arXiv Query: search_query=all:"text-to-image" AND all:generation&id_list=&start=0&max_results=30

UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation

2026-10-07T10:47:52Z

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

Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning

2026-10-07T05:07:09Z

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

Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data

2026-10-07T04:12:30Z

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

vLLM-Omni Technical Report: A Unified Serving Runtime for Omni-Modality Generation

2026-10-07T02:04:28Z

Interaction with intelligent systems is expanding beyond text-centric chatbots and coding agents. Speech-native assistants, visual generation and editing, world-model environments, and robot action loops require models that emit text, audio, images, video, and actions. These models differ in execution pattern: multi-stage autoregressive omni and TTS pipelines, iterative diffusion or flow-matching generators, and longer-lived world-model or robot loops that carry state across steps. As a result, serving is no longer a single text decode loop, but a heterogeneous multi-stage workflow with cross-stage transfer, streaming, and session-shaped interaction. Existing inference stacks are typically optimized for one architecture family. LLM servers deepen autoregressive scheduling and KV management, while diffusion stacks deepen denoising and parallel generation. Neither provides a shared control plane for pipelines that emit speech, pixels, or actions through separate generators, so production deployments often fall back to ad-hoc composition across disjoint runtimes. We present vLLM-Omni, a unified serving runtime for omni-modality generation. vLLM-Omni organizes each workload as a multi-stage pipeline under a single orchestrator that admits requests, advances them across stages, and demultiplexes streaming outputs. Specialized engines and stage replicas provide compute; a connector carries heavy payloads on the data plane; and session-oriented control supports long-lived duplex, world-model, and robot workloads. This report covers the architecture (stage-level KV paths, replica pools, multi-hardware platforms, and efficiency stack) and OpenAI-compatible and OpenPI APIs for omni, TTS, image/video, world-model, robot, and duplex workloads. We evaluate on the multimodal nightly CI on H100 (TTS and MiniCPM-o on H200), focused on Qwen3-Omni.

Visual Memory Attacks Can Persist Through The KV Cache

2026-10-06T19:25:08Z

Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input continue to steer a model even after that input is removed from its context? We show that attacks can be trained to persist through the key/value (KV) cache of subsequent tokens, allowing adversarial influence to outlive direct access to its source.We consider the Visual Memory Injection (VMI; Schlarmann and Hein, 2026) attack setting, in which an adversarial image that stays in the context plants a hidden backdoor: the model behaves normally until a chosen trigger elicits an attacker-chosen response. We first demonstrate persistence in this setting with optimized soft prompts, which remain effective after we mask the prompt from attention. We then introduce Persistent Visual Memory Injection (P-VMI), which optimizes images to preserve this adversarial behaviour after they are masked from attention. These attacks persist over conversations substantially longer than those used during optimization. On Qwen3-VL-8B-Instruct, P-VMI achieves up to approximately $90\%$ target success in its strongest configuration and remains effective under a stricter removal setting that exposes the image only on the first turn. A cache-swap ablation localizes the persistent influence to the KV cache. Finally, we show that these attacks can be trained to survive compaction that retains the KV cache of a summary generated by the same model, demonstrating that adversarial behaviour can persist in cached state without continued access to its source.

Two Halves are More than One: Phase-wise Velocity Distillation for Fast and High-Quality Image Generation

2026-10-06T10:03:30Z

Recent diffusion-based image generation backbones have grown substantially in scale, making the network inference cost increase rapidly. While diffusion distillation techniques can reduce the number of inference steps, high-quality image generation within a single full-backbone-forward compute budget remains challenging. Existing one-step methods typically allocate this budget to a single evaluation of a monolithic student. However, approximating the heterogeneous coarse-to-fine transport with a single monolithic mapping is difficult and often leads to over-smoothed outputs. To address this issue, we propose Phase-wise Velocity Distillation (PVD), which partitions the generation timeline into a coarse and a fine phase, and models the transition within each phase via the average velocity. A dedicated half-sized expert is assigned to each phase, decoupling structural composition from detail refinement while keeping the cumulative computation equivalent to one full-backbone forward pass. We show that the use of two half-sized phase-specific experts outperforms a single full-size monolithic student. On class-conditional image generation, PVD achieves an FID of 1.48 on ImageNet 256 x 256. On more complex text-to-image (T2I) tasks, PVD-distilled models (Stable Diffusion 3.5-Medium, FLUX.1-dev, Qwen-Image) produce results competitive with their multi-step teachers, significantly outperforming prior distillation methods. Moreover, across the evaluated T2I backbones, PVD reduces active parameters by 49.10-50.89% and peak VRAM by 45.76-48.36% compared to the corresponding teachers. Source code and distilled models are available at https://github.com/PolyU-VCLab/PVD.

Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation

2026-10-06T03:18:07Z

Personalized image generation aims to synthesize text-driven images conditioned on reference images, while mainly casting the generation as image customization for foreground and style transfer for background. Previous arts of diffusion models suffers from the text misalignment with background for image customization and foreground for style transfer during the denoising process. Such facts, as we observed, rooted from the entanglement among hybrid frequency bands during the denoising process. To address such salient limitation, in this paper, we study personalized generation based on dual references - customization and color and style reference - and propose a paradigm to disentangle these Dual image references within Frequency-aware Diffusion Models, dubbed Dual-FDM, to simultaneously tackle two crucial personalized image generation tasks: customization style transfer and color style transfer, by disentangling different frequency bands via mask strategy within frequency domain. For customization style transfer, we replace the mid-frequency band of the background in the style reference with that from the foreground of the customized reference. For color style transfer, we substitute the low-frequency band of the background in the style reference with that from both the foreground and background of the color reference. Both the substituted frequency bands are used as the key and value to reconstruct the query foreground and background of the denoised personalized image.Extensive experiments validate the superiority of Dual-FDM over the state-of-the-art diffusion models for personalized image generation. Our code can be accessed from https://github.com/htyjers/Dual-FDM.

Global Transport Couplings for Classifier-Free Guided Flows

2026-10-06T00:39:45Z

Optimal-transport couplings have been shown to reduce training variance in unconditional flow models, but their role in conditional generation remains unclear. A natural approach constructs separate couplings for each condition, but this is impractical for large or continuous conditioning spaces found in modern image foundation models. We introduce Global Transport (GT), a global class-agnostic optimal-transport coupling, computed without class labels. GT can associate different conditions with different regions of the source noise, and consequently worsens performance without guidance. However, when combined with classifier-free guidance (CFG), GT consistently improves generation across domains, model scales, and sampling budgets. This reversal suggests that couplings for conditional flows should be evaluated both empirically and theoretically under the guided flow used at inference, rather than on unguided generation. We evaluate GT over both discrete class and continuous text conditioned image generation across model scales, and investigate how coupling choice alters guided trajectories. These results identify coupling design in the guided flow setting as a simple training time axis to improve performance without modifying existing architectures, samplers, or guidance mechanisms.

Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation

2026-10-05T18:50:09Z

Wrapping an image generation model in an agentic harness can effectively boost Text-to-Image task performance: the harness can leverage memory, skills, workflow orchestration, result verification, and iterative refinement to continually construct and revise prompts, thereby eliciting better images. These gains, however, remain external to the diffusion model and are realized only while the full harness runs. We propose Diffusion On-Policy Context Distillation (D-OPCD), which treats the agent-improved prompt as privileged context and distills the knowledge encoded in the agent harness into the weights of the diffusion model, so that the model retains part of the harness's benefit when conditioned on the original query alone. Using a Text-to-Image agent equipped with our proposed Auto Skill Evolver (ASE), we show that D-OPCD can internalize harness capabilities into the generator's weights, raising the average direct-generation score from 60.52 to 65.09 across four benchmarks. With this knowledge absorbed into the weights, the harness can shed its saturated skills and resume evolving: a second ASE round on the updated generator improves on a skill-free harness by additional 1.83 points, pointing toward text-to-image systems in which harness and model keep improving each other through continual co-evolution.

Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations

2026-10-05T15:22:19Z

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

On Color Alignment in VAE Latent Spaces and Its Applications

2026-10-05T08:53:58Z

Variational autoencoders (VAEs) are a key part of modern text-to-image models, which generate images within their latent space. VAEs are known to disentangle the main factors of variation in the data, and color is known to be one of the most structured of these in natural images: decorrelating it yields one luminance axis and two opponent-color axes. Color should therefore be expected to emerge as a distinct factor in the VAE latent space. Yet how these latent spaces represent color remains largely unexplored. In this work, we show that the VAEs of text-to-image models share a color subspace aligned with brightness and opponent-colors. Through a linear approximation of the encoder and targeted latent steering, we find this subspace consistently across a broad range of VAEs, from SD1.5 to FLUX.2 and Z-Image. Building on this characterization, we propose three applications: ColorTuning, which achieves state-of-the-art in precise numerical color generation on the fine-grained CSS3/X11 system of GenColorBench, saturation control, to adjust the global chromatic intensity, and color transfer, to change the palette to match a reference. The code and models are publicly available at https://julian075.github.io/Color_Subspace/

Safe Image Generation via Reinforcement Learning

2026-10-05T07:24:01Z

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

Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models

2026-10-04T23:12:01Z

Existing attacks on unlearned diffusion models assume that the erased concepts are known in advance and focus on recovering them. In practice, however, model providers may not disclose which concepts have been removed, and even with access to the original base model, an adversary may still lack a clear target to attack. In this paper, we aim to answer the following critical but overlooked questions: which concepts have been erased from the model, and how many have been erased in total? To this end, we present Tracer, a framework that rapidly and accurately identifies erased concepts and estimates their number. Tracer efficiently identifies erased concepts without generating and classifying images. By combining lightweight spectral analysis of weight footprints, it enables efficient search over large candidate vocabularies. To distinguish multiple erased concepts, we introduce a footprint coverage objective that guides sequential discovery. Tracer estimates the number of erased concepts by detecting a sharp decline in candidate confidence as the selected concepts account for the erasure footprint, without requiring labeled examples for calibration. The framework requires only lightweight linear algebra and limited forward probes, with no prior knowledge of the unlearning algorithm. Experiments across text-to-image and text-to-video backbones and diverse unlearning methods demonstrate that Tracer identifies erased concepts and estimates their number in seconds, achieving 150 to 137,000 times and 133 to 20,000 times speedups over MIA and brute-force search on image and video models, respectively, with substantially higher identification accuracy.

No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models

2026-10-04T17:37:49Z

Text-to-image diffusion models can generate prohibited content, which motivates concept erasure through machine unlearning. Most erasure methods intervene at the text interface, through prompt modification or localized updates to text-conditioning weights, and they are evaluated by what the model outputs for given prompts. Such evaluation cannot see what the network still encodes. Latent-space auditing, which bypasses text conditioning and probes the denoising network directly, shows that erased concepts remain recoverable from internal representations. We find that this also holds for methods built to be robust against adversarial prompts, and that the problem grows with the number of erased concepts. We propose Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models (AVCE), a framework that grounds erasure in the model's latent representations. AVCE audits the embedding neighborhood of each concept and condenses the discovered vulnerable directions into an anchor at the weakest geometric point. It edits cross-attention and self-attention projections in closed form at this anchor, then fine-tunes the two pathways with pathway-level auditing losses, using orthogonal gradient projection to consolidate multiple concepts. Experiments on SD v1.5, SDXL, and Flux 1.0 across object, explicit-content, and artistic-style unlearning show that AVCE reduces attack success rates by 5.07x and improves auditing scores by 3.84x over the strongest baseline, while preserving competitive generation quality.

Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models

2026-10-04T09:06:57Z

Adapting step-distilled text-to-image (T2I) models through post-training incurs additional computational costs and affects native few-step generation behavior. This motivates a complementary route beyond style-specific adaptation: drawing on the visual knowledge already encoded in step-distilled T2I models to elicit stylistic capabilities through language. Pursuing this direction requires textual guidance that captures how visual attributes jointly define a style and remain applicable as the depicted content changes. To explore this approach, we introduce StyleForge, a fully automatic, training-free framework that expresses reference styles as reusable rendering instructions. By integrating overall rendering characteristics with local color and lighting behavior, StyleForge organizes visual evidence from reference images into a coherent specification of how the target style should be expressed. The specification is then compiled into textual guidance that can be reused across content prompts, enabling frozen step-distilled T2I models to render different subjects and scenes in the reference style while retaining native few-step generation. Extensive experiments show relative gains of up to 29.47\% in generation quality scores over the strongest baseline, while Pareto analysis indicates that improved stylization is accompanied by strong adherence to the requested content.

VisualErase: Dual-Branch Visual Trajectory Redirection for Robust Concept Erasure in Text-to-Image Diffusion Models

2026-10-04T06:44:27Z

Concept erasure is essential for the safe deployment of text-to-image diffusion models, as they may reproduce harmful, copyrighted, or privacy-sensitive content learned from unconstrained large-scale data. Existing methods typically erase unwanted concepts while preserving general generation capability by redirecting target-related text-to-image mappings. However, recent studies show that erased models may still retain visual generative trajectories of target concepts, leaving them vulnerable to adversarial recovery attacks and revealing a fundamental gap between redirecting text-to-image mappings and truly removing visual knowledge. To bridge this gap, we propose VisualErase, a new paradigm that redirects concept-bearing visual generative trajectories toward explicitly defined concept-removed outcomes. To enable this redirection, we use structure-preserving image editing to construct content-aligned, concept-removed counterparts for source images, providing explicit visual endpoints that retain non-target content. We then derive a denoising target from each source-to-counterpart pair and use a dual-branch redirection loss to align both text-conditioned and unconditional predictions with this target, since conditional supervision alone does not explicitly constrain generation without textual guidance. To mitigate the adverse effects of concept erasure on non-target generation, we jointly optimize the redirection loss with a counterpart retention loss that matches denoising predictions from the frozen pretrained model. Across style, celebrity, and nudity erasure, VisualErase limits the maximum attack success rate over seven attacks to 0%, 8%, and 0.1%, respectively, while retaining general generation quality. These results highlight the importance of visual trajectory redirection for robust concept erasure beyond text-to-image mappings alone.

Geometry-Aware Preference Optimization for Text-to-Image Diffusion Models

2026-10-04T05:55:08Z

Preference alignment has become a standard practice for text-to-image diffusion models. Direct Preference Optimization (DPO) simplifies this process by eliminating explicit reward modeling. Its diffusion variant, Diffusion-DPO, has become a widely adopted baseline. Diffusion-DPO essentially encourages the likelihood of preferred samples while suppressing dispreferred ones. In this paper, we revisit DPO-style alignment methods for diffusion models from the perspective of the manifold hypothesis. Under this view, natural images concentrate near a low-dimensional manifold embedded in the high-dimensional ambient space, whereas DPO directly optimizes preference distributions in the full space without accounting for this geometric structure. This creates a mismatch in the optimization dynamics: it suppresses geometry-preserving tangential updates, while insufficiently restricting hazardous normal-direction updates. This mismatch gradually degrades image quality and diversity. To address this issue, we propose Anisotropic Geometry-Aware Preference Optimization (APO), which replaces the uniform Euclidean treatment of prediction errors with a geometry-aware anisotropic metric derived from the reference model. Concretely, APO adaptively strengthens regularization in directions where the reference denoising function is highly sensitive, while relaxing constraints in directions that permit safe semantic adjustment. This recalibrates preference optimization according to the local manifold geometry, and maintains the original manifold structure. Experiments show that APO achieves strong performance and an average win rate exceeding 60\% against various existing alignment methods across diverse benchmarks. It requires significantly fewer training steps than prior methods, and preserves generation diversity throughout training.

