# Image

Image refers to a depiction or representation that visually portrays objects, scenes, or ideas. This topic covers a broad spectrum from digital photographs and illustrations to complex graphics used in various forms of media. It explores the creation, editing, and usage of images in fields like photography, graphic design, advertising, and digital art. This topic also delves into the technologies and software that facilitate image processing and enhancement, highlighting trends and innovations in visual media.

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

## e-Paper Price Tags Become Picture Frames

DevFeed: [e-Paper Price Tags Become Picture Frames](<https://devfeed.tech/articles/e-paper-price-tags-become-picture-frames-146418.md>)

Original publisher: [Read original article](<https://hackaday.com/2026/11/20/e-paper-price-tags-become-picture-frames/>)

Author: Zoe Skyforest

Published: 2026-11-20T16:30:42Z

Content type: news

Language: en

Sources: [Hackaday](<https://devfeed.tech/sources/hackaday.md>)

Topics: [e-ink](<https://devfeed.tech/topics/e-ink.md>), [Image](<https://devfeed.tech/topics/image.md>), [image animation](<https://devfeed.tech/topics/image-animation.md>), [screen](<https://devfeed.tech/topics/screen.md>)

Tags: [backup](<https://devfeed.tech/tags/backup.md>), [bluetooth](<https://devfeed.tech/tags/bluetooth.md>), [browser](<https://devfeed.tech/tags/browser.md>), [colors](<https://devfeed.tech/tags/colors.md>), [custom-firmware](<https://devfeed.tech/tags/custom-firmware.md>), [display](<https://devfeed.tech/tags/display.md>), [e-ink](<https://devfeed.tech/tags/e-ink.md>), [e-paper](<https://devfeed.tech/tags/e-paper.md>), [electronic-shelf-label](<https://devfeed.tech/tags/electronic-shelf-label.md>), [esl](<https://devfeed.tech/tags/esl.md>), [frame](<https://devfeed.tech/tags/frame.md>), [hacks](<https://devfeed.tech/tags/hacks.md>), [images](<https://devfeed.tech/tags/images.md>), [install](<https://devfeed.tech/tags/install.md>), [open-firmware](<https://devfeed.tech/tags/open-firmware.md>), [price-tag](<https://devfeed.tech/tags/price-tag.md>), [software-hacks](<https://devfeed.tech/tags/software-hacks.md>), [tag](<https://devfeed.tech/tags/tag.md>), [timer](<https://devfeed.tech/tags/timer.md>)

### AI overview

pin16 is open firmware for Solum EFR32BG22 electronic shelf labels, specifically the EL016 (200x200) and EL022 (160x296), which use black, white, red, and yellow. It lets users upload images over Bluetooth through a browser; the browser converts them for display, and the labels can show them as timed slideshows or custom graphics. Firmware updates can then be made over Bluetooth, but the initial installation requires SWD reprogramming, and factory firmware cannot be backed up. The excerpt cautions against installing it on tags you do not own.

### Source excerpt

E-paper has lots of applications, though it's found a particularly solid market penetration as a replacement for simple paper price tags. Because why have a cheap slip of paper for ...read more

## DAWN: Robust Neural Blind Deconvolution via Alternating Wiener Guidance

DevFeed: [DAWN: Robust Neural Blind Deconvolution via Alternating Wiener Guidance](<https://devfeed.tech/articles/dawn-robust-neural-blind-deconvolution-via-alternating-wiener-guidance-145555.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25621>)

Author: Yida Pan, Yixuan Jia, Chaoyan Huang, Qing Qu, Ismail Alkhouri

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](<https://devfeed.tech/topics/image.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>)

Tags: [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>), [dataset](<https://devfeed.tech/tags/dataset.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [dip](<https://devfeed.tech/tags/dip.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [image](<https://devfeed.tech/tags/image.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [microscopy](<https://devfeed.tech/tags/microscopy.md>), [network](<https://devfeed.tech/tags/network.md>), [neural](<https://devfeed.tech/tags/neural.md>), [noise](<https://devfeed.tech/tags/noise.md>), [photography](<https://devfeed.tech/tags/photography.md>), [robust](<https://devfeed.tech/tags/robust.md>), [training-data](<https://devfeed.tech/tags/training-data.md>)

### AI overview

DAWN is a training-data-free deep image prior framework for blind image deconvolution, designed to reduce noise overfitting and improve blur-kernel estimates. It alternates between feeding model-based estimates into the network and refining them with the network's prior, using autoencoding regularization on both image and kernel networks. On natural and scientific images with Gaussian and Poisson noise, the authors report better image and kernel quality than state-of-the-art methods, including up to 4.5 dB over the next-best baseline on the Levin dataset at σ = 0.1. Without training images, DAWN is also reported to remain highly competitive with a diffusion model trained on many in-distribution FFHQ images.

### Source excerpt

arXiv:2611.25621v1 Announce Type: cross Abstract: Blind image deconvolution (BID) is an ill-posed inverse problem that aims to jointly recover a sharp image and blur kernel from a single degraded observation. Under nontrivial and high noise, which is common in photography and scientific imaging such as microscopy, BID remains particularly challenging, as existing methods suffer from noise overfitting and inaccurate kernel estimation. Existing training-data-free learning methods for BID, such as those based on the deep image prior (DIP), often utilize external guidance by including model-based estimates as additional loss terms, which underexploits the information these estimates carry especially under nontrivial noise. To address these challenges, we propose DAWN, a training-data-free DIP framework that alternates between injecting model-based estimates directly into the model input and refining this imperfect estimate with the network's own prior. To provide more reliable kernel estimates for these injections, we apply autoencoding regularization to both the image and kernel networks. On natural and scientific images under varying levels of Gaussian and Poisson noise, DAWN outperforms state-of-the-art methods in both image and kernel quality (achieving up to +4.5 dB over the next best baseline on the Levin dataset at $\sigma = 0.1$). Without any training images, DAWN remains highly competitive with a state-of-the-art diffusion model on FFHQ, despite the latter being trained on a massive number of in-distribution images.

