# ai-image-generator

AI image generation is the use of machine learning, particularly neural networks, to create images from text, sketches, sample pictures, or learned patterns.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## AesDistill: Distilling Generative Aesthetics for Image Color Enhancement

DevFeed: [AesDistill: Distilling Generative Aesthetics for Image Color Enhancement](<https://devfeed.tech/articles/aesdistill-distilling-generative-aesthetics-for-image-color-enhancement-145556.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25635>)

Author: Chuanzhi Xu, Chengkun Yue, Huiqi Liang, Haoyang Li, Zihan Deng, Qingwen Zeng, Pengfei Ye, Weidong Cai

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Color Grading](<https://devfeed.tech/topics/color-grading.md>), [image editing](<https://devfeed.tech/topics/image-editing.md>), [Image](<https://devfeed.tech/topics/image.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>)

Tags: [color](<https://devfeed.tech/tags/color.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [distilling](<https://devfeed.tech/tags/distilling.md>), [enhancement](<https://devfeed.tech/tags/enhancement.md>), [generative](<https://devfeed.tech/tags/generative.md>), [image](<https://devfeed.tech/tags/image.md>)

### AI overview

AesDistill transfers color-editing aesthetics from four open-source generative models into a compact 1.13-million-parameter student, aiming to preserve image semantics while avoiding the narrow preferences represented by expert targets. The authors generated 64,644 teacher-edited images at a cost of about 3,360 H100 GPU-hours and trained the student with confidence-weighted supervision. In evaluations using 12 aesthetic and 4 image-quality assessment models, teacher targets ranked above the FiveK and PPR10K expert-target means; across both datasets, the student outperformed 20 baseline methods and ranked behind the four teachers. These are reported results from the abstract.

### Source excerpt

arXiv:2611.25635v1 Announce Type: cross Abstract: Image color enhancement aims to improve visual appeal, but previous methods often learn to reproduce ground-truth expert targets. These targets reflect the preferences of a few experts and cover a limited range of aesthetic choices. Matching them does not ensure stronger aesthetic quality across different tastes and scenes. By contrast, large generative models learn rich visual knowledge from large image collections and often produce vivid, appealing image edits. However, direct generation can change the source image's semantic structure along with its colors. In this paper, we introduce AesDistill, a framework for distilling generative aesthetics into image color enhancement. We use 4 leading open-source large generative models to produce 64,644 edited images as teacher targets at a cost of about 3,360 H100 GPU-hours, forming the AesDistill Dataset. AesDistill also includes AesDistill Student, a 1.13M-parameter model that learns teacher color changes through confidence-weighted supervision while preserving the source image's semantic structure. We evaluate AesDistill with 12 aesthetic and 4 image-quality assessment models. Every teacher's targets rank above the FiveK and PPR10K expert target means in the joint assessment. Across both datasets, AesDistill Student outperforms all 20 baseline methods and ranks directly behind the 4 teachers. These results demonstrate that distilling aesthetics from generative models enables a compact student to outperform methods trained on expert targets.

## Paint-Anything: Unified Any-Color Control for Image Generation and Editing

DevFeed: [Paint-Anything: Unified Any-Color Control for Image Generation and Editing](<https://devfeed.tech/articles/paint-anything-unified-any-color-control-for-image-generation-and-editing-144929.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.20816>)

Author: Ji Xie, Dewei Zhou, Xinyu Huang, Zhennan Chen, Xun Wang

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Image](<https://devfeed.tech/topics/image.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [image editing](<https://devfeed.tech/topics/image-editing.md>), [color](<https://devfeed.tech/topics/color.md>), [hex value](<https://devfeed.tech/topics/hex-value.md>), [flux](<https://devfeed.tech/topics/flux.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [color](<https://devfeed.tech/tags/color.md>), [compact-models](<https://devfeed.tech/tags/compact-models.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [flux-2](<https://devfeed.tech/tags/flux-2.md>), [generation](<https://devfeed.tech/tags/generation.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [hex](<https://devfeed.tech/tags/hex.md>), [hex-value](<https://devfeed.tech/tags/hex-value.md>), [image](<https://devfeed.tech/tags/image.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [interface](<https://devfeed.tech/tags/interface.md>), [labeling](<https://devfeed.tech/tags/labeling.md>), [language](<https://devfeed.tech/tags/language.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [model](<https://devfeed.tech/tags/model.md>), [object](<https://devfeed.tech/tags/object.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [supervision](<https://devfeed.tech/tags/supervision.md>)

### AI overview

Paint-Anything trains a shared hex-prompt interface to control object colors in both image generation and editing. Its Paint-500K pipeline uses object grounding, perceptual color labels, and synthesized editing pairs from real images; because shadows make those labels approximate, it adds pure-color anchors with exact hex-matched pixels, used only at high-noise timesteps. The paper evaluates object-level color fidelity with ACBench-T2I and ACBench-Edit. On FLUX.2-4B, it reports scores 85.3% and 28.3% higher than the base model on those benchmarks, respectively, and the highest average CompColor score among compared methods.

### Source excerpt

arXiv:2609.20816v3 Announce Type: replace-cross Abstract: Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and colorization, but often relies on dedicated color representations or specialized inference procedures. Advances in large language models offer a simpler starting point: even compact models can associate hex values with color semantics. We present Paint-Anything, which learns a shared hex-prompt interface for generation and editing through object-level color supervision. We develop a data pipeline that constructs Paint-500K from real images through object grounding, perceptual color labeling, and editing-pair synthesis. Since shadows make real-image labels only approximate colors, we complement this supervision with pure-color anchors whose pixels exactly match their paired hex values. These anchors are used only at high-noise timesteps, leaving low-noise training to natural images. We further introduce Any Color Benchmark (ACBench), comprising ACBench-T2I and ACBench-Edit, to measure object-level hex color fidelity across both tasks. On FLUX.2-4B, Paint-Anything improves ACBench-T2I and ACBench-Edit scores by 85.3% and 28.3%, respectively, relative to the base model, with ablations supporting the training recipe. It also achieves the highest average CompColor score among the compared methods.

## Inject Where It Matters: Objective-Dependent Feature Control in Rectified-Flow Image Editing

DevFeed: [Inject Where It Matters: Objective-Dependent Feature Control in Rectified-Flow Image Editing](<https://devfeed.tech/articles/inject-where-it-matters-objective-dependent-feature-control-in-rectified-flow-image-editing-145589.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25811>)

Author: Nina Goncharova, Alexandra Ivanova, Aibek Alanov

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [image editing](<https://devfeed.tech/topics/image-editing.md>), [Image processing](<https://devfeed.tech/topics/image-processing.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [diffusion-transformers](<https://devfeed.tech/topics/diffusion-transformers.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [bench](<https://devfeed.tech/tags/bench.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [feature-injection](<https://devfeed.tech/tags/feature-injection.md>), [flux](<https://devfeed.tech/tags/flux.md>), [image-editing](<https://devfeed.tech/tags/image-editing.md>), [inference](<https://devfeed.tech/tags/inference.md>), [masking](<https://devfeed.tech/tags/masking.md>), [masks](<https://devfeed.tech/tags/masks.md>), [objectives](<https://devfeed.tech/tags/objectives.md>), [top-k](<https://devfeed.tech/tags/top-k.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

### AI overview

The method controls source-feature injection in prompt-driven FLUX image editing through adaptive spatial masks and REINFORCE-selected Top-K transformer blocks. Masks gate injection using differences between source- and target-conditioned outputs at matched inversion states; selected blocks remain fixed at inference, with no online search. On PIE-Bench with FLUX.1-dev, masking controls the alignment-preservation trade-off. Across 60 validation examples, a learned nine-block set achieved lower whole-image LPIPS than RF-Edit's 18-block set in the same masked pipeline, with slightly lower alignment. It had the lowest LPIPS among 50 random nine-block sets, though not the highest reward. Objective sweeps favored different blocks for preservation and alignment.

### Source excerpt

arXiv:2611.25811v1 Announce Type: new Abstract: Many prompt-driven FLUX editing methods rely on injecting source features into target-conditioned generation, creating an inherent trade-off between source preservation and the desired edit. We address this problem by controlling where source features are injected and which transformer blocks are used. First, we introduce adaptive masks that spatially gate feature injection using differences between source- and target-conditioned block outputs at matched inversion states. Second, we use REINFORCE to select Top-K injection blocks under different preservation-editability objectives. The selected blocks are fixed at inference and require no online search. On PIE-Bench with FLUX.1-dev, spatial masking controls the alignment-preservation trade-off. On 60 validation examples, a learned nine-block set gives lower whole-image LPIPS than the 18-block RF-Edit set within the same masked pipeline, with slightly lower alignment. Among 50 random nine-block sets, it has the lowest LPIPS but not the highest reward. Separate objective sweeps reveal different block preferences for preservation and alignment.

