments. When powering Wan3.0's video generator, WanPE-397B boosts human preference over raw user prompts by 10.66-18.84 points at 5-15 seconds and by a dramatic 50.86 points in the 30-second arena. Ablation studies show that reverse construction demonstrates clear superiority over forward rewriting, while SC-GRPO robustly preserves semantic fidelity across model scales. Ultimately, WanPE leads all evaluated commercial offerings at 5-15 seconds and remains competitive with Seedance 2.5 at 30 seconds.

Abstract: Marketers now deploy generative AI agents as synthetic consumers to pretest visual assets such as logos, packaging, and advertising at a fraction of human-panel cost. However, this procedure assumes that a model seeing a visual cue can also perceive its consumer meaning, which is largely untested. We stress-test the assumption using six canonical visual marketing experiments, varying the two levers managers control: model generation (GPT-4o-mini vs. GPT-5.4-mini) and input format (plain text vs. JSON). Every resulting configuration passed the manipulation checks; however, none of the configurations reproduced more than two of the six human effects, and the remainder were nonsignificant. The one exception was a significant reversal of the human pattern. Providing conceptual or empirical evidence through in-context learning steers average responses toward the human effect. Yet steering has a limit: even when it succeeds, a configuration reproduces less than half of the natural spread of human responses and so understates consumer heterogeneity. We integrate these results into an AI governance protocol (Calibrate, Intervene, Deploy) that delineates when synthetic consumers can responsibly screen creatives and when human panels remain necessary.

Abstract: Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to satisfy prompts requiring specialized knowledge, specific identities, physical consistency, or ordered events. In this paper, we present VideoGen-Agent, a multimodal agent trained through multitask agentic reinforcement learning to use external tools for video generation. The agent coordinates augmentation, generation, and verification tools through multi-turn interactions, using the prompt and intermediate observations to guide its decisions. We train a shared policy on a category-balanced dataset spanning six tasks. Supervised fine-tuning on teacher-generated trajectories establishes tool-use behavior, which is then refined through reinforcement learning. A category-aware hybrid reward evaluates tool-call validity, task-appropriate tool use, and generated video quality. We further introduce VABench, a held-out benchmark of 600 prompts covering procedural knowledge, single- and multi-entity identity preservation, physical consistency, scene composition, and multi-shot temporal structure. On VABench, VideoGen-Agent improves over its base text-to-video generator by 19.1 points, from 56.5 to 75.6. Upgrading the generation tools further raises the score to 86.1 without additional agent training. Human raters prefer the upgraded configuration over the strongest standalone baseline in 84.3% of comparisons. These results support learning tool use across video-generation tasks and show that the trained agent can benefit from subsequent advances in generation tools.

Abstract: In this paper, we address the problem of graphic design template creation, which generates a background image and a layout of foreground elements over the background to form a harmonious composition from an input text. Prior work on graphic design generation mostly adopts a sequential paradigm, where design elements are generated sequentially. We argue that such a sequential scheme falls short of faithfully capturing the dependency between the background and layout (and thus the joint image-layout distribution), which limits the quality of generated design templates. To overcome this limitation, we propose a model, InterIL, which jointly generates the two modalities, background image and layout, in a single generative process. The novel design of our joint model connects the backbones of pretrained image and layout diffusion models with a learnable communication module to explicitly model bidirectional image-layout interaction. During training, the image and layout backbones are frozen to maintain and leverage the vast pretrained single-modality prior knowledge, while only the communication module is updated, so that the model can focus on learning image-layout interaction and thereby better capture the joint image-layout distribution for improved composition harmony. Our model has no design-specific inductive bias, which allows it to better preserve the original characteristics of realistic designs. We further introduce a test-time guidance strategy to enable users to impose their specific preferences on generated results. Our experiments show that, compared with prior approaches, our model can generate significantly better results in terms of image, layout and image-layout harmonization, producing outputs closer to real samples. We also demonstrate the flexibility of our model in enforcing user preferences at inference without retraining.

Abstract: Multi-subject video generation faces two key challenges: uncontrollable fidelity strength and potential semantic drift. We address these by analyzing the internal mechanisms of Diffusion Transformers (DiTs). We found that certain attention blocks naturally form an Intrinsic Spatial Grounding Map (ISGM) that precisely locates reference subjects. Building on this insight, we propose Dual-phase Intrinsic Attention Leveraging (DIAL), a framework that uses these internal signals for both training and inference. In low-noise stages, we use ISGM to guide the attention mechanism, allowing precise control over fidelity strength during inference without retraining. In high-noise stages, we use these same maps to automatically build preference pairs at no additional cost for Reinforcement Learning (RL). This RL procedure effectively anchors the model's attention to reference subjects and mitigates semantic drift. Extensive experiments show that DIAL significantly outperforms baseline models on the OpenS2V-Eval benchmark, consistently improving identity consistency and enabling controllable fidelity strength.

Abstract: The integration of large language models (LLMs) into video generation has enabled rapid text-to-video creation and improved visual quality. However, it still falls short of professional filmmaking, where cinematographic language is less refined than human-crafted camera work and multi-shot continuity remains challenging. To address these limitations, we introduce CamPilot, a multi-agent framework that integrates cinematographic planning and camera-work control to produce more coherent, logically structured, and human-aesthetic movies. CamPilot adopts a GRPO-based learning paradigm to learn camera work planning from 14K real-world professional movies, internalizing motion patterns and composition principles that support reasoning over shooting techniques (e.g., camera angle, motion, and focal behavior) and cross-shot relationships for controllable camera-viewpoint generation. Multiple agents further collaborate and evolve to improve overall output quality. To support this work and further studies in this domain, we establish CamEval, a benchmark for evaluating camera work quality and cinematic engagement. Empirical results show that CamPilot outperforms state-of-the-art text-to-movie generation methods on cinematographic control and quality, highlighting the impact of professional camera design on movie generation.