## 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.

## Keystone: Judging Previews at Key Steps for Test-Time Search in Diffusion Models

DevFeed: [Keystone: Judging Previews at Key Steps for Test-Time Search in Diffusion Models](<https://devfeed.tech/articles/keystone-judging-previews-at-key-steps-for-test-time-search-in-diffusion-models-145530.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25530>)

Author: Jiajun Fan, Chaoran Cheng, Ziwen Wang, Changyi Yang, Bangji Yang, Qinglong Zheng, Ge Liu

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

Content type: article

Language: en

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

Topics: [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Image](<https://devfeed.tech/topics/image.md>), [diffusion-transformers](<https://devfeed.tech/topics/diffusion-transformers.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [keystone](<https://devfeed.tech/tags/keystone.md>), [preview](<https://devfeed.tech/tags/preview.md>), [search](<https://devfeed.tech/tags/search.md>), [test](<https://devfeed.tech/tags/test.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>)

### AI overview

Keystone is a training-free method for judging diffusion-model previews early in denoising, where the abstract says outcomes are often already determined by the seed or a sampler's initial stochastic steps. Instead of applying reward models designed for finished images--which read early previews near chance on several prompt types--Keystone turns prompts into typed questions about objects, counts, colours, and positions, then uses an off-the-shelf multimodal decision model to answer them. On GenEval with SD3.5-Medium, its adaptive search and pruning reportedly beat best-of-8 with every other verifier using less than half the generator compute. As a drop-in verifier, its score also improved best-of-N, progressive seed pruning, and FK steering there. Without retuning, both searches remained above the strongest other verifier's best-of-N on average across four base models and three benchmarks.

### Source excerpt

arXiv:2611.25530v1 Announce Type: new Abstract: Text-to-image diffusion and flow models yield a preview, their clean-image estimate, at every denoising step. When they miscount, drop or misplace objects, test-time search is in a bind: its verifiers are reward models built for finished images, so judging early misreads blurry previews, and judging late, as best-of-N does, pays to fully denoise doomed candidates. We find that the image is not the problem: the outcome is settled as denoising starts, by the seed or by a stochastic sampler's first steps, and already shows in early previews; what fails on them is the judge, as reward models read them near chance on several kinds of prompts. We introduce Keystone, a training-free judge of previews that compiles a prompt into typed questions about its objects, counts, colours and positions and has an off-the-shelf multimodal decision model answer them. Asked this way, the judge reads counts and positions from early previews better than reward models read them from finished images. Searching at these key steps on GenEval with SD3.5-Medium, Keystone's adaptive search and pruning significantly outperform best-of-8 with every other verifier at under half its generator compute, and as a drop-in verifier there, the Keystone score significantly improves best-of-N, progressive seed pruning and FK steering; without retuning, both searches stay significantly above the strongest other verifier's best-of-N on average over four base models and three benchmarks. Keystone thus moves test-time judgment to the key steps where the outcome already shows.

## Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth

DevFeed: [Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth](<https://devfeed.tech/articles/depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth-145199.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26603>)

Author: Peiyun Hu, Marko Mihajlovic, Lyndon Duong, Lahav Lipson, Wei Dong, Ama\\"el Delaunoy, Stephan R. Richter, Vladlen Koltun

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

Content type: article

Language: en

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

Topics: [Image](<https://devfeed.tech/topics/image.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [depth-estimation](<https://devfeed.tech/tags/depth-estimation.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [images](<https://devfeed.tech/tags/images.md>), [maps](<https://devfeed.tech/tags/maps.md>), [metric](<https://devfeed.tech/tags/metric.md>), [models](<https://devfeed.tech/tags/models.md>), [native](<https://devfeed.tech/tags/native.md>), [network](<https://devfeed.tech/tags/network.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [sharp](<https://devfeed.tech/tags/sharp.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [trade](<https://devfeed.tech/tags/trade.md>), [train](<https://devfeed.tech/tags/train.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

Depth Pro 2 is a scalable network for estimating dense metric depth from images and video at native resolution. The authors identify a common tradeoff in prior monocular methods: multi-frame approaches tend to favor temporal consistency, while single-frame approaches favor sharp boundaries. Their model processes both images and video and is reported to deliver metric accuracy, sharpness, and temporal consistency together, outperforming prior work on those dimensions. The released model family spans a Pareto frontier across metric accuracy, sharpness, temporal consistency, and runtime; the excerpt does not provide quantitative comparisons or details on runtime.

### Source excerpt

arXiv:2611.26603v1 Announce Type: cross Abstract: We present Depth Pro 2, an approach to estimating dense metric depth for images and video at full resolution. By analyzing prior methods for monocular depth estimation, we find that they commonly trade off temporal consistency and boundary sharpness: multi-frame methods favor consistency, single-frame methods favor sharpness. To overcome this trade-off, we train a single, scalable network that processes both images and video and predicts depth maps at native resolution. Depth Pro 2 produces depth maps that are metrically accurate, sharp, and temporally consistent all at once, outperforming prior work in all of these dimensions. We release a family of models that define a new Pareto frontier in terms of metric accuracy, sharpness, temporal consistency, and runtime. We release code and weights at https://apple-aiml-research.github.io/ml-depth-pro-2/

## D\\'ej\\\`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates

DevFeed: [D\\'ej\\\`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates](<https://devfeed.tech/articles/d-ej-a-cue-localizing-states-in-object-histories-via-vocabulary-relative-coordinates-144916.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.02044>)

Author: Haofan Cao, Zhichao You, Yunkai Yang, Liang Guo, Jie Wang, Chongshou Li

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

Content type: article

Language: en

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

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [absolute](<https://devfeed.tech/tags/absolute.md>), [alternatives](<https://devfeed.tech/tags/alternatives.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>), [cs-mm](<https://devfeed.tech/tags/cs-mm.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [encoder](<https://devfeed.tech/tags/encoder.md>), [localization](<https://devfeed.tech/tags/localization.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [object](<https://devfeed.tech/tags/object.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [text](<https://devfeed.tech/tags/text.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

Déjà Cue localizes described states in tracked object histories by comparing each description against the alternatives in a supplied, state-balanced vocabulary. The training-free method centers description embeddings on the vocabulary mean, then uses frozen vision-language encoders to calibrate frame scores and retrieve intervals of multiple durations within contiguous visible runs. The authors introduce MS-VOST, annotating 620 object histories with 2,465 states. With the encoder and temporal search fixed, it outperforms absolute scoring on all three localization metrics across eight encoder configurations, improving Top-1 temporal IoU by 0.42-1.14 percentage points. Reported gains persist across four text constructions; candidate-ranking analysis indicates relevant intervals are ranked higher within the same search space.

### Source excerpt

arXiv:2608.02044v2 Announce Type: replace-cross Abstract: Object tracking preserves identity through visual changes, but cannot tell when an object is whole, cut, or peeled. We study state-moment retrieval: locating when a tracked object exhibits each state in a supplied set of descriptions. However, absolute image--text similarity can favor shared object semantics, obscuring the distinctions needed to localize individual states. Our insight is that the alternatives themselves provide a reference for measuring state evidence. We introduce D\'ej\`a Cue, a training-free framework that centers description embeddings on a state-balanced vocabulary mean, producing query directions that compare each state against its alternatives. Using frozen vision--language encoders, D\'ej\`a Cue calibrates frame scores and retrieves intervals at multiple durations within contiguous visible runs. We construct MS-VOST by annotating 620 object histories with 2,465 states. With the encoder and temporal search fixed, D\'ej\`a Cue improves all three localization metrics over absolute scoring across eight encoder configurations, raising Top-1 temporal IoU by 0.42--1.14 percentage points. These gains persist across four text constructions, and candidate-ranking analysis shows that the vocabulary reference brings relevant intervals forward within the same search space. These results establish the supplied state vocabulary as an object-specific reference for localizing semantic states from frozen visual representations.

## Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration

DevFeed: [Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration](<https://devfeed.tech/articles/beyond-visual-fidelity-benchmarking-super-resolution-models-for-large-scale-remote-sensing-imagery-via-downstream-task-integration-144889.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.00310>)

Author: Zhili Li, Kangyang Chai, Zhihao Wang, Xiaowei Jia, Yanhua Li, Gengchen Mai, Sergii Skakun, Zhe Zhu, Dinesh Manocha, Yiqun Xie

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>)

Tags: [agriculture](<https://devfeed.tech/tags/agriculture.md>), [benchmark-dataset](<https://devfeed.tech/tags/benchmark-dataset.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [change-detection](<https://devfeed.tech/tags/change-detection.md>), [cross-platform](<https://devfeed.tech/tags/cross-platform.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>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [remote-sensing](<https://devfeed.tech/tags/remote-sensing.md>), [super-resolution](<https://devfeed.tech/tags/super-resolution.md>)

### AI overview

GeoSR-Bench evaluates satellite image super-resolution by whether it improves Earth monitoring tasks, not just visual fidelity. It contains spatially co-located, temporally aligned, quality-controlled image pairs from about 36,000 locations across diverse land covers, at resolutions from 500 m to 0.6 m. The benchmark tests GAN, transformer, neural operator, and diffusion models across 270 settings, including two cross-platform SR tasks and downstream tasks such as land cover segmentation, infrastructure mapping, and biophysical variable estimation. Results show that better PSNR or SSIM often does not predict better task performance, and correlations can be negative, limiting these metrics as guides for model selection.

### Source excerpt

arXiv:2605.00310v3 Announce Type: replace-cross Abstract: Super-resolution (SR) techniques have made major advances in reconstructing high-resolution images from low-resolution inputs. The increased resolution provides visual enhancement and utility for monitoring tasks. In particular, SR has been increasingly developed for satellite-based Earth observation, with applications in urban planning, agriculture, ecology, and disaster response. However, existing SR studies and benchmarks typically use fidelity metrics such as PSNR or SSIM, whereas the true utility of super-resolved images lies in supporting downstream tasks such as land cover classification, biomass estimation, and change detection. To bridge this gap, we introduce GeoSR-Bench, a downstream task-integrated SR benchmark dataset to evaluate SR models beyond fidelity metrics. GeoSR-Bench comprises spatially co-located, temporally aligned, and quality-controlled image pairs from about 36,000 locations across diverse land covers, spanning resolutions from 500m to 0.6m. To the best of our knowledge, GeoSR-Bench is the first SR benchmark that directly connects improved image resolution from SR models with downstream Earth monitoring tasks, including land cover segmentation, infrastructure mapping, and biophysical variable estimation. Using GeoSR-Bench, we benchmark GAN, transformer, neural operator, and diffusion-based SR models on perceptual quality and downstream task performance. We conduct experiments with 270 settings, covering 2 cross-platform SR tasks, 9 SR models, 3 downstream task models, and 5 downstream tasks for each SR task. The results show that improvements in traditional SR metrics often do not correlate with gains in task performance, and the correlations can be negative, indicating that these metrics provide limited guidance for selecting superior models for downstream tasks. This reveals the need to integrate downstream tasks into SR model development and evaluation.

## Question, Then Affirm: Restoring Commitment Does Not Restore Refusal

DevFeed: [Question, Then Affirm: Restoring Commitment Does Not Restore Refusal](<https://devfeed.tech/articles/question-then-affirm-restoring-commitment-does-not-restore-refusal-146050.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25929>)

Author: Haoyang Xu, Qirui Wang, Liuwan Zhu

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

Content type: article

Language: en

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

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

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [deferred](<https://devfeed.tech/tags/deferred.md>), [element](<https://devfeed.tech/tags/element.md>), [elements](<https://devfeed.tech/tags/elements.md>), [generation](<https://devfeed.tech/tags/generation.md>), [gpt-image-2](<https://devfeed.tech/tags/gpt-image-2.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [meaning](<https://devfeed.tech/tags/meaning.md>), [question](<https://devfeed.tech/tags/question.md>), [restore](<https://devfeed.tech/tags/restore.md>), [safety](<https://devfeed.tech/tags/safety.md>)

### AI overview

On a 300-case challenge set, gpt-image-2 generated images for 43.3% of harmful requests phrased as questions followed by an affirmation, versus 16.3% of direct statements; the images endorsed the original proposition in 41.3% versus 15.3% of cases. The authors call this Deferred Semantic Commitment: questioning withdraws commitment, then a separate element restores it, but safety behavior appears to track the withdrawal. In an open-weight language model, re-endorsement only partly reversed the refusal-related change caused by questioning. The authors argue safeguards should assess the completed message. These findings are reported in the supplied abstract.

### Source excerpt

arXiv:2611.25929v1 Announce Type: new Abstract: We find that safeguards for image generation can be bypassed without changing what a message says. A sign stating a harmful proposition is blocked, but the same proposition phrased as a question and followed by a check mark is generated, even though the resulting image endorses the original claim. On a 300-case challenge set, gpt-image-2 returns images for 43.3% of question-affirmation requests versus 16.3% of direct statements, with 41.3% versus 15.3% of cases yielding images that endorse the original proposition. We define this as Deferred Semantic Commitment (DSC): commitment is withdrawn by the question and restored by a separate element, while safety behavior follows only the withdrawal. To investigate why, we study an open-weight language model and find that re-endorsement only partially reverses the refusal-related change introduced by questioning. These findings reveal a mismatch between recovered meaning and refusal behavior, motivating safeguards that assess the completed message rather than its individual elements.

## Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction

DevFeed: [Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction](<https://devfeed.tech/articles/infer3d-inverse-generative-modeling-enables-robust-3d-reconstruction-145004.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25061>)

Author: Amani Kiruga, Mark Hamilton, Joshua B. Tenenbaum, William T. Freeman, Vincent Sitzmann, Yilun Du, Ayush Tewari

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

Content type: article

Language: en

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

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-reconstruction](<https://devfeed.tech/tags/3d-reconstruction.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [generative](<https://devfeed.tech/tags/generative.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [ood](<https://devfeed.tech/tags/ood.md>), [robust](<https://devfeed.tech/tags/robust.md>)

### AI overview

Infer3D reconstructs 3D scenes from a single image by optimizing the latent variables of a generative model to match the input, rather than relying only on fast feedforward inference. A frozen 3D lifting network constrains optimization to a valid, multi-view-consistent 3D manifold to prevent flat outputs. On controlled synthetic and real-world tasks, the authors report better out-of-distribution reconstruction accuracy than feedforward networks trained on equal or larger datasets. Its adaptive strategy spends more test-time compute on ambiguous out-of-distribution examples while routing in-distribution inputs efficiently; the abstract does not quantify this compute or accuracy tradeoff.

### Source excerpt

arXiv:2611.25061v1 Announce Type: cross Abstract: Humans can understand the 3D structure of scenes even from highly unfamiliar or extreme viewpoints. Cognitive science suggests this generalization stems from a top-down generative inference strategy. In contrast, state-of-the-art 3D reconstruction neural networks typically rely on amortized, feedforward inference. While fast, this pattern-matching approach degrades when faced with out-of-distribution (OOD) scene conditions unseen during training. Inspired by the generative nature of human vision, we propose Infer3D, an inverse generative modeling framework that recovers the latent variables of a generative model to best match the monocular input. To prevent degenerate flat outputs, we couple the generative image prior with a frozen 3D lifting network that constrains the optimization space to a valid, multi-view-consistent 3D manifold. Across a variety of controlled synthetic and real-world tasks, Infer3D demonstrates superior OOD reconstruction accuracy compared to feedforward networks trained on equal or larger datasets. Furthermore, mirroring how human perception requires more time to process confusing stimuli, we introduce an adaptive inference strategy that expends more test-time compute on ambiguous OOD examples while efficiently routing in-distribution inputs. Project website: https://amanikiruga.github.io/infer3d-site/

## 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.

## {\\lambda}Split: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy

DevFeed: [{\\lambda}Split: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy](<https://devfeed.tech/articles/lambda-split-self-supervised-content-aware-spectral-unmixing-for-fluorescence-microscopy-144881.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2603.23647>)

Author: Federico Carrara, Talley Lambert, Mehdi Seifi, Florian Jug

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: [Physics-guided deep learning](<https://devfeed.tech/topics/physics-guided-deep-learning.md>), [Image](<https://devfeed.tech/topics/image.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>), [hardware](<https://devfeed.tech/tags/hardware.md>), [image](<https://devfeed.tech/tags/image.md>), [learning](<https://devfeed.tech/tags/learning.md>), [microscopy](<https://devfeed.tech/tags/microscopy.md>), [model](<https://devfeed.tech/tags/model.md>), [noise](<https://devfeed.tech/tags/noise.md>), [overlap](<https://devfeed.tech/tags/overlap.md>)

### AI overview

λSplit addresses fluorescence spectral unmixing, where pixel-wise least-squares methods can degrade with overlapping emissions and noise. It uses a hierarchical Variational Autoencoder to learn a conditional distribution over fluorophore concentration maps, with a differentiable Spectral Mixer enforcing consistency with image formation. The authors report evaluation on 66 challenging benchmarks derived from three real-world datasets, compared with 10 classical and learning-based baselines. They report competitive performance and greater robustness under high noise, substantial spectral overlap, and reduced spectral dimensionality, as well as implicit noise removal. The method is described as compatible with standard confocal microscope data without hardware modifications.

### Source excerpt

arXiv:2603.23647v4 Announce Type: replace-cross Abstract: In fluorescence microscopy, spectral unmixing aims to recover individual fluorophore concentrations from spectral images that capture mixed fluorophore emissions. Since classical methods operate pixel-wise and rely on least-squares fitting, their performance degrades with increasingly overlapping emission spectra and higher levels of noise, suggesting that a data-driven approach that can learn and utilize a structural prior might lead to improved results. Learning-based approaches for spectral imaging do exist, but they are either not optimized for microscopy data or are developed for very specific cases that are not applicable to fluorescence microscopy settings. To address this, we propose {\lambda}Split, a physics-informed deep generative model that learns a conditional distribution over concentration maps using a hierarchical Variational Autoencoder. A fully differentiable Spectral Mixer enforces consistency with the image formation process, while the learned structural priors enable state-of-the-art unmixing and implicit noise removal. We demonstrate {\lambda}Split on 3 real-world datasets that we synthetically cast into a total of 66 challenging spectral unmixing benchmarks. We compare our results against a total of 10 baseline methods, including classical methods and a range of learning-based methods. Our results consistently show competitive performance and improved robustness in high noise regimes, when spectra overlap considerably, or when the spectral dimensionality is lowered, making {\lambda}Split a new state-of-the-art for spectral unmixing of fluorescent microscopy data. Importantly, {\lambda}Split is compatible with spectral data produced by standard confocal microscopes, enabling immediate adoption without specialized hardware modifications.

## Multi-View Transformer with Geometry-Guided Multi-Modal ControlNet for 3D Virtual Try-On

DevFeed: [Multi-View Transformer with Geometry-Guided Multi-Modal ControlNet for 3D Virtual Try-On](<https://devfeed.tech/articles/multi-view-transformer-with-geometry-guided-multi-modal-controlnet-for-3d-virtual-try-on-145615.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25979>)

Author: Sarthak Batra, Armin Mustafa, Adrian Hilton

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

Content type: article

Language: en

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

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-gaussian-splatting](<https://devfeed.tech/tags/3d-gaussian-splatting.md>), [3dgs](<https://devfeed.tech/tags/3dgs.md>), [attention](<https://devfeed.tech/tags/attention.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [camera](<https://devfeed.tech/tags/camera.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>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [image](<https://devfeed.tech/tags/image.md>), [modal](<https://devfeed.tech/tags/modal.md>), [proximity](<https://devfeed.tech/tags/proximity.md>), [reference](<https://devfeed.tech/tags/reference.md>), [self-attention](<https://devfeed.tech/tags/self-attention.md>), [structure](<https://devfeed.tech/tags/structure.md>), [training](<https://devfeed.tech/tags/training.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [view](<https://devfeed.tech/tags/view.md>), [virtual-try-on](<https://devfeed.tech/tags/virtual-try-on.md>)

### AI overview

GS-VTON-MVT aims to keep garment details consistent across views when editing a person captured as a 3D Gaussian Splatting scene. It jointly inpaints training views using cross-view self-attention, conditions its diffusion editor on the garment image plus depth and surface normals rendered from the current 3DGS, and adapts attention between current and reference views according to camera-pose proximity. The approach addresses inconsistencies associated with independently edited views and fixed, hand-designed fusion. On 3D-VTONBench, the authors report improvements in FID, KID, LPIPS-based cross-view consistency, and user preference over general-purpose 3D editors and earlier 3D try-on methods; the excerpt gives no metric values.