## Channel-wise Vector Quantization: Native 1D Visual Tokenization with Learnable Ordering

DevFeed: [Channel-wise Vector Quantization: Native 1D Visual Tokenization with Learnable Ordering](<https://devfeed.tech/articles/channel-wise-vector-quantization-native-1d-visual-tokenization-with-learnable-ordering-145338.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.26089>)

Author: Wei Song, Tianhang Wang, Yitong Chen, Tong Zhang, Zuxuan Wu, Min Li, Jiaqi Wang, Kaicheng Yu

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [quantization](<https://devfeed.tech/topics/quantization.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [channel](<https://devfeed.tech/tags/channel.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [generation](<https://devfeed.tech/tags/generation.md>), [image](<https://devfeed.tech/tags/image.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [ordering](<https://devfeed.tech/tags/ordering.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [sequence](<https://devfeed.tech/tags/sequence.md>), [tokenization](<https://devfeed.tech/tags/tokenization.md>)

### AI overview

Channel-wise Vector Quantization (CVQ) tokenizes images by quantizing feature-map channels instead of patch vectors, forming a 1D sequence with learnable coarse-to-fine ordering. Its Channel-wise Autoregressive (CAR) model predicts channels sequentially, first establishing global structure and then adding fine detail. The abstract reports CVQ maintains over 95% codebook utilization up to 2^16 entries, with reconstruction gains over conventional VQ growing as codebook size increases. CAR reports a DPG score of 86.7 and GenEval score of 0.79 for text-to-image generation.

### Source excerpt

arXiv:2605.26089v3 Announce Type: replace-cross Abstract: We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantization, which assigns a discrete token to each patch feature vector, CVQ quantizes each channel of the feature map. This represents an image as a 1D channel sequence with learnable coarse-to-fine ordering, rather than a 2D patch grid. Based on CVQ, we introduce a new visual autoregressive framework with "next-channel prediction". Instead of rendering images patch by patch in raster order, our Channel-wise Autoregressive (CAR) model predicts image channels sequentially, producing progressively enriched visual details. Specifically, it first sketches global structure and then refines fine-grained attributes, akin to a human artist's workflow. Empirically, we show that: (1) CVQ exhibits strong codebook scalability, maintaining 95%+ utilization with up to $2^{16}$ entries while delivering growing reconstruction gains over VQ as the codebook scales up; and (2) CAR attains a DPG score of 86.7 and a GenEval score of 0.79, demonstrating strong effectiveness for text-to-image generation.

## Training-Free Domain Generation for One-Shot Federated Learning with Server-Side Pre-trained Diffusion Models

DevFeed: [Training-Free Domain Generation for One-Shot Federated Learning with Server-Side Pre-trained Diffusion Models](<https://devfeed.tech/articles/training-free-domain-generation-for-one-shot-federated-learning-with-server-side-pre-trained-diffusion-models-142722.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23908>)

Author: Yixuan Tong, Yuanguo Bi, Mingjian Zhi, Wenchao Xu, Yuan Wu

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [adapter](<https://devfeed.tech/tags/adapter.md>), [class](<https://devfeed.tech/tags/class.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classification-accuracy](<https://devfeed.tech/tags/classification-accuracy.md>), [client](<https://devfeed.tech/tags/client.md>), [communication](<https://devfeed.tech/tags/communication.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [data](<https://devfeed.tech/tags/data.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [distributions](<https://devfeed.tech/tags/distributions.md>), [domain](<https://devfeed.tech/tags/domain.md>), [domains](<https://devfeed.tech/tags/domains.md>), [encoder](<https://devfeed.tech/tags/encoder.md>), [entropy](<https://devfeed.tech/tags/entropy.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [guidance](<https://devfeed.tech/tags/guidance.md>)

### AI overview

FedDoG addresses heterogeneous client data in one-shot federated learning by using a server-side pre-trained diffusion model to generate domain-aligned synthetic data. Clients send compact domain representations extracted with a frozen image encoder; a pre-trained image-conditioning adapter uses them as visual guidance. The method adjusts conditioning strength based on domain concentration and filters generated samples for class consistency and predictive entropy. On three benchmarks, the authors report higher-quality synthetic images and better classification accuracy than existing OSFL baselines, alongside 99.9% less client upload and 91.5% less client computation time. These are reported experimental results; the excerpt gives no benchmark names or further evaluation details.

### Source excerpt

arXiv:2611.23908v1 Announce Type: new Abstract: One-shot federated learning (OSFL) has attracted increasing attention for its ability to substantially reduce communication overhead by limiting client-server interaction to a single communication round. Nevertheless, this limited interaction makes learning from heterogeneous client distributions challenging. Diffusion-based OSFL approaches seek to address this challenge by synthesizing data that approximate client distributions. However, existing diffusion-based approaches often impose substantial computational costs on clients and lack effective visual guidance to generate data aligned with client distributions. To address these limitations, we propose FedDoG, a training-free Domain Generation framework that leverages server-side pre-trained diffusion models to synthesize data aligned with client domains. FedDoG extracts compact domain representations using a frozen image encoder, substantially reducing client-side computational and communication costs. These representations are incorporated into the diffusion model through a pre-trained image-conditioning adapter, thereby providing explicit visual guidance for domain generation. To further improve the quality of synthetic data, FedDoG adapts the strength of visual conditioning according to domain concentration and filters generated samples based on class consistency and predictive entropy. Experiments on three benchmarks demonstrate that FedDoG generates higher-quality synthetic images and outperforms existing OSFL baselines in classification accuracy. Meanwhile, FedDoG reduces client upload and computation time by 99.9% and 91.5%, respectively. The code is available at https://github.com/YXTong17/FedDoG.

## VerifyPrompt: Towards Text-to-Image Models Verification Behind Black-Box APIs

DevFeed: [VerifyPrompt: Towards Text-to-Image Models Verification Behind Black-Box APIs](<https://devfeed.tech/articles/verifyprompt-towards-text-to-image-models-verification-behind-black-box-apis-143098.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2410.22725>)

Author: Ji Guo, Rui Zhang, Guomin Lu, Aiguo Chen, Tianwei Zhang, Hongwei Li, Wenbo Jiang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [text-to-image](<https://devfeed.tech/topics/text-to-image.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [apis](<https://devfeed.tech/tags/apis.md>), [black-box](<https://devfeed.tech/tags/black-box.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [image](<https://devfeed.tech/tags/image.md>), [learning](<https://devfeed.tech/tags/learning.md>), [model](<https://devfeed.tech/tags/model.md>), [model-providers](<https://devfeed.tech/tags/model-providers.md>), [model-verification](<https://devfeed.tech/tags/model-verification.md>), [models](<https://devfeed.tech/tags/models.md>), [oracle](<https://devfeed.tech/tags/oracle.md>), [platforms](<https://devfeed.tech/tags/platforms.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [search](<https://devfeed.tech/tags/search.md>), [security](<https://devfeed.tech/tags/security.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>), [third-party](<https://devfeed.tech/tags/third-party.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

VerifyPrompt tests whether a black-box text-to-image service matches a claimed reference model, addressing possible model substitution by third-party platforms. It searches for a model-specific adversarial verify prompt designed to make the target generate a particular image while other models generate different ones. VerifyPrompt-RL uses reinforcement learning, multi-sample exploration, and group relative error estimation to stabilize and speed that black-box search. The abstract reports over 90% verification accuracy across various T2I platforms; it does not provide further experimental details here.

### Source excerpt

arXiv:2410.22725v5 Announce Type: replace-cross Abstract: With the rise of diverse Text-to-Image (T2I) models such as DALL-E 3, third-party platforms increasingly integrate multiple black-box APIs to deliver cost-effective services. This also raises a new and practical security question: are these third-party platforms truly offering the models they claim? Such model substitution fraud, in which a malicious third-party platform operator acts as the adversary, enables the platform to profit illicitly while undermining user interests and damaging the commercial reputation of legitimate model providers. To address this practical concern, we first define the task of T2I model verification, which determines whether a black-box target model matches a black-box oracle reference model. After that, we propose VerifyPrompt, which performs T2I model verification through a specially designed verify prompt. Intuitively, the verify prompt is an adversarial prompt for the target model, without transferability to other models. It makes the target model generate a specific image while making other models produce entirely different images. Our key idea for generating verify prompts is to enforce strong interactions between adversarial perturbations and the target model, thereby overfitting the target and producing model-specific perturbations. To enable efficient black-box search for verify prompts, we further introduce VerifyPrompt-RL, a reinforcement learning-based strategy that leverages multi-sample exploration and group relative error estimation to stabilize and accelerate the search process. Experiments show that VerifyPrompt achieves over 90\% accuracy across various T2I platforms, confirming its effectiveness in real-world third-party services.