DEPICT: Scoring Text-to-Image Alignment by Answer Agreement

2026-10-02T17:13:49Z

Image-text alignment is a core problem in computer vision with applications in caption evaluation, hallucination detection, data curation, and the benchmarking of text-to-image (T2I) generators. As T2I models improve, benchmarking has become demanding, requiring metrics capable of finding a series of issues like missing objects, swapped attributes, miscounts, and ignored negations. Recent work addresses this by fine-tuning evaluators on preference data or by prompting a vision-language model, either holistically with the caption or with decomposed verification questions. However, existing approaches fall short: fine-tuned metrics remain bound to one backbone and training distribution; holistic metrics miss fine-grained details; and decomposed metrics rely on a fixed-YES assumption that penalizes faithful images whenever that assumption fails. In contrast, we propose DEPICT, a training-free metric that replaces fixed reference answers with expected agreement between image-based and caption-only answers, weighting questions by how decisively the caption determines them. By replacing fixed references, our agreement rule increases negation accuracy from 19% to 88%. To recover the context lost during decomposition, DEPICT merges this agreement score with a holistic score. We evaluate DEPICT on five benchmarks and eleven backbones from three model families and find that it surpasses all training-free metrics and exceeds fine-tuned evaluators on two out of three human-correlation benchmarks.

ProgressNet: Sketching and Prompting with a Frozen Text-to-Image Model

2026-10-02T16:05:29Z

Humans draw progressively: a few strokes, a look at the result, a stroke erased, a prompt revised. Image generators do not work this way. They typically take a finished sketch and produce the image in a single pass, so every edit starts the picture again, and the models that do keep state across turns are driven by text, cannot take a stroke, and are too slow to draw with. We present ProgressNet, a training-free framework that lets a frozen text-to-image model follow a drawing session as it unfolds: strokes are added and erased, the prompt is revised, and the image keeps up at about a second per turn. It needs no new parameters because the frozen model already has what a progressive generator needs, a pathway through which the previous turn can be remembered, layers that can carry appearance forward without freezing structure, and an internal signal of how far to trust an unfinished sketch; three inference-time mechanisms (Previous-Concept Memory, Layer-Selective K/V Injection and Banded Adaptive Control) use each in turn. As a sketch fills in, every existing method degrades, the FID of the FLUX+ControlNet baseline doubling between 10% and 100% completion on FS-COCO, while ProgressNet's barely moves; it maintains strong fidelity and progressive coherence across three sketch domains and is preferred by users over five competitors, most widely on erasure.

AREX: Affine-Residual Exponential Integrator for Few-Step Sampling in Flow Matching

2026-10-02T15:50:49Z

We introduce AREX, a training-free sampler for pretrained flow matching models that uses the target mean and covariance to capture an analytically tractable part of the sampling dynamics. We show that the velocity field of the moment-matched Gaussian target is the $L^2$-optimal affine approximation to the marginal velocity field. This motivates decomposition of the learned dynamics into an affine component over the whole sampling path, determined by the first two target moments, and a neural residual term. AREX keeps the affine component and integrates it using an explicit matrix-valued propagator. In turn, we only require to integrate over the residual term. This differs from scalar exponential integrators, which analytically handle only isotropic linear dynamics. Across image and text-to-image generation tasks, AREX consistently improves sample fidelity in the few-step sampling regime without retraining the underlying model.

NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models

2026-10-02T10:03:56Z

Text-to-image (T2I) models are judged by benchmarks that measure whether requested content appears, but these benchmarks largely overlook the complementary ability to satisfy negated constraints, for example, generating "a non-red cup." Measuring negation raises challenges not faced by affirmation-based benchmarks and requires careful prompt and evaluation design. We introduce NegT2IBench, a benchmark of 4,800 prompts covering two attribute types and four relation categories. Prompts are organized by polarity: the number of positive statements that must hold and negated statements that must not, each ranging from 0 to 2. Varying the two independently separates the effect of negation from the effect of prompt complexity. Our detector-based scoring is reproducible, auditable, and pinpoints which requirement failed. On 600 images with three-annotator labels, it agrees with humans as closely as vision-language judges up to 30x larger, while using only a fraction of their GPU memory. Across eleven T2I models and 211,200 images, nine score lower on a single negated statement than on a single positive one. Per-statement scoring reveals that the loss is largest for color and near zero for proximity, and that 41.5% of failed statements render exactly what the prompt forbids. Rendering what a prompt asks for and withholding what it forbids are distinct capabilities that an aggregate compositional score cannot distinguish. NegT2IBench measures the latter directly, providing a controlled testbed for diagnosing negation failures and developing methods to overcome them.