### Source excerpt

arXiv:2611.25979v1 Announce Type: cross Abstract: Editing a 3D Gaussian Splatting (3DGS) capture of a person so that they wear a new garment requires every rendered view to agree on the same garment details. Existing 3D virtual try-on (VTON) pipelines, however, edit training views largely independently and fuse them with hand-designed heuristics such as manually chosen reference views and fixed attention-blending weights. The resulting inconsistencies are baked into the 3D representation and surface as texture drift, blurred prints, and implausible geometry in novel views. We present GS-VTON-MVT, a three-stage framework that combines implicit and explicit 3D reasoning for consistent 3DGS try-on. (i) A multi-view inpainting transformer jointly edits a set of training views with full cross-view self-attention, so that cross-view correspondence is learned rather than imposed. (ii) A geometry-guided multi-modal ControlNet conditions the diffusion editor on the garment image together with depth and surface normals rendered from the current 3DGS state, supplying explicit structure where visual evidence is weakest. (iii) A pose-adaptive persona-aware attention replaces the fixed blending weight between current-view and reference-view features with weights derived from camera-pose proximity. On the 3D-VTONBench benchmark, GS-VTON-MVT improves FID, KID, LPIPS-based cross-view consistency, and user preference over general-purpose 3D editors and prior 3D try-on methods.

## Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method

DevFeed: [Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method](<https://devfeed.tech/articles/towards-embodied-air-ground-cooperative-object-search-benchmark-dataset-and-agentic-method-145369.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.08402>)

Author: Boao Yu, Zimo Chen, Junreng Rao, Yue Hu, Zhengqiu Zhu, Yong Zhao, Rusheng Ju

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

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>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [air](<https://devfeed.tech/tags/air.md>), [approach](<https://devfeed.tech/tags/approach.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmark-dataset](<https://devfeed.tech/tags/benchmark-dataset.md>), [computer-science](<https://devfeed.tech/tags/computer-science.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>), [dataset](<https://devfeed.tech/tags/dataset.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [first](<https://devfeed.tech/tags/first.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-3-6-flash](<https://devfeed.tech/tags/gemini-3-6-flash.md>), [object](<https://devfeed.tech/tags/object.md>), [search](<https://devfeed.tech/tags/search.md>), [vision-language-models-vlms](<https://devfeed.tech/tags/vision-language-models-vlms.md>), [vlms](<https://devfeed.tech/tags/vlms.md>)

### AI overview

The paper introduces AGOS, an urban search task where UAVs find a target vehicle from multi-view references and UGVs verify it at ground level. AGOS-Bench evaluates whether general-purpose vision-language models can coordinate those roles; its companion AGOS-Dataset contains 7.7k automatically constructed episodes across three difficulty levels. The proposed training-free, tool-augmented AGOS-Agent uses a search-handoff-verify protocol, leaving scene understanding and decision-making to the VLMs. Across nine evaluated models, it improves overall success rate for eight and reduces decision steps for all nine. On the hard split, Gemini-3.6-Flash's success rate rises from 8.6% to 55.7%, and its SPL from 7.6% to 44.0%.

### Source excerpt

arXiv:2609.08402v2 Announce Type: replace-cross Abstract: Air-Ground Object Search (AGOS) in urban environments is a challenging embodied task, which requires an Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV) to jointly search for and verify a specified target vehicle from multi-view visual references. To study this underexplored problem, we introduce AGOS-Bench, the first dedicated benchmark for evaluating whether general-purpose Vision-Language Models (VLMs) can integrate aerial discoveries and ground-level verification through UAV-UGV cooperation. We further provide AGOS-Dataset as the companion resource of exemplary trajectories constructed by an automatic pipeline. It consists of 7.7k episodes for searching objects of diverse categories and attributes, spanning three difficulty levels. To address the AGOS task, we propose AGOS-Agent, a training-free and tool-augmented approach. The agentic method relieves VLMs from complex and dynamic coordination via a deliberate search-handoff-verify cooperation protocol, only demanding VLMs for scene understanding and decision-making. Extensive experiments on nine VLMs show that AGOS-Agent improves overall success rate for eight of the nine evaluated backbones while reducing decision steps for all nine. On the hard split, the SR and SPL of Gemini-3.6-Flash increase from 8.6% to 55.7% and from 7.6% to 44.0%, respectively.

## HiUni: Harmonizing Understanding and Generation in Shared Visual Space

DevFeed: [HiUni: Harmonizing Understanding and Generation in Shared Visual Space](<https://devfeed.tech/articles/hiuni-harmonizing-understanding-and-generation-in-shared-visual-space-145631.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26107>)

Author: Jiahao Hu, Jingdong Du, Yichen Zhang, Yi Song, Zhenyu Zhang, Jiaxin Niu, Ruihang Li, Xiangzhao Hao, Yiqian Zhang, Yong Huang, Zefeng Zhang, Zheyuan Gu, Shuohuan Wang

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

Content type: article

Language: en

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

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

Tags: [comparisons](<https://devfeed.tech/tags/comparisons.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>), [experiments](<https://devfeed.tech/tags/experiments.md>), [generation](<https://devfeed.tech/tags/generation.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [key](<https://devfeed.tech/tags/key.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [pixel](<https://devfeed.tech/tags/pixel.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [sharing](<https://devfeed.tech/tags/sharing.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vision-language-model](<https://devfeed.tech/tags/vision-language-model.md>), [vit](<https://devfeed.tech/tags/vit.md>)

### AI overview

HiUni extends a pretrained vision-language model for understanding and image generation using the same language-aligned ViT and dense Transformer backbone, with task-specific computation confined to the output. To address the difficulty of optimizing pixel-space generation and the loss of spatial detail in the pretrained ViT, it adds a Pixel Diffusion Head and a lightweight HiGate pathway. The abstract reports an average understanding score similar to the pretrained model and competitive image generation and editing performance; it provides no specific scores or benchmark details.