## The Elephant in the Question: Unified Models Picture the Concepts Behind Their Answers

DevFeed: [The Elephant in the Question: Unified Models Picture the Concepts Behind Their Answers](<https://devfeed.tech/articles/the-elephant-in-the-question-unified-models-picture-the-concepts-behind-their-answers-143563.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24793>)

Author: Tobias Braun, Marcus Rohrbach, Lorenzo Cavallaro

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [model architecture](<https://devfeed.tech/topics/model-architecture.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Chain-of-thought](<https://devfeed.tech/topics/chain-of-thought.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [concepts](<https://devfeed.tech/tags/concepts.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generators](<https://devfeed.tech/tags/generators.md>), [hidden](<https://devfeed.tech/tags/hidden.md>), [hidden-states](<https://devfeed.tech/tags/hidden-states.md>), [image](<https://devfeed.tech/tags/image.md>), [images](<https://devfeed.tech/tags/images.md>), [inspect](<https://devfeed.tech/tags/inspect.md>), [intermediate](<https://devfeed.tech/tags/intermediate.md>), [intermediate-representations](<https://devfeed.tech/tags/intermediate-representations.md>), [lens](<https://devfeed.tech/tags/lens.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [picture](<https://devfeed.tech/tags/picture.md>), [question](<https://devfeed.tech/tags/question.md>), [unified-models](<https://devfeed.tech/tags/unified-models.md>)

### AI overview

V-lens visualizes a chosen token's hidden state in unified multimodal models by using their image generators, without training a decoder. Across four diffusion-based and two autoregressive models, the visualizations expose intermediate concepts linking questions to answers, including concepts never stated explicitly; controlled tests examine how they vary with context, token position, and depth. The paper also introduces lens tuning, which supervises selected hidden states with pictures through V-lens. For BAGEL, SenseNova-U1, and HunyuanImage-3.0, correct visualizations of pronoun referents rise from 2-11% to 86-94%. The abstract reports that this visual supervision also improves text answers without directly supervising answer tokens.

### Source excerpt

arXiv:2611.24793v1 Announce Type: cross Abstract: Visualizing intermediate representations could help us inspect the reasoning steps underlying a model output. Unified multimodal models offer this opportunity by combining understanding and generation in one architecture. Their image generators can access representations formed while processing text. We introduce the V-lens, which uses this connection to visualize a chosen token's hidden state without training a decoder. Across four diffusion-based and two purely autoregressive unified models, the resulting images reveal key intermediate concepts that connect a question to its answer even when the concepts are never named explicitly. Controlled tests show how this content changes with context, token position, and depth. We then introduce lens tuning, which supervises selected hidden states with pictures through the V-lens. Across BAGEL, SenseNova-U1, and HunyuanImage-3.0, the rate of correct visualizations of pronoun referents rises from 2-11% to 86-94%. Surprisingly, such visual supervision also improves text answers without supervising the answer tokens directly. Code is available at https://github.com/multimodal-ai-lab/V-lens.

## ReflectScene:MLLM-Guided Closed-Loop Diffusion for 3D Indoor Scene Generation

DevFeed: [ReflectScene:MLLM-Guided Closed-Loop Diffusion for 3D Indoor Scene Generation](<https://devfeed.tech/articles/reflectscene-mllm-guided-closed-loop-diffusion-for-3d-indoor-scene-generation-142710.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23845>)

Author: Jiawei Shen, Jie Feng, Junpeng Zhang, Guanbin Li, Wanyi Chen, Weisheng Dong, Guangming Shi

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Machine Perception](<https://devfeed.tech/topics/machine-perception.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [denoising](<https://devfeed.tech/tags/denoising.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [functional](<https://devfeed.tech/tags/functional.md>), [generation](<https://devfeed.tech/tags/generation.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [layout](<https://devfeed.tech/tags/layout.md>), [layouts](<https://devfeed.tech/tags/layouts.md>), [quality](<https://devfeed.tech/tags/quality.md>), [reward](<https://devfeed.tech/tags/reward.md>), [scene-generation](<https://devfeed.tech/tags/scene-generation.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantics](<https://devfeed.tech/tags/semantics.md>)

### AI overview

ReflectScene uses a closed-loop diffusion process to make object-level corrections to generated 3D indoor layouts while preserving non-target arrangements during denoising. A frozen multimodal large language model interprets structured layouts alongside multi-view visual evidence, and its assessments of candidate corrections are distilled into a lightweight reward predictor to reduce correction-decision computation. The selected corrections are applied through transient conditioning and persistent clean-estimate projection. On 3D-FRONT, the authors report improved functional consistency and semantic alignment with competitive generation quality and diversity.

### Source excerpt

arXiv:2611.23845v1 Announce Type: cross Abstract: Text-conditioned 3D indoor scene generation requires layouts satisfying geometric, functional, and semantic constraints. However, existing diffusion methods rely primarily on static textual conditions, limiting their ability to assess evolving scenes and translate semantic discrepancies into executable object-level corrections. MLLM-based post-hoc refinement provides semantic feedback but remains decoupled from denoising, potentially disrupting scene coherence.We propose ReflectScene, an MLLM-guided closed-loop diffusion framework. First, we introduce Hierarchical Prior-Grounded Scene Understanding that aligns structured layouts with multi-view visual evidence, to interpret object-specific context and scene global semantics via a frozen multi-modal large language model (MLLM). Second, we propose MLLM-Guided Semantic Reward Evaluation to distill MLLM's diagnoses and assessments on possible candidate corrections into a lightweight Reward Predictor, enabling correction decision making with reduced computation burden. Finally, Decision-Conditioned Trajectory-Consistent Diffusion is proposed to integrate selected corrections through transient conditioning and persistent clean-estimate projection, correcting object layout in the generated scene while preserving non-target arrangements throughout denoising.Experiments on 3D-FRONT demonstrate improved functional consistency and semantic alignment while maintaining competitive generation quality and diversity.

## Do Diffusion Models Learn to Generalize Basic Visual Skills?

DevFeed: [Do Diffusion Models Learn to Generalize Basic Visual Skills?](<https://devfeed.tech/articles/do-diffusion-models-learn-to-generalize-basic-visual-skills-141773.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22427>)

Author: Amish Sethi, Boya Zeng, Wenhao Chai, Zhuang Liu

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [color](<https://devfeed.tech/tags/color.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [design](<https://devfeed.tech/tags/design.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [extrapolation](<https://devfeed.tech/tags/extrapolation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generative](<https://devfeed.tech/tags/generative.md>), [position](<https://devfeed.tech/tags/position.md>), [rotation](<https://devfeed.tech/tags/rotation.md>), [rules](<https://devfeed.tech/tags/rules.md>), [skills](<https://devfeed.tech/tags/skills.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>), [training](<https://devfeed.tech/tags/training.md>), [training-data](<https://devfeed.tech/tags/training-data.md>)

### AI overview

The Visual Generative Lab (VGL) tests diffusion models' visual-skill generalization using rule-generated synthetic data and task-specific metrics. In the reported controlled experiments, extrapolation beyond training ranges was limited: size and position performance degraded within a few pixels, out-of-range count accuracy was about 50%, and rotation results varied widely across random seeds. For compositional generalization, the number of distinct combinations of basic skills mattered more than dataset size. Skills mostly failed independently, with position as an exception. These findings apply to the paper's experimental setup.

### Source excerpt

arXiv:2611.22427v1 Announce Type: cross Abstract: Diffusion models generate high-quality images, but how well they generalize is hard to measure. Current evaluations rely on human preference and prompt-following benchmarks for text-to-image models and on distribution-level metrics such as Fr\'echet Inception Distance (FID) and Inception Score (IS) for class-conditional models, but these cannot tell whether models learn basic visual skills or largely match training patterns. To address this gap, we introduce the Visual Generative Lab (VGL), a controlled experimental framework for studying how diffusion models learn and generalize basic visual skills, including size, position, rotation, count, color, shape, and their compositions. By generating synthetic training data for each skill from explicit rules, VGL allows precise measurement of generalization with task-specific, rule-based metrics. Training models from scratch on these data reveals three patterns in this controlled setting: (1) with our default design, extrapolation is limited: size and position degrade within a few pixels of the training range, count reaches only about 50% accuracy on out-of-range counts, and rotation extrapolation accuracy varies widely across seeds; (2) for compositional generalization, the number of distinct basic visual skill combinations matters more than dataset size; (3) skills mostly fail independently, except position. Code and data-generation scripts: https://github.com/AmishSethi/visual-generative-lab.