Where to Look Is Not How to Fix: Pre-Denoising Diagnostics and Modality-Dependent Control in Diffusion Composition

2026-10-02T09:50:43Z

Understanding compositional failures in text-to-image diffusion requires identifying both where stress is detectable and how intervention changes the output. We study these questions through a controlled anchor--stress protocol that jointly evaluates text-encoder diagnostics and denoiser interventions. We introduce a text-only Compositional Stress Index (CSI), which separates common from rare compositions across SD1.5, SDXL, and the SD3 text path and provides an upstream diagnostic coordinate. A matched six-prompt localization study links intervention location to distinct outcomes: residual-minimizing embedding adapters improve representation fit, while downstream cross-attention intervention increases color hit rate (CHR) by 0.0272. Across SD1.5 and SDXL denoiser blocks, the largest positive signed diagnostic-accessibility mean occurs at the deep encoder, whereas selective boost has its largest positive mean CHR response at decoder blocks. Selective subtraction and broad ablation reveal further modality- and architecture-dependent responses, including a substantial CHR decrease when SDXL decoder cross-attention is broadly ablated. We find a diagnosis-control dissociation under our controlled attribute-object composition setting: compositional defects are diagnosable before denoising, but the representation coordinate that exposes risk is not necessarily the coordinate or modality that improves generation.

Recursive Self-Improvement in Unified Multimodal Models

2026-10-02T08:34:21Z

Unified multimodal models (UMMs) understand and generate both text and images, which lets a model produce its own training data. Existing self-improvement in UMMs keeps supervision on the visual side, where image understanding judges image generation. We propose recursive cross-capability self-improvement (RSI), a training loop in which the text and visual abilities of a UMM supply training data for one another. In each round, the model generates images and reads them to find where it falls short. It then writes programs aimed at these shortcomings, and execution verifies every result against its specification. Verified renders train image generation, while labeled renders and the model's own correct programs train visual understanding and program writing. Program execution thus acts as a source of truth outside the model, so errors do not accumulate across rounds. We study RSI on charts and build BasicChartBench to evaluate open models early in training. On requests worded differently from training, four rounds of RSI raise the score from 45.7% to 60.2%, while continued training stays at 46.3%. Verified construction carries most of the gain, and targeting the model's failures adds 3.5%. Along the way, the share of verified programs rises from 48.9% to 95.2%, and the reader's accuracy on edited renders rises from 55.6% to 87.4%.

Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards

2026-10-02T08:05:34Z

Recent text-to-image generation models have achieved remarkable visual quality, but improving them through post-training remains challenging because no single reward signal captures the full range of human preference. In this work, we develop a simple and effective post-training recipe for open-domain text-to-image generation based on the composition of complementary reward signals. Our reward system consists of two main components: a preference reward, trained on large-scale human preference data using a Bradley-Terry objective to capture overall human aesthetic and perceptual preferences, and rubric-based rewards, which explicitly evaluate prompt faithfulness and other desirable properties while providing safeguards against reward hacking. A key challenge is how to combine these heterogeneous reward signals. We show that a naive weighted average leads to suboptimal optimization behavior, and propose a simple reward composition strategy that more effectively balances preference optimization with rubric satisfaction. In the Arena text-to-image leaderboard (https://arena.ai/), our RL-trained Flux2dev achieves an Elo rating 69 points above the base model, and our post-trained Ideogram-4 surpasses every open-source model on the leaderboard, reaching an Elo of 1223.5. (Claims of state-of-the-art performance are based on the Arena leaderboard snapshot as of September 4, 2026.) Our results suggest that effective rewards for frontier generative-model training require broad coverage of user intent and robustness to exploitation under optimization. To support reproducible research, we release Arena-T2I-Training, a 1K subset of training data that recovers some gains of full-scale training, providing a resource that we hope will facilitate future work on post-training for text-to-image models.

TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows

2026-10-02T07:56:57Z

Recent text-to-image models have made substantial progress in photorealism, aesthetics, and text-image alignment. Yet visually appealing images can still violate real-world plausibility, exhibiting malformed object structures, impossible anatomy, physically implausible interactions, or inconsistent spatial relationships. Such failures are not well captured by existing fidelity, aesthetics, preference, or alignment metrics. To address this gap, we introduce TerraVis, a framework for evaluating world-grounded visual consistency in generated images. TerraVis defines a structured taxonomy of world-consistency violations spanning object-, interaction-, and scene-level failures, and employs a multi-stage evaluation framework to identify and quantify them. Given an image, TerraVis first uses an MLLM to assess its eligibility for evaluation, then detects violations across 18 taxonomy-defined types and classifies them as minor or major to derive an overall world-consistency score. Across diverse open-source and proprietary text-to-image models on two widely used benchmarks, TerraVis achieves the strongest correlation with human judgments of world consistency among existing metrics. Our benchmark results further show that models that achieve strong performance on conventional metrics can still exhibit substantial world-consistency failures. These findings highlight world consistency as a complementary evaluation dimension and demonstrate that TerraVis enables systematic quantification, diagnosis, and comparison of such failures. Our code is publicly available at https://github.com/ShyFoo/TerraVis.

Correcting Guided Diffusion Trajectories with Spectral Alignment

2026-10-02T03:30:02Z

The practical success of conditional image generation hinges on fine-grained differences in condition alignment and visual fidelity. Classifier-free guidance (CFG) is central to this success, but its lack of an explicit criterion makes it difficult to assess whether the guided trajectory is progressing as intended. To address this gap, we show that spectral alignment provides a principled criterion for understanding guidance behavior and improving guided diffusion sampling through adaptive correction. Our analysis identifies the spectra of intermediate states as an indicator of consistency with the expected spectral evolution of the forward process. Based on this observation, we introduce Spectral Correction Guidance, a method that corrects deviations from an analytic reference spectrum during sampling. The proposed method is training-free and applicable across diffusion backbones and conditional generation tasks without modifying the underlying model. Experiments demonstrate consistent gains in preference-based metrics over baseline guidance methods in text-to-image generation and improved generation quality over CFG on ImageNet. These improvements persist across a range of guidance scales and with fewer denoising steps. Our analyses and ablations provide insight into guidance behavior and how the proposed method affects generation quality.

DAGS: Disentangled Appearance-and-Geometry Steering of a Frozen Image DiT for Temporally Stabilized Generative Rendering

2026-10-01T22:59:42Z

Diffusion transformers (DiTs) generate high-fidelity images from text and image conditions, but their outputs carry large variance and their faithfulness to a desired target depends heavily on how the condition is supplied. We present DAGS, a lightweight, attention-free, disentangled appearance and geometry conditioning scheme that steers a frozen image DiT to produce high-fidelity, highly faithful, and independently controllable renders. Two small convolutional encoders compute conditioning features once per frame and inject them as a learned, per-layer, element-wise residual into the image tokens, avoiding the quadratic cost of stacking conditions through attention. Because control and temporal handling live outside the frozen backbone, we retain its vast pretrained prior and eliminate backbone-overfitting risk. We further add a small recurrent lighting stabilizer and a training-free temporal guidance term that, coupled with our conditioning, elevate a per-frame image model into a streaming renderer. DAGS produces controllable, high-quality renders at a fraction of the compute of path tracing; it is not real-time, trading compute for controllability and quality. On a matched 1-spp + G-buffer input, per-frame DAGS reconstructs +8.6 dB / +10.1 dB PSNR over the real-time denoiser Intel OIDN and the diffusion renderer RGB<->X while being 2.5-8x more temporally stable perceptually (temporal-LPIPS flicker).