### Source excerpt

arXiv:2611.26107v1 Announce Type: cross Abstract: Unified multimodal models aim to support visual understanding and generation within a single framework. However, prevailing approaches often separate their visual representations or backbone computation to accommodate the different requirements of these two tasks, which limits the degree of unification. In this paper, we present HiUni, which revisits this design choice and explores whether a pretrained vision language model can be directly extended into a unified model with extensive parameter sharing. Specifically, HiUni reuses the same language-aligned ViT and dense Transformer backbone for both capabilities, while confining task-specific computation to the output side. Yet such a design introduces two key challenges. Generation in pixel space is difficult to optimize, and semantic abstraction in pretrained ViT discards fine spatial details required for synthesis. To address these challenges, HiUni introduces a \emph{Pixel Diffusion Head} tailored to direct pixel-space optimization and a lightweight \emph{HiGate} pathway that provides fine-grained spatial details near the output stage. Extensive experiments show that HiUni achieves a similar average understanding score to the pretrained VLM while attaining competitive performance on image generation and editing. Controlled comparisons and analyses further demonstrate that a single dense backbone can effectively support both capabilities without task-specific backbone computation, highlighting a simpler path toward unified multimodal modeling.

## Class-Conditional Conformal Triage for ICAO Face-Image Compliance under Class Imbalance

DevFeed: [Class-Conditional Conformal Triage for ICAO Face-Image Compliance under Class Imbalance](<https://devfeed.tech/articles/class-conditional-conformal-triage-for-icao-face-image-compliance-under-class-imbalance-145045.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25342>)

Author: Mustafa Vedat Yildirim, Inna Skarga-Bandurova

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

Content type: article

Language: en

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

Topics: [Image](<https://devfeed.tech/topics/image.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [classification](<https://devfeed.tech/tags/classification.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [conformal-prediction](<https://devfeed.tech/tags/conformal-prediction.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [false-positive](<https://devfeed.tech/tags/false-positive.md>), [image](<https://devfeed.tech/tags/image.md>), [images](<https://devfeed.tech/tags/images.md>), [layer](<https://devfeed.tech/tags/layer.md>), [performance](<https://devfeed.tech/tags/performance.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [reduction](<https://devfeed.tech/tags/reduction.md>), [triage](<https://devfeed.tech/tags/triage.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

### AI overview

The study evaluates conformal prediction as an uncertainty-based triage layer for BioGaze's 14 ICAO/ISO face-image criteria, using synthetic TONO data and subject-disjoint splits without retraining the analyser. Marginal conformal prediction reached about 0.90 overall coverage but under-covered violations (as low as a 0.37 ten-partition mean for one criterion). Mondrian class-conditional coverage means were 0.89-0.92 across criteria. Most criterion-level false-positive reduction came from adding per-criterion logistic classifiers (0.145 to 0.048); tuned abstention rules had lower false-positive rates than Mondrian at comparable retake rates. Bonferroni correction for joint coverage across all 14 criteria required retaking nearly every image, exposing a trade-off between coverage guarantees and practical retake burden.

### Source excerpt

arXiv:2611.25342v1 Announce Type: new Abstract: Automated ICAO/ISO face-image compliance analysers provide criterion-level pass/fail decisions, yet these verdicts do not quantify uncertainty when deciding whether to accept, reject, or retake a photograph. We investigate conformal prediction as a triage layer for BioGaze, evaluating 14 compliance criteria on the synthetic TONO benchmark. Without retraining the analyser, we fit per-criterion logistic classifiers and compare marginal and label-conditional (Mondrian) conformal prediction with conventional abstention rules using subject-disjoint splits. Marginal conformal prediction achieved approximately 0.90 overall coverage but substantially under-covered violations, with a ten-partition mean of 0.37 for one criterion. The corresponding Mondrian means ranged from 0.89 to 0.92 across criteria. However, most of the reduction in criterion-level false positives came from the logistic layer (0.145 to 0.048), while tuned abstention rules achieved lower false-positive rates than Mondrian at comparable retake rates. Bonferroni correction for joint coverage across 14 criteria required retaking nearly all images. These findings show that class-conditional conformal prediction can achieve near-target empirical coverage for minority violation classes and reveal trade-offs between statistical coverage, classification performance, and retake requirements in multi-criterion face-image compliance assessment.

## AeroBelief: Budgeted First-Action Verification for Evidence-Guided Aerial Sensing

DevFeed: [AeroBelief: Budgeted First-Action Verification for Evidence-Guided Aerial Sensing](<https://devfeed.tech/articles/aerobelief-budgeted-first-action-verification-for-evidence-guided-aerial-sensing-145539.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25568>)

Author: Tianren Li, Dongbo Li, Hongkai Chen, Jie Liu, Guoliang Xing

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

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

Tags: [budgeting](<https://devfeed.tech/tags/budgeting.md>), [complete](<https://devfeed.tech/tags/complete.md>), [context](<https://devfeed.tech/tags/context.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dji](<https://devfeed.tech/tags/dji.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [hosted](<https://devfeed.tech/tags/hosted.md>), [image](<https://devfeed.tech/tags/image.md>), [image-processing](<https://devfeed.tech/tags/image-processing.md>), [imagery](<https://devfeed.tech/tags/imagery.md>), [queries](<https://devfeed.tech/tags/queries.md>), [reference](<https://devfeed.tech/tags/reference.md>), [sensing](<https://devfeed.tech/tags/sensing.md>), [target](<https://devfeed.tech/tags/target.md>), [verification](<https://devfeed.tech/tags/verification.md>), [world-model](<https://devfeed.tech/tags/world-model.md>)

### AI overview

AeroBelief verifies candidate aerial views by their next executable action: an inexpensive proposer scans grouped views, then a structured world model is queried selectively. Calibrated bounds and a six-query controller connect action selection to belief updates, acceptance checks, and scheduled sensing. In 960 executions across 40 worlds, it completed 75.42% of tasks, versus 73.33% with exhaustive world-model scoring and 65.83% with line-of-sight geometry, while using 91.81% fewer reference-candidate evaluations than exhaustive scoring. In fixed-reference replay, proposer-scaled bounds improved first-action certificate availability from 36.25% to 54.69% and cut mean queries per state by 13.54% versus unit-scale anchored bounds. A separate ground-hosted pipeline applied context-guided admission and feedback to 2,685 UAV images from seven routes: it retained all eight independently supported target confirmations while processing 76.05% fewer images and using 70.02% less active processing service than uncapped all-frame processing. These findings are reported for the described simulations and recorded imagery.