## Hierarchical Diffusion Transformer for End-to-End Image Generation

DevFeed: [Hierarchical Diffusion Transformer for End-to-End Image Generation](<https://devfeed.tech/articles/hierarchical-diffusion-transformer-for-end-to-end-image-generation-140096.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22962>)

Author: Xiaoyu Wu, Yifei Wang, Weihang Guo, Chen Wei, Lydia E Kavraki, Niloofar Mireshghallah, Steven Wu

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [diffusion-transformers](<https://devfeed.tech/topics/diffusion-transformers.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Image](<https://devfeed.tech/topics/image.md>), [ImageNet](<https://devfeed.tech/topics/imagenet.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [diffusion-transformers](<https://devfeed.tech/tags/diffusion-transformers.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [generation](<https://devfeed.tech/tags/generation.md>), [hierarchy](<https://devfeed.tech/tags/hierarchy.md>), [hit](<https://devfeed.tech/tags/hit.md>), [image](<https://devfeed.tech/tags/image.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [images](<https://devfeed.tech/tags/images.md>), [jit](<https://devfeed.tech/tags/jit.md>), [pixel](<https://devfeed.tech/tags/pixel.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [quality](<https://devfeed.tech/tags/quality.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>), [token](<https://devfeed.tech/tags/token.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [training](<https://devfeed.tech/tags/training.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

### AI overview

HiT improves pixel-space diffusion efficiency by progressively grouping related image tokens into compact group tokens for the Transformer bottleneck, then restoring features to their original positions. A compression budget lets group membership and counts vary by image and diffusion timestep. The model learns coherent object and part groupings without segmentation labels; for text-to-image, it also aligns caption words with corresponding image patches without region annotations. On ImageNet 256x256, HiT reports 1.48 FID and generation quality comparable to JiT at about 40% of its cumulative training FLOPs. Across five text-to-image benchmarks, it exceeds UniLiP's average score with roughly 6x fewer denoiser parameters and 3x fewer forward FLOPs. The abstract reports these results for end-to-end pixel-space generation without external visual pretraining.

### Source excerpt

arXiv:2611.22962v1 Announce Type: cross Abstract: Pixel-space diffusion learns visual representations and image generation jointly in a single end-to-end training stage, without a separately pretrained visual encoder. However, plain pixel-space Transformers still trail leading two-stage latent diffusion models in generation quality and training efficiency. We hypothesize that part of this gap arises from retaining one token per patch throughout the backbone, which does not explicitly encourage a visual hierarchy that summarizes related content at progressively coarser levels. To address this, we introduce Hierarchical Diffusion Transformers (HiT), which progressively group related tokens and represent each group with a single token. The main Transformer bottleneck processes these compact group tokens, and ungrouping restores features to their original image positions. A compression budget regulates the average compression ratio across the batch, allowing group memberships and counts to vary across images and diffusion timesteps during both training and generation. The model exhibits emergent semantic structure, learning to group coherent objects and object parts without segmentation labels. In text-to-image generation, HiT further learns to group caption words with image patches depicting the same concepts, without region annotations. HiT achieves 1.48 FID on ImageNet $256\times256$ and reaches comparable generation quality to JiT using approximately 40\% of its cumulative training FLOPs. For text-to-image generation, HiT exceeds UniLiP's average score across five benchmarks with roughly $6\times$ fewer denoiser parameters and $3\times$ fewer forward FLOPs. These results suggest that learning a visual hierarchy within the generator breaks down the barrier to stronger image generation without external visual pretraining.

## Pathology Randomization for Synthetic Priors and Zero-Shot Detection

DevFeed: [Pathology Randomization for Synthetic Priors and Zero-Shot Detection](<https://devfeed.tech/articles/pathology-randomization-for-synthetic-priors-and-zero-shot-detection-139940.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21975>)

Author: Alexandra G. Roberts, Tonmoy Hossain, Mark Olchanyi, Stefan Brandst\\"atter, Jonathan Williams Ramirez, Ana Lawry Aguila, Matthew Rosen, Annabel Sorby-Adams, W. Taylor Kimberly, Juan Eugenio Iglesias

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Medical imaging](<https://devfeed.tech/topics/medical-imaging.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [acquisition](<https://devfeed.tech/tags/acquisition.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [array](<https://devfeed.tech/tags/array.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [brain](<https://devfeed.tech/tags/brain.md>), [but](<https://devfeed.tech/tags/but.md>), [code](<https://devfeed.tech/tags/code.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [detection](<https://devfeed.tech/tags/detection.md>), [disease](<https://devfeed.tech/tags/disease.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [eess-iv](<https://devfeed.tech/tags/eess-iv.md>), [features](<https://devfeed.tech/tags/features.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [zero-shot](<https://devfeed.tech/tags/zero-shot.md>)

### AI overview

PathoDraw inserts anatomy-conditioned synthetic lesions into brain MRI label maps before contrast-agnostic rendering. A single contrast-agnostic 3D UNet estimates healthy anatomy and signed intensity deviations, enabling zero-shot pathology detection through tissue statistics and learned features without training on real pathology. The abstract reports evaluation on public stroke, tumor, and white matter hyperintensity datasets and archived clinical scans across T₁-weighted, FLAIR, and T₂-weighted images at varied resolutions. Under a recent unsupervised anomaly-detection benchmark, the model reportedly exceeds or performs comparably to contrast-specific detectors trained on real scans while preserving healthy anatomy. The same generator also supports training for super-resolution and registration in the presence of pathology.

### Source excerpt

arXiv:2611.21975v1 Announce Type: cross Abstract: Hospital brain imaging archives hold a diverse array of pathology at sample sizes beyond prospective studies, particularly for underrepresented populations and diseases. To unlock uncurated clinical data and scale analysis, methods are needed to detect abnormalities across contrasts and resolutions. Synthetic data has provided robust, contrast-agnostic models for a variety of human neuroimaging tasks in healthy anatomy, but pathology detection and other tasks in clinical settings still require real patient data, contrast-specific models, or disease-specific generators. We propose PathoDraw, a generative model of brain MRI with pathology. A conditional distribution of lesions given the healthy anatomy is drawn into the label map before contrast-agnostic rendering, and a single network estimates healthy anatomy with exact signed intensity deviation of any input scan. The contrast-agnostic 3D UNet learns the healthy labels under the lesion and the signed deviation directly and identifies pathology via robust tissue statistics and learned features, despite no training on real pathology. We show zero-shot detection on public stroke, tumor, and white matter hyperintensity datasets as well as archived clinical data, spanning $T_1$w, FLAIR and $T_2$w at various resolutions under a recent unsupervised anomaly detection benchmark protocol. Our single model exceeds or performs comparably to contrast-specific anomaly detectors trained on real scans and keeps healthy anatomy intact. The same generator trains networks for super-resolution and for registration in the presence of pathology. Our model, robust across acquisition and disease, enables the use of uncurated, archived data for clinical analysis. Our code is available at https://github.com/agr78/Pathology-Randomizer.

## An Optimization Framework for Denoising Generation

DevFeed: [An Optimization Framework for Denoising Generation](<https://devfeed.tech/articles/an-optimization-framework-for-denoising-generation-141746.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22202>)

Author: Xinyu Zhou, Jiawei Zhang, Stephen J. Wright

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>)

Tags: [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [denoising](<https://devfeed.tech/tags/denoising.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [generation](<https://devfeed.tech/tags/generation.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [noise](<https://devfeed.tech/tags/noise.md>), [objectives](<https://devfeed.tech/tags/objectives.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [robustness](<https://devfeed.tech/tags/robustness.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

The paper frames noise-unconditioned denoising generation as gradient ascent on a fixed log-density landscape and analyzes whether that process reaches meaningful data while preserving diversity. For empirical and population multi-scale Gaussian-mixture objectives, it proves almost-sure convergence near a reference manifold under stated posterior and landscape conditions, and uses a source-sink identity to establish regional coverage at finite resolution. An affine construction identifies a positive-bandwidth regime in which empirical-score optimization can avoid memorizing training samples while retaining diversity at training resolution. The abstract also reports that penalty-guided control uses the same fixed objective, and that experiments support the proposed mechanisms, including greater robustness to large-step guidance and downstream gains consistent with finite-data generalization.

### Source excerpt

arXiv:2611.22202v1 Announce Type: new Abstract: Noise-unconditioned denoising learns a single score, so generation can be viewed as gradient ascent on a fixed log-density landscape. This optimization interpretation leaves two questions: do trajectories approach meaningful data, and do different initializations retain diverse outcomes? We establish both phenomena for empirical and population multi-scale Gaussian-mixture objectives. Under explicit posterior and landscape conditions, ascent converges almost surely within $O(m\sigma_{\min}^2/\tau)$ of an $m$-dimensional reference manifold with reach at least $\tau$. We derive a source--sink identity for the same fixed field and use it to prove finite-resolution regional coverage. In an affine construction, we further identify a positive-bandwidth regime where even empirical-score optimization can avoid training-sample memorization while preserving diversity at the training resolution. The same fixed objective naturally supports penalty-guided controllable generation. Experiments support our predicted mechanisms, show improved robustness under large-step guidance, and demonstrate downstream gains consistent with finite-data generative generalization.