Octrees as an Explicit 3D Language

2026-10-01T19:10:13Z

Existing 3D large language models (LLMs) compromise on two fronts: they compress shapes into latent codebook indices or coordinate text, which removes spatial structure from what the model observes, and they acquire the 3D modality by fine-tuning the backbone, which overwrites its general language ability. We present OctLLM, which addresses both limitations. Geometry enters as an explicit 3D sequence of octree occupancy tokens. However, full octree sequences grow rapidly with depth; OctLLM therefore randomly empties penultimate-level nodes and omits descendants while preserving shape, yielding a shorter coordinate- and depth-anchored Sparse Octree (S-Octree) for position-aware mask-modeling generation and 3D understanding. On the other front, existing methods introduce a new modality with full fine-tuning or LoRA, but full fine-tuning is costly, LoRA limits 3D capacity, and both modify the language pathway. OctLLM instead adds 3D capacity in parameters separate from the pretrained ones: mesh tokens are routed through independent trainable branches in a subset of blocks while text and image tokens retain the frozen vision-language pathway, and the two streams interact through shared self-attention. It trains far fewer parameters than full fine-tuning, yet sets a new state of the art among unified multimodal LLMs, lowering image-to-3D FID by $17.4\%$ and raising render-grounded captioning by $28.7$ points over ShapeLLM-Omni, while matching the backbone on general language benchmarks.

Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion

2026-10-01T18:50:24Z

Text-to-image generation enables users to explore several images generated from the same prompt. For these generated images to be useful, each one must reflect the user's preferences, measured by a learned reward, and differ visually from the others to maintain diversity. Existing methods are limited: they either address reward and diversity separately or combine them in one aggregate score, enabling high diversity to offset low rewards. In this paper, we address these limitations by formulating generation as satisficing: every image (candidate) must satisfy a reward floor and the batch of images must satisfy a diversity cutoff. The reward floor controls the balance between worst-candidate reward and batch diversity; we show that varying this floor defines a Pareto frontier. To traverse this frontier, we introduce SatisDive, a training-free inference-time method. SatisDive uses a batch-relative reward cutoff to distinguish lower- from higher-reward candidates, emphasizing reward improvement for candidates below the cutoff and diversity among candidates above it. On Pick-a-Pic, at matched DreamSim, SatisDive improves worst-candidate reward over FK steering by up to 0.43 with FLUX.1-dev as the base model and HPSv3 as the reward, and by up to 0.70 with SANA-1.6B as the base model and ImageReward as the reward. More broadly, across their overlapping DreamSim ranges, SatisDive's satisfaction-diversity curve Pareto-dominates FK steering's curve in each setting.

Moore, Escher, Penrose: A Conformal Golden Braid

2026-10-01T17:59:59Z

I don't think I have ever done anything as peculiar in my life. Among other things, it shows a young man looking with interest at a print on the wall of an exhibition that features himself. How can this be? Perhaps I am not far removed from Einstein's curved universe.'' So wrote M.C. Escher about his 1956 lithograph Print Gallery. Nearly half a century later, a mathematical analysis related its geometry to an untwisted source image through a conformal power map $z \mapsto z^α$, $α\in \mathbb{C}$. Building on this construction, we use a frozen text-to-image diffusion model to generate new self-referential scenes. Prompting alone does not enforce the recursion, while a post-hoc transformation can leave structures poorly connected. Applying the transformation during sampling is also insufficient: the denoiser may "repair" the intended distortion or drift out of the prescribed geometry. We construct a generalized inverse $T^\dagger$ of the non-invertible image transformation $T$, adapted to its recursive constraint. In the idealized formulation, the Penrose identity $TT^\dagger T = T$ makes $TT^\dagger$ an idempotent projection onto geometrically admissible images. Yet denoising only the transformed image remains an out-of-distribution task, even with projection. We therefore braid denoising steps with $T$ and $T^\dagger$: source-space steps develop the untwisted scene, while transformed-space steps refine its appearance and connections in the final geometry. We generate Print Gallery-like compositions and explore further transformations. Rather than distorting a finished image, we let the scene and its distortion develop together.