### Source excerpt

arXiv:2611.25568v1 Announce Type: new Abstract: Aerial sensing must combine uncertain overhead context with current observations while budgeting prediction, movement and image processing. AeroBelief uses the next executable action as the unit of verification against reference scores. It groups candidate views by first action, scans them with an inexpensive proposer, and selectively queries a structured world model (WM). Calibrated group bounds support strict commitment; a six-query controller connects selective prediction with belief updates, acceptance checks and scheduled sensing. Across four layout families, 40 worlds and 960 closed-loop executions, the AeroBelief controller completes 75.42% of tasks, compared with 73.33% for exhaustive WM scoring and 65.83% for line-of-sight geometry, using 91.81% fewer reference-candidate evaluations than exhaustive scoring. In fixed-reference replay with a six-query cap, proposer-scaled anchored bounds raised first-action certificate availability from 36.25% to 54.69% and reduced mean queries per state by 13.54% relative to unit-scale anchored bounds. A complete ground-hosted pipeline processes 2,685 self-collected 20-megapixel unmanned aerial vehicle (UAV) images from seven DJI Mavic 3M routes. Context-guided admission and feedback retain all eight independently supported target confirmations with 76.05% fewer processed images and 70.02% less accumulated active processing service than uncapped all-frame processing; feedback saves another 5.17% of images relative to static context. The studies connect budgeted action selection with evidence-driven processing of recorded flight imagery.

## Seeing Beyond the Obvious: Complementary Semantic Guidance for Salient Single-Positive Multi-Label Learning

DevFeed: [Seeing Beyond the Obvious: Complementary Semantic Guidance for Salient Single-Positive Multi-Label Learning](<https://devfeed.tech/articles/seeing-beyond-the-obvious-complementary-semantic-guidance-for-salient-single-positive-multi-label-learning-145124.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25986>)

Author: Tong Jin, Meng-Long Wang, Xingyu Zhao, Sheng-Jun Huang

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

Content type: article

Language: en

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

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

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [framework](<https://devfeed.tech/tags/framework.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [prototypes](<https://devfeed.tech/tags/prototypes.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [support](<https://devfeed.tech/tags/support.md>), [target](<https://devfeed.tech/tags/target.md>)

### AI overview

Salient Single-Positive Multi-Label Learning records only each image's most salient positive label, so prototypes built from observed positives may miss the visual diversity of unlabeled positives. CoST supplements those Salient Prototypes with class-wise Coverage Prototypes: it selects semantically relevant candidates among unknown classes using task-learned category information and image-text correspondence, then aggregates them by class. A ranking-based selective refinement step strengthens soft targets only for classes with stronger Coverage Prototype support, leaving other base soft targets unchanged. The abstract reports strong gains over existing baselines across multiple benchmarks, but gives no benchmark names or quantitative results.

### Source excerpt

arXiv:2611.25986v1 Announce Type: new Abstract: Salient Single-Positive Multi-Label Learning (SalSPML) assigns each image its most salient positive label, leaving other classes unlabeled. Existing methods construct class-level Salient Prototypes from observed positives to guide the recognition of unobserved classes. However, since salient annotations favor visually prominent instances, these prototypes may not fully capture the visual diversity of hidden positives, resulting in insufficient positive supervision. To address this limitation, we propose CoST, a Coverage-guided Complementary Soft-Target Refinement framework that supplements Salient Prototypes with complementary class-semantic information. Specifically, CoST identifies semantically relevant candidates from unknown classes by leveraging task-learned category information and image-text semantic correspondence. The selected candidates are then aggregated into class-wise Coverage Prototypes to complement the semantic representations provided by Salient Prototypes. Furthermore, we introduce a ranking-based selective refinement strategy that identifies classes receiving stronger semantic support from Coverage Prototypes and selectively enhances their soft targets while preserving the base soft targets for the rest. Experiments on multiple benchmarks demonstrate the effectiveness of CoST, with strong performance gains over existing baselines.

## Visual Jev: Accurate and Efficient Decisions from Shared Visual Context

DevFeed: [Visual Jev: Accurate and Efficient Decisions from Shared Visual Context](<https://devfeed.tech/articles/visual-jev-accurate-and-efficient-decisions-from-shared-visual-context-144932.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.25845>)

Author: Guanxu Yu, Yuhang Yao

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

Content type: article

Language: en

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

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

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [apis](<https://devfeed.tech/tags/apis.md>), [applications](<https://devfeed.tech/tags/applications.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [caching](<https://devfeed.tech/tags/caching.md>), [candidate](<https://devfeed.tech/tags/candidate.md>), [choice](<https://devfeed.tech/tags/choice.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-model](<https://devfeed.tech/tags/decision-model.md>), [discrimination](<https://devfeed.tech/tags/discrimination.md>), [engine](<https://devfeed.tech/tags/engine.md>), [error](<https://devfeed.tech/tags/error.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [full](<https://devfeed.tech/tags/full.md>), [hosted](<https://devfeed.tech/tags/hosted.md>), [image](<https://devfeed.tech/tags/image.md>), [independent](<https://devfeed.tech/tags/independent.md>), [jev](<https://devfeed.tech/tags/jev.md>)

### AI overview

Visual Jev combines candidate readout from a language model head, answer-supervised post-training, and independent question branches over a shared visual prefix to answer multiple closed-choice questions about one image. Across held-out images from four benchmarks, task fine-tuning raises a 4B model's macro accuracy from 83.4% to 88.5% and error-discrimination AUROC from 0.834 to 0.890. Its accuracy exceeds the hosted Jev and OpenAI Decisions APIs by 2.77 and 5.06 percentage points, respectively, and it reports the lowest NLL. Reliability remains limited: fixed confidence thresholds exceed target error rates, and reordering options changes 17% of accept-or-review decisions on SNLI-VE. At 32 questions per image on one RTX 5090, shared-prefix inference cuts amortized time per question from 20.5 to 5.6 ms (3.7x faster than batched full sequences); engine-level prefix caching uses 24.3% of the KV memory of the custom shared-prefix path.

### Source excerpt

arXiv:2609.25845v2 Announce Type: replace-cross Abstract: Applications increasingly ask multiple closed-choice questions about the same image, requiring accurate probabilities and efficient inference. We present Visual Jev, a visual decision model combining LM-head candidate readout, answer-supervised post-training, and independent question branches over a shared visual prefix. On held-out test images from four benchmarks, task SFT raises the 4B model's macro accuracy from 83.4% to 88.5% and error-discrimination AUROC from 0.834 to 0.890. Its macro accuracy exceeds the hosted Jev and OpenAI Decisions APIs by 2.77 and 5.06 percentage points, respectively, with the lowest NLL. We further show that better accuracy and calibration do not ensure reliable decisions. Fixed confidence thresholds exceed target error rates, and simply reordering options changes 17% of the model's accept-or-review decisions on SNLI-VE. At 32 questions per image, shared-prefix inference reduces amortized time per question from 20.5 to 5.6 ms, a 3.7x speedup over batched full sequences on one RTX 5090. Engine-level prefix caching reduces KV memory to 24.3% of that used by our custom shared-prefix path.