## Distortion-Free Semantic Watermarks for Black-Box Generative Models

DevFeed: [Distortion-Free Semantic Watermarks for Black-Box Generative Models](<https://devfeed.tech/articles/distortion-free-semantic-watermarks-for-black-box-generative-models-141505.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23208>)

Author: Aviv Yossef, Or Patashnik, Or Zamir

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [watermarking](<https://devfeed.tech/topics/watermarking.md>)

Tags: [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [black-box](<https://devfeed.tech/tags/black-box.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [detection](<https://devfeed.tech/tags/detection.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [encoder](<https://devfeed.tech/tags/encoder.md>), [generative](<https://devfeed.tech/tags/generative.md>), [image](<https://devfeed.tech/tags/image.md>), [images](<https://devfeed.tech/tags/images.md>), [model](<https://devfeed.tech/tags/model.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [robust](<https://devfeed.tech/tags/robust.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [watermark](<https://devfeed.tech/tags/watermark.md>), [watermarking](<https://devfeed.tech/tags/watermarking.md>)

### AI overview

The proposed watermark is distortion-free in the formal sense that averaging over its secret detection key leaves the generator's output distribution unchanged. It uses only black-box sampling from the generator and black-box queries to a semantic embedding, avoiding prior approaches' reliance on autoregressive-generation or diffusion-specific access. For images, the embedding must stay stable under content-preserving transformations while distinguishing independent generations from the same prompt. The authors train an encoder for this tradeoff and report better separation than off-the-shelf alternatives, with strong aggregate detection that remains robust to various transformations. They demonstrate the scheme on open-source and closed models; the supplied abstract does not specify quantitative results or which transformations were tested.

### Source excerpt

arXiv:2611.23208v1 Announce Type: cross Abstract: We present a provably distortion-free semantic watermarking algorithm that requires only black-box sampling access to a generative model and black-box access to a semantic embedding. A watermark is called distortion-free if, averaged over its secret detection key, it leaves the generator's output distribution unchanged; this provides a formal guarantee that watermarking does not reduce output quality. Conventional such watermarks are often brittle to transformations. This is especially problematic for images, where benign operations such as compression, cropping, or resizing change the entire pixel representation. Semantic watermarks therefore require detection to be robust to content-preserving transformations. Previous methods combining these properties rely heavily on specific white-box properties of the underlying model: either to autoregressive text generation or to diffusion-specific access, such as control of the initial noise or diffusion inversion. In contrast, our construction is fully generic: It only interacts with the generative model and the semantic embedding, a function that determines the notion of "preserving content" under which detection should be robust, via sample and query access. We then instantiate this framework for image generation. We characterize the two competing properties required of the semantic embedding: it should remain stable under transformations that preserve an image's content, but should distinguish independent generations from the same prompt. We train an image encoder directly for this tradeoff. The resulting encoder improves separation while maintaining stability over off-the-shelf alternatives and enables strong aggregate detection while remaining robust to various transformations. We demonstrate the effectiveness of our watermark scheme on both open-source and closed models, which is possible only due to restriction to black-box access.

## Sample-Aligned Decoders for Latent Generative Models

DevFeed: [Sample-Aligned Decoders for Latent Generative Models](<https://devfeed.tech/articles/sample-aligned-decoders-for-latent-generative-models-141779.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22458>)

Author: Yu Lei, Yi Li, Hongcheng Gao, Yipeng Wei, Liang Li, Li Su, Qingming Huang

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [ImageNet](<https://devfeed.tech/topics/imagenet.md>)

Tags: [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [generative-models](<https://devfeed.tech/tags/generative-models.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>)

### AI overview

Generated latents follow a different distribution from encoder latents despite lying similarly close to the encoder latent manifold, so decoder robustness to perturbed real latents may not address generator errors. Sample-Aligned Decoders (SAD) post-trains only the decoder of a frozen generator, adding no inference cost. It aligns decoded generated latents with unpaired real images in a frozen foundation-model feature space and uses Encoder Anchor Preservation to limit drift on encoder latents. The reported alignment acts on generated latents and can work against the anchor on encoder latents. SAD improves four ImageNet generators across three tokenizers; for REPA-E, FID-50K falls from 1.15 to 0.98. The abstract also reports compatibility with discriminator guidance and extension to text-to-image generation.

### Source excerpt

arXiv:2611.22458v1 Announce Type: cross Abstract: Latent generative models synthesize images by decoding generated latents, yet their decoder is trained only to reconstruct encoder latents and never sees the latents it decodes at test time, so the residual errors of the generator are rendered directly into the final image. Existing remedies retrain the generator, add cost at every sampling step, or make the decoder robust to perturbed real latents, assuming that generator errors resemble such perturbations. We find that they do not. Generated latents lie on the encoder latent manifold as closely as real ones, yet follow a different distribution. The decoder should therefore be adapted to the distribution of generated latents, which raises two challenges: (1) unpaired supervision, since a generated latent has no ground-truth image, and (2) latent-space drift, since a decoder freed from paired targets forgets the latent space it must decode. We propose Sample-Aligned Decoders (SAD), a post-training framework that fine-tunes only the decoder of a frozen generator at no inference cost. Generated-Sample Distribution Alignment matches decoded generated latents to unpaired real images in a frozen foundation-model feature space, and Encoder Anchor Preservation keeps the decoder close to the original one on encoder latents. Our analysis shows that the alignment is effective only on generated latents, where it corrects each sample in proportion to how much more often the generator produces such latents than the encoder; on encoder latents it can only work against the anchor. SAD improves four state-of-the-art ImageNet generators across three tokenizers, e.g., FID-50K from 1.15 to 0.98 for REPA-E, complements discriminator guidance, and extends to text-to-image generation. Our code and models are available at https://torpedo2003.github.io/SAD/.

## Sivia: Learning to Draw, Learning to Learn

DevFeed: [Sivia: Learning to Draw, Learning to Learn](<https://devfeed.tech/articles/sivia-learning-to-draw-learning-to-learn-137285.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.33386>)

Author: Feng Yuan, Xinyi Gao, Zijun Sun, Haoyue Li, Menglei Hua, Xiao Li, Yifan Gao

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [code](<https://devfeed.tech/tags/code.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [errors](<https://devfeed.tech/tags/errors.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [figure](<https://devfeed.tech/tags/figure.md>), [graphics](<https://devfeed.tech/tags/graphics.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [presentation](<https://devfeed.tech/tags/presentation.md>), [quality](<https://devfeed.tech/tags/quality.md>), [readability](<https://devfeed.tech/tags/readability.md>), [recursive-self-improvement](<https://devfeed.tech/tags/recursive-self-improvement.md>), [rra](<https://devfeed.tech/tags/rra.md>)

### AI overview

Sivia creates paper overview figures by extracting and planning scientific relations, adapting visual organization from recent top-conference papers, and composing designs for image generation. It improves through human-guided recursive self-improvement at two levels: revising its drawing skill from accuracy and presentation feedback, and revising the updater that proposes those changes. Personal presentation profiles adapt aesthetics while keeping scientific content fixed. In a study of 48 test papers, the two-level learning approach achieved 93.54% required-relation accuracy, outperforming the initial skill, Fixed-updater, and GEPA baselines by 15.31, 9.38, and 8.33 points, respectively; readability and visual-quality ratings also rose to 4.70 and 4.78 out of five. Learned profiles increased liking from 4.02 to 4.73 and adoption from 34 to 45 of 48 tasks. A diagnostic study found omissions were the most common errors and source-derived relation plans improved accuracy by up to 19.85 points.

### Source excerpt

arXiv:2609.33386v2 Announce Type: cross Abstract: A paper's overview figure is often the first thing readers see: it must explain the method correctly and look polished. We present Sivia, an overview-figure system that reads the paper, plans its relations, adapts visual organization from recent top-conference papers, and composes a design for image generation. Sivia improves with use through human-guided recursive self-improvement (RSI) at two levels: learning to draw revises its drawing skill from feedback on accuracy and presentation, and learning to learn revises the updater that proposes those revisions. A personal profile adapts presentation to its user's aesthetic preferences while the scientific content stays fixed. A diagnostic study of 1,964 overviews for 445 papers (17,973 relation judgments) shows that most errors are omissions and that source-derived relation plans raise required-relation accuracy (RRA) by up to 19.85 points. On 48 test papers, learning both levels reaches 93.54\% RRA, 15.31, 9.38, and 8.33 points above the initial skill, the Fixed-updater, and the GEPA baselines, while readability and visual quality rise from 3.95 and 4.00 to 4.70 and 4.78 on five-point scales. Learned presentation profiles raise liking from 4.02 to 4.73 and adoption from 34 to 45 of 48 tasks. Code and released artifacts are available at https://github.com/exsinger-hub/Sivia

## Beyond Semantic Prompts: Unified Watermarking and Access Control for Text-to-Image Diffusion Models

DevFeed: [Beyond Semantic Prompts: Unified Watermarking and Access Control for Text-to-Image Diffusion Models](<https://devfeed.tech/articles/beyond-semantic-prompts-unified-watermarking-and-access-control-for-text-to-image-diffusion-models-139302.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20470>)

Author: Fangming Shi, Li Li, Guorui Feng, Xinpeng Zhang

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [text-to-image](<https://devfeed.tech/topics/text-to-image.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [watermarking](<https://devfeed.tech/topics/watermarking.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [autoencoder](<https://devfeed.tech/tags/autoencoder.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [customizable](<https://devfeed.tech/tags/customizable.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [generation](<https://devfeed.tech/tags/generation.md>), [image-processing](<https://devfeed.tech/tags/image-processing.md>), [images](<https://devfeed.tech/tags/images.md>), [models](<https://devfeed.tech/tags/models.md>), [prompt-structure](<https://devfeed.tech/tags/prompt-structure.md>), [prompts](<https://devfeed.tech/tags/prompts.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [quality](<https://devfeed.tech/tags/quality.md>), [recognition](<https://devfeed.tech/tags/recognition.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [robustness](<https://devfeed.tech/tags/robustness.md>), [services](<https://devfeed.tech/tags/services.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>), [watermarking](<https://devfeed.tech/tags/watermarking.md>)

### AI overview

The proposed framework combines multi-bit watermarking and tiered access control in a single text prompt. It encodes watermark messages as designated words with dedicated learnable tokens, then jointly adapts the diffusion U-Net and token embeddings using a frozen reference model and pretrained watermark codec. A prompt-structure recognition network controls the VAE decoder to produce clear watermarked images, blurred previews, or black outputs according to access state. The abstract reports reliable watermark recovery, robustness to tested image-processing operations and model modifications, and preserved decoding fidelity and watermark recovery under full access. It does not provide quantitative results in the supplied excerpt.

### Source excerpt

arXiv:2611.20470v1 Announce Type: new Abstract: Text-to-image diffusion services require both traceability of generated content and differentiated access to generation capabilities. However, existing watermarking methods commonly expose watermark control through mechanisms beyond the text-prompt interface, while credential-based access control does not inherently enforce distinct output quality levels. We propose a unified framework that enables customizable multi-bit watermark embedding and tiered access control through a single text prompt. A unified prompt represents watermark messages using designated words and associates protocol structures with different access states. The framework adopts a two-stage training strategy. First, watermark payload partitioning represents messages as designated watermark words, while vocabulary extension assigns each protocol word a dedicated token with a learnable input embedding. Guided by a frozen reference model and a pretrained watermark codec, joint adaptation of the U-Net and protocol-token embeddings transfers message-dependent watermark patterns into the generation process. Second, a prompt-structure recognition network controls feature modulation within the variational autoencoder decoder, which is trained to produce clear watermarked images, blurred previews, or black outputs according to the access state. Experiments demonstrate reliable watermark recovery, robustness to common image-processing operations and evaluated model modifications, and consistent performance across diverse generation settings. The controlled decoder also achieves distinct output behaviors under restricted access while closely preserving reference decoding fidelity and watermark recoverability under full access. Our open-source code and model weights will be public after acceptance.

## Beyond Alignment: Supervising the Generator for EEG-to-Image Reconstruction

DevFeed: [Beyond Alignment: Supervising the Generator for EEG-to-Image Reconstruction](<https://devfeed.tech/articles/beyond-alignment-supervising-the-generator-for-eeg-to-image-reconstruction-137421.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.19232>)

Author: Sangmin Jo, Wootaek Jeong, Heung-Il Suk

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [diffusion-transformers](<https://devfeed.tech/topics/diffusion-transformers.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>)

Tags: [alignment](<https://devfeed.tech/tags/alignment.md>), [brain](<https://devfeed.tech/tags/brain.md>), [condition](<https://devfeed.tech/tags/condition.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [denoising](<https://devfeed.tech/tags/denoising.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-transformers](<https://devfeed.tech/tags/diffusion-transformers.md>), [eeg](<https://devfeed.tech/tags/eeg.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [features](<https://devfeed.tech/tags/features.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generator](<https://devfeed.tech/tags/generator.md>), [generators](<https://devfeed.tech/tags/generators.md>), [image](<https://devfeed.tech/tags/image.md>), [images](<https://devfeed.tech/tags/images.md>), [inference](<https://devfeed.tech/tags/inference.md>), [neural](<https://devfeed.tech/tags/neural.md>), [process](<https://devfeed.tech/tags/process.md>), [quality](<https://devfeed.tech/tags/quality.md>)

### AI overview

Stronger EEG-to-vision alignment alone did not yield comparable gains in image reconstruction, and EEG-conditioned generators struggled to follow the fixed targets used by Representation Alignment (REPA). The paper introduces generation-derived supervision (GDS): an image-conditioned teacher maps static image-encoder features into a diffusion transformer's internal representation space, and an EEG-conditioned student tracks those dynamic targets during denoising. The teacher is discarded at inference. On THINGS-EEG and THINGS-MEG, the method reportedly outperforms conditioning-centric baselines in reconstruction fidelity. The supplied text is an abstract, so it does not provide implementation details or quantitative results.

### Source excerpt

arXiv:2611.19232v1 Announce Type: cross Abstract: Visual brain decoding translates neural activity into human-interpretable images. While recent EEG-to-image reconstruction methods rely on aligning EEG signals with pretrained visual embeddings to condition an image generator, we empirically demonstrate that stronger cross-modal alignment do not translate into comparable gains in reconstruction quality. This indicates that improving the input condition alone is insufficient; the generative process itself requires explicit supervision. Although Representation Alignment (REPA) offers a solution by guiding diffusion transformers with pretrained vision encoder features, we find that EEG-conditioned generators struggle to follow these fixed targets. To address this mismatch, we introduce generation-derived supervision (GDS): an image-conditioned teacher that translates static image-encoder features into the internal representation space of a diffusion transformer. Our EEG-conditioned student generator closely tracks these dynamic targets during denoising, discarding the teacher at inference. Evaluated on THINGS-EEG and THINGS-MEG, our approach consistently outperforms conditioning-centric baselines, achieving state-of-the-art reconstruction fidelity.

## High-quality cost-effective AI image generation on Amazon ECS

DevFeed: [High-quality cost-effective AI image generation on Amazon ECS](<https://devfeed.tech/articles/high-quality-cost-effective-ai-image-generation-on-amazon-ecs-136885.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/containers/high-quality-cost-effective-ai-image-generation-on-amazon-ecs/>)

Author: Nick Biso

Published: 2026-11-17T00:19:06Z

Content type: article

Language: en

Sources: [Containers](<https://devfeed.tech/sources/containers.md>)

Topics: [diffusion-transformers](<https://devfeed.tech/topics/diffusion-transformers.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [AWS Inferentia](<https://devfeed.tech/topics/aws-inferentia.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Amazon EC2](<https://devfeed.tech/topics/amazon-ec2.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [ai-image-generation](<https://devfeed.tech/tags/ai-image-generation.md>), [amazon-ec2](<https://devfeed.tech/tags/amazon-ec2.md>), [amazon-elastic-container-service](<https://devfeed.tech/tags/amazon-elastic-container-service.md>), [auto-scaling](<https://devfeed.tech/tags/auto-scaling.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [cost](<https://devfeed.tech/tags/cost.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [ecs](<https://devfeed.tech/tags/ecs.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

The described Amazon ECS service runs Z-Image-Turbo on AWS Inferentia2, with one service per image resolution and one request at a time per instance because inference saturates the accelerator. Its key deployment mechanism is compiling model artifacts once in CI/CD, caching them on Amazon EFS, and loading them into containers at startup; the post reports this cuts startup to about two minutes from over 30 minutes and avoids recompilation when changes do not affect the model graph. The excerpt estimates $0.003 per 512px image and $0.011 per 1024px image at $1.97/hour for an inf2.8xlarge in us-east-1, while noting costs vary with utilization and other AWS resources still incur charges. It also describes resolution-based routing and streaming intermediate image frames over WebSockets. Deployment requires AWS quotas for Inf2 instances, CDK bootstrap, and listed local tools; first deployment takes about 45 minutes, including compilation.

### Source excerpt

Learn how to run Z-Image-Turbo, a 6-billion-parameter diffusion transformer, on AWS Inferentia2 and Amazon ECS to generate high-quality images at a fraction of a cent each, with auto-scaling, arbitrary resolution support, and a complete CI/CD pipeline.

## MAI-Image-2.7 and MAI-Image-2.7-Flash now available on AI Gateway

DevFeed: [MAI-Image-2.7 and MAI-Image-2.7-Flash now available on AI Gateway](<https://devfeed.tech/articles/mai-image-2-7-and-mai-image-2-7-flash-now-available-on-ai-gateway-138551.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/mai-image-2-7-and-mai-image-2-7-flash-now-available-on-ai-gateway>)

Author: Zachary Chen

Published: 2026-11-17T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [assets](<https://devfeed.tech/tags/assets.md>), [cli](<https://devfeed.tech/tags/cli.md>), [edits](<https://devfeed.tech/tags/edits.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [images](<https://devfeed.tech/tags/images.md>), [layouts](<https://devfeed.tech/tags/layouts.md>), [mai-image-2-7](<https://devfeed.tech/tags/mai-image-2-7.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [microsoft-account](<https://devfeed.tech/tags/microsoft-account.md>), [pixels](<https://devfeed.tech/tags/pixels.md>), [playground](<https://devfeed.tech/tags/playground.md>), [preview](<https://devfeed.tech/tags/preview.md>), [prompts](<https://devfeed.tech/tags/prompts.md>), [reference](<https://devfeed.tech/tags/reference.md>), [rendering](<https://devfeed.tech/tags/rendering.md>), [terminal](<https://devfeed.tech/tags/terminal.md>), [transparent](<https://devfeed.tech/tags/transparent.md>)

### AI overview

Microsoft's MAI-Image-2.7 and MAI-Image-2.7-Flash are in public preview on AI Gateway. Both generate or edit images up to 2048 x 2048 pixels, support transparent backgrounds, photorealism and text rendering, and accept up to five reference images. MAI-Image-2.7 is positioned for final assets when image quality is the priority; Flash is faster and lower cost for prompt exploration or variations. Use either with an AI Gateway API key, AI SDK 6 or later, and its model ID; no Microsoft account is required. For transparent PNG output, set `providerOptions.azure.background` to `'transparent'`. The source also shows image editing with a reference image and describes equivalent terminal use through the AI CLI.

### Source excerpt

Microsoft's MAI-Image-2.7 and MAI-Image-2.7-Flash are now available in public preview on AI Gateway. Both increase the maximum output size to 2048 x 2048 pixels and add transparent backgrounds for generated and edited images. Generate images from text or edit existing images with one AI Gateway API key, without a Microsoft account. Both models support photorealistic images, text rendering, and targeted edits to products, portraits, and layouts. Use up to five reference images to guide edits or combine subjects. MAI-Image-2.7 (microsoft/mai-image-2.7): for final assets where image quality is the priority MAI-Image-2.7-Flash (microsoft/mai-image-2.7-flash): for faster, lower-cost generation when exploring prompts or creating variations Set the AI_GATEWAY_API_KEY environment variable, then use either model ID with AI SDK 6 or later. To generate a transparent PNG, set providerOptions.azure.background to 'transparent': To edit an image, provide it as a reference and describe what to change: You can also generate and edit images from the terminal with the AI CLI, using the same API key and model IDs: Try MAI-Image-2.7 or MAI-Image-2.7-Flash in the model playground, or follow the image generation guide. Read more

## Learning Anisotropic Prediction Targets for Flow Models

DevFeed: [Learning Anisotropic Prediction Targets for Flow Models](<https://devfeed.tech/articles/learning-anisotropic-prediction-targets-for-flow-models-135825.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17767>)

Author: Rayhan Zirvi, Hansheng Chen, Gordon Wetzstein, Leonidas Guibas

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [ImageNet](<https://devfeed.tech/topics/imagenet.md>)

Tags: [alignment](<https://devfeed.tech/tags/alignment.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [better](<https://devfeed.tech/tags/better.md>), [changes](<https://devfeed.tech/tags/changes.md>), [choice](<https://devfeed.tech/tags/choice.md>), [component](<https://devfeed.tech/tags/component.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [easier](<https://devfeed.tech/tags/easier.md>), [error](<https://devfeed.tech/tags/error.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [flow](<https://devfeed.tech/tags/flow.md>), [flow-matching](<https://devfeed.tech/tags/flow-matching.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-models](<https://devfeed.tech/tags/generative-models.md>), [learning](<https://devfeed.tech/tags/learning.md>), [models](<https://devfeed.tech/tags/models.md>), [prediction](<https://devfeed.tech/tags/prediction.md>)

### AI overview

AnisoFlow learns the flow model's prediction target by assigning nonnegative noise weights to directions in a jointly learned basis. A closed-form map exactly recovers velocity, so the architecture, flow-matching loss, and sampler remain unchanged while training chooses a target that is easier to predict. The analysis predicts that preferred directional weights scale near-linearly with data variance, consistent with learned pixel-space weights. On ImageNet 256x256, the method improves FID from 1.90 to 1.55 over the JiT baseline without representation alignment or architectural changes. For pixel-space text-to-image generation, the abstract reports improved image quality and fewer patch-seam artifacts under reduced-precision inference, attributed to better-conditioned velocity recovery.

### Source excerpt

arXiv:2611.17767v1 Announce Type: cross Abstract: Flow-based generative models are trained on a hand-chosen prediction target, such as the velocity, the noise, or the clean data. This choice strongly affects training and sample quality. We introduce Anisotropic Flow Models (AnisoFlow), which replaces a fixed prediction target with a fully learnable one. AnisoFlow learns to scale the noise component of the target anisotropically, assigning a separate nonnegative weight to each direction in a jointly learned basis. A closed-form map recovers the velocity from the network's prediction, leaving the architecture, flow-matching loss, and sampler unchanged. Since recovery is exact, training optimizes the target purely to make it easier for the network to predict. We theoretically analyze the resulting prediction error and predict that the preferred noise weight in each direction scales near-linearly with data variance, in agreement with the weights learned empirically in pixel space. AnisoFlow improves FID from 1.90 to 1.55 over the JiT baseline on ImageNet 256$\times$256, by learning only the prediction target, without representation alignment or architectural changes. In pixel-space text-to-image generation, AnisoFlow improves image quality and, through better-conditioned velocity recovery, largely removes patch-seam artifacts under reduced-precision inference.

## Rethinking Visual Reasoning in Text-to-Image Reward Modeling

DevFeed: [Rethinking Visual Reasoning in Text-to-Image Reward Modeling](<https://devfeed.tech/articles/rethinking-visual-reasoning-in-text-to-image-reward-modeling-135083.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17585>)

Author: Shiye Su, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [text-to-image](<https://devfeed.tech/topics/text-to-image.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [human feedback](<https://devfeed.tech/topics/human-feedback.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [vlm](<https://devfeed.tech/topics/vlm.md>)

Tags: [continual-learning](<https://devfeed.tech/tags/continual-learning.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [generation](<https://devfeed.tech/tags/generation.md>), [image](<https://devfeed.tech/tags/image.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [images](<https://devfeed.tech/tags/images.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [inference](<https://devfeed.tech/tags/inference.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [pairing](<https://devfeed.tech/tags/pairing.md>), [pairs](<https://devfeed.tech/tags/pairs.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [reward](<https://devfeed.tech/tags/reward.md>), [text](<https://devfeed.tech/tags/text.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>)

### AI overview

Reward models used for text-to-image selection and post-training can lose visual reasoning ability during preference fine-tuning, while continual-learning baselines do not resolve the reported tradeoff with preference accuracy. The paper pairs existing visual reasoning examples by keeping the image fixed and varying the prompt, then mixes these pairs with conventional human preferences, which pair images under a shared prompt. The authors report improved visual understanding and preference prediction, plus average GenEval gains of 4.0% in best-of-n selection and 5.5% in RL post-training. Their model also outperforms HPSv3, despite HPSv3 having been trained on six times more preference pairs.

### Source excerpt

arXiv:2611.17585v1 Announce Type: cross Abstract: Reward models are a core component of modern text-to-image systems, serving as the objective for inference-time selection and RL-based post-training. A key prerequisite is visual understanding: to judge prompt adherence and ground aesthetic preferences, a reward model must bind attributes, resolve relations, and count reliably. We find that widely-used reward models perform poorly on targeted visual reasoning evaluations. Even when starting from strong vision-language backbones, preference fine-tuning erodes these capabilities, and continual-learning baselines fail to mitigate a steep tradeoff between visual reasoning and preference accuracy. We propose a data-centric intervention that injects visual reasoning supervision into preference learning by flipping the pairing axis. To complement conventional human preference data (paired images under a shared prompt), we convert existing visual reasoning datasets into preference pairs that share the same image but differ in prompt, and train on the mixture. This yields a Pareto improvement in both visual understanding and preference prediction. Across inference-time best-of-n selection and RL post-training, the resulting reward model improves text-to-image generation on challenging compositional prompts (GenEval) by an average of 4.0% and 5.5% respectively, outperforming HPSv3 which was trained on 6x more preference pairs.

## When Chekhov's Gun Fires Anyway: Over-Realization in Text-to-Image Models

DevFeed: [When Chekhov's Gun Fires Anyway: Over-Realization in Text-to-Image Models](<https://devfeed.tech/articles/when-chekhov-s-gun-fires-anyway-over-realization-in-text-to-image-models-132264.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16630>)

Author: Jiahao Huang, Kon Woo Kim, Song-Duo Ma, Yuka Kitamura, Felix Wagner, Yunshan Huang, Sunisth Kumar, Xanh Ho, Yun-Ang Wu, Zhijie Chen, Yunjia Xu, Junfeng Jiang, Zefan Yu, Fei Cheng, Akiko Aizawa

Published: 2026-11-13T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [text-to-image](<https://devfeed.tech/topics/text-to-image.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>)

Tags: [attention](<https://devfeed.tech/tags/attention.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>)

### AI overview

Text-to-image models often depict a mentioned target even when the prompt negates it, places it in a character's imagination or a figurative comparison, or hides it from view. The paper calls this over-realization and introduces OverReal: 698 prompts to measure rates across these four situations, plus 2,841 human-labeled images to verify its automatic judge. Across eight systems, all over-realize; conventional metrics such as CLIPScore reward the failure, and prompt expansion only partly reduces it. The authors report that diffusion backbones attend nearly as much to merely mentioned targets as to requested ones, while cues meant to suppress those targets receive less attention than ordinary words.

### Source excerpt

arXiv:2611.16630v1 Announce Type: cross Abstract: In text-to-image generation, a target that the prompt mentions often appears in the generated image in a way the prompt does not call for. We call this failure over-realization. Mental-spaces theory points to the situations where it can happen: under a negation, inside what a character believes or imagines, as the vehicle of a figurative comparison, or behind a viewpoint that hides the target. Prior work has studied only negation in depth, and the conventional alignment and preference metrics do not penalize the failure. We build OverReal to measure it: OverReal-Gen, 698 prompts covering the four situations, on which we measure each generator's over-realization rate; and OverReal-Det, 2,841 generated images human-labeled for whether and how the target is over-realized, on which we verify the automatic judge that produces this rate. Our evaluation of eight text-to-image systems reveals that all of them over-realize, and that conventional metrics such as CLIPScore reward the failure rather than penalize it. Prompt expansion only partly mitigates the failure. Inside the generator, the diffusion backbone attends to a mentioned target almost as much as to a requested one. The cue words that should hold the target back receive less attention than ordinary words.

## Rethinking Floorplan Generation with Space Syntax: From Design Theory to Model Improvement

DevFeed: [Rethinking Floorplan Generation with Space Syntax: From Design Theory to Model Improvement](<https://devfeed.tech/articles/rethinking-floorplan-generation-with-space-syntax-from-design-theory-to-model-improvement-132760.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.22507>)

Author: Zhuoyang Jiang, Dongqing Zhang, Qingxiang Liu, Yuxuan Liang

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [ai](<https://devfeed.tech/tags/ai.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [applications](<https://devfeed.tech/tags/applications.md>), [applying](<https://devfeed.tech/tags/applying.md>), [approach](<https://devfeed.tech/tags/approach.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [call](<https://devfeed.tech/tags/call.md>), [capture](<https://devfeed.tech/tags/capture.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [design](<https://devfeed.tech/tags/design.md>), [generation](<https://devfeed.tech/tags/generation.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [model](<https://devfeed.tech/tags/model.md>), [space](<https://devfeed.tech/tags/space.md>), [syntax](<https://devfeed.tech/tags/syntax.md>), [theory](<https://devfeed.tech/tags/theory.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The paper uses space syntax to make functional organization in generated floorplans measurable. Its Space Syntax Integration Operator (SSIO) recovers convex-space access graphs across heterogeneous formats as a shared design representation. Applying SSIO to residential corpora from 15 countries, the authors find that public spaces have the highest integration, with distributions varying by corpus. They use these patterns to build RPLAN-SSI, which evaluates population-level functional-profile alignment (IPD) and the distribution of public-space advantage within plans (PIAD). Against this reference, generated floorplans show a smaller integration advantage for public spaces. Space Syntax-Guided Post-Training (SSPT) uses SSIO-derived reinforcement-learning feedback to reduce IPD and PIAD across five heterogeneous diffusion backbones while preserving their native mechanisms.

### Source excerpt

arXiv:2602.22507v4 Announce Type: replace Abstract: Architectural design increasingly adopts generative AI (GenAI) for floorplan generation, an early-stage design task exploring how spaces should be organized for use. Yet fidelity objectives inherited from native visual and geometric generators do not automatically capture this design purpose. This organization remains largely implicit in generated representations, limiting direct evaluation and feedback. Drawing on space syntax, an established architectural design theory, the Space Syntax Integration Operator (SSIO) recovers convex-space access graphs across heterogeneous formats. This theory-grounded shared intermediate representation, which we call a design container, supports evaluation and model understanding of spatial design. Applying SSIO to four residential corpora spanning 15 countries reveals public spaces' integration levels are highest, with corpus-dependent distributions. These patterns underpin the RPLAN-SSI benchmark, an empirical design reference system assessing population-level functional-profile alignment (IPD) and distributional alignment of within-plan public-space advantage (PIAD). Comparison with this residential reference reveals a design gap: public spaces in generated floorplans have a smaller integration advantage over other spaces. To address this gap, Space Syntax-Guided Post-Training (SSPT) provides a plug-and-play design-learning interface: SSIO-derived RL feedback reduces IPD and PIAD across five heterogeneous diffusion backbones while preserving native mechanisms. We further discuss how this approach may inform GenAI applications in other design domains.

## Verifier Choice is a Benchmark Design Variable: Auditing Structural Counting Evaluation in Text-to-Image Models

DevFeed: [Verifier Choice is a Benchmark Design Variable: Auditing Structural Counting Evaluation in Text-to-Image Models](<https://devfeed.tech/articles/verifier-choice-is-a-benchmark-design-variable-auditing-structural-counting-evaluation-in-text-to-image-models-132994.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15433>)

Author: Shurun Li, Michael Hua Wang, Haibo Zeng, Long Wang

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [text-to-image](<https://devfeed.tech/topics/text-to-image.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Trustworthy AI](<https://devfeed.tech/topics/trustworthy-ai.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [flux](<https://devfeed.tech/topics/flux.md>), [qwen](<https://devfeed.tech/topics/qwen.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [aggregate](<https://devfeed.tech/tags/aggregate.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [audit](<https://devfeed.tech/tags/audit.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmark-design](<https://devfeed.tech/tags/benchmark-design.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [bias](<https://devfeed.tech/tags/bias.md>), [chairs](<https://devfeed.tech/tags/chairs.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-opus](<https://devfeed.tech/tags/claude-opus.md>), [clover](<https://devfeed.tech/tags/clover.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [counts](<https://devfeed.tech/tags/counts.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [image](<https://devfeed.tech/tags/image.md>), [models](<https://devfeed.tech/tags/models.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>)

### AI overview

The paper finds that structural-counting benchmark scores depend on the verifier and how it is used, not just on the image generator. Across 6,240 images and seven object or substructure categories, the authors compare open MLLM verifiers under count-only and reject-aware, zero-shot and few-shot protocols, alongside TIFA-like queries, a detector baseline, and closed-model checks on two difficult objects. On a balanced 2,280-image split, similar aggregate scores can hide image-level disagreement; every tested verifier-protocol setup narrows the human-measured gap between Qwen-Image-2512 and FLUX.2-dev by 7.5-25 percentage points. With Z-Image added, all four tested protocols reverse its human ranking against FLUX.2-dev on the fixed prompt suite. Closed-model checks retain failures: GPT-5.5 achieves 59.92% valid-count fidelity on clover, while Claude Opus 4.7 has κ=0.432 same-slice agreement. The authors propose reporting verifier reliability across score gaps, image-level agreement, generator-comparison distortion, valid-count fidelity, rejection, output compliance, and directional bias.

### Source excerpt

arXiv:2611.15433v1 Announce Type: cross Abstract: Automatic evaluation is now central to text-to-image benchmarking, but the verifier that converts generated images into scores is often treated as an implementation detail. We argue that this is unsafe: an automatic benchmark score is a property of the image generator, prompt distribution, verifier, verifier-use protocol, and scoring rule, not of the generator alone. We study this issue in structural counting, a controlled setting where human-visible counts can be audited. We construct a verifier-centric audit suite over seven counting objects: cell phones, chairs, and traffic lights for object counting, and clover leaflets, dresser drawer fronts, power-strip sockets, and turbine blades for substructure counting. Across 6,240 generated images from Qwen-Image-2512 and FLUX.2-dev, we compare open MLLM verifiers under count-only, reject-aware, zero-shot and few-shot protocols, plus TIFA-like target queries, a detector baseline, and frontier closed-model checks on two hard objects. On a balanced 2,280-image evaluation split, aggregate score matching can coexist with image-level disagreement, and verifier-use protocols and generator distributions change the measured reliability. Every verifier-protocol configuration also shrinks the human score difference between the two generators, by 7.5-25.0 pp, and with a third generator, Z-Image, all four tested protocols reverse the human ordering of Z-Image and FLUX.2-dev on our fixed prompt suite. GPT-5.5 and Claude Opus 4.7 checks do not remove the failure modes: GPT-5.5 still has only 59.92% clover valid-count fidelity, while Claude Opus 4.7 has lower same-slice agreement ($\kappa=0.432$). We propose reporting automatic benchmark scores with a factorized verifier reliability profile: aggregate score gap, image-level agreement, generator-comparison distortion, valid-image count fidelity, rejection behavior, output compliance, and directional bias.

[Next page](<https://devfeed.tech/topics/ai-image-generator.md?cursor=WyIyMDI2LTExLTEzVDA1OjAwOjAwKzAwOjAwIiwgImQ0MjM3ZjFiLTNmYTItNDA1YS04MDk1LTg2YjQwYWVhMTIzMyJd>)