## 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.

## A Wolf in Sheep's Pixels: Visual Camouflage Attacks via HDR Gain Maps

DevFeed: [A Wolf in Sheep's Pixels: Visual Camouflage Attacks via HDR Gain Maps](<https://devfeed.tech/articles/a-wolf-in-sheep-s-pixels-visual-camouflage-attacks-via-hdr-gain-maps-145517.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25469>)

Author: Qi Shen, Yujia Gong, Yue Zhao, Tong Liu

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 processing](<https://devfeed.tech/topics/image-processing.md>), [Image](<https://devfeed.tech/topics/image.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>)

Tags: [attacks](<https://devfeed.tech/tags/attacks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [exploits](<https://devfeed.tech/tags/exploits.md>), [hdr](<https://devfeed.tech/tags/hdr.md>), [maps](<https://devfeed.tech/tags/maps.md>), [processing](<https://devfeed.tech/tags/processing.md>), [sdr](<https://devfeed.tech/tags/sdr.md>)

### AI overview

DRJanus exploits the difference between SDR image processing and HDR display: automated systems may inspect an SDR base while viewers see a reconstruction that also uses an auxiliary gain map. It embeds two independently chosen color images in one JPEG without querying or optimizing against the target model, preserving the SDR base exactly and achieving an average HDR reconstruction PSNR of 43.03 dB across 400 images. In tests, it evaded all six commercial moderation services and nine vision-language models on a 100-image sexual-content benchmark. Across five agents, tested on 120 task cases per threat setting, attack success ranged from 31.67% to 100% for moderation evasion and 95% to 100% for task manipulation. The authors also explore cross-view consistency checks as a mitigation; the supplied abstract does not report their effectiveness.

### Source excerpt

arXiv:2611.25469v1 Announce Type: cross Abstract: An image can pass automated safety checks while showing harmful content to its human viewer. We introduce DRJanus, a visual camouflage attack that exploits the gap between standard dynamic range (SDR) processing and high dynamic range (HDR) display. Automated systems often read only an image's SDR base, whereas HDR viewers reconstruct its appearance using an auxiliary gain map. DRJanus inverts this reconstruction to embed two independently chosen color images in a single JPEG, without querying or optimizing against the target model. It preserves the chosen SDR base exactly and reconstructs HDR targets at an average PSNR of 43.03 dB across 400 images. On a benchmark of 100 sexual-content images, DRJanus evades detection by all six tested commercial moderation services and nine vision-language models. Across five agents, each evaluated on 120 task cases per threat setting, attack success ranges from 31.67% to 100% for moderation evasion and from 95% to 100% for task manipulation. We also explore cross-view consistency checks as a mitigation. These findings expose a gap in visual trust: securing what a machine reads does not secure what a user sees. A demo is available at https://qshen0629.github.io/DRJanus/

## VisualJevBench: A Benchmark and Black-Box Attacks for Visual Typed Decision Models

DevFeed: [VisualJevBench: A Benchmark and Black-Box Attacks for Visual Typed Decision Models](<https://devfeed.tech/articles/visualjevbench-a-benchmark-and-black-box-attacks-for-visual-typed-decision-models-146031.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25435>)

Author: Li Zeng, Yeqi Zeng, Hengkai Liang, Shiguo Wang, Meng Xie, Zeyu Ye, Jinheng Zhang, Xianlong Wang, Ziqi Zhou, Hangtao Zhang

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

Content type: article

Language: en

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

Topics: [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [asr](<https://devfeed.tech/tags/asr.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [black-box](<https://devfeed.tech/tags/black-box.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [geometric-transformations](<https://devfeed.tech/tags/geometric-transformations.md>), [image](<https://devfeed.tech/tags/image.md>), [search](<https://devfeed.tech/tags/search.md>), [selection](<https://devfeed.tech/tags/selection.md>), [spoofing](<https://devfeed.tech/tags/spoofing.md>), [transformation](<https://devfeed.tech/tags/transformation.md>)

### AI overview

VisualJevBench evaluates adversarial robustness in Visual Jev using 800 images and 3,200 questions across eight scenarios and four attack surfaces: typographic manipulation, visual evidence spoofing, target selection interference, and geometric transformation. Its Adaptive Black-Box Parameter Search (ABPS) uses typed-output feedback to find image-specific and universal manipulations; universal attacks can transfer to unseen images and tasks in new scenarios without further optimization. Experiments on jev-1.14.0 report up to 69.6% attack success for image-specific attacks, 33.15% average success for universal attacks on unseen images, and 40.09% average cross-scenario transfer success for geometric transformations.

### Source excerpt

arXiv:2611.25435v1 Announce Type: new Abstract: Typed decision models (TDMs) return structured decisions instead of generating free-text responses, enabling fast and cheap decisions in real-world applications. Recent support for image inputs extends Jev, a representative TDM, to visual decision-making. We refer to this setting as Visual Jev. However, red teaming of Visual Jev leaves two gaps: a systematic evaluation of direct image manipulations is lacking, and universal visual attacks remain underexplored. To address these gaps, we introduce VisualJevBench, a benchmark for evaluating the adversarial robustness of Visual Jev. It comprises 800 images and 3,200 questions across eight scenarios and four visual attack surfaces: typographic manipulation, visual evidence spoofing, target selection interference, and geometric transformation. We also introduce Adaptive Black-Box Parameter Search (ABPS), a lightweight framework that uses typed-output feedback to find effective image manipulations. ABPS supports both image-specific attacks and universal attacks that transfer to unseen images and tasks in new scenarios without further optimization. Extensive experiments on jev-1.14.0 show that image-specific attacks achieve an attack success rate (ASR) of up to 69.6%, while universal attacks achieve an average ASR of 33.15% on unseen images. Geometric transformations achieve an average ASR of 40.09% in cross-scenario transfer.

## Automating the Expert Eye: A System-Agnostic Deep Learning Framework for Rare Event Discovery in Imbalanced Force Spectroscopy

DevFeed: [Automating the Expert Eye: A System-Agnostic Deep Learning Framework for Rare Event Discovery in Imbalanced Force Spectroscopy](<https://devfeed.tech/articles/automating-the-expert-eye-a-system-agnostic-deep-learning-framework-for-rare-event-discovery-in-imbalanced-force-spectroscopy-144903.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.09541>)

Author: Jorge Rodriguez-Ramos

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

Content type: article

Language: en

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

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Image](<https://devfeed.tech/topics/image.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>)

Tags: [2d](<https://devfeed.tech/tags/2d.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [grad](<https://devfeed.tech/tags/grad.md>), [manual-review](<https://devfeed.tech/tags/manual-review.md>), [notebook](<https://devfeed.tech/tags/notebook.md>), [open-source-software](<https://devfeed.tech/tags/open-source-software.md>), [physics-app-ph](<https://devfeed.tech/tags/physics-app-ph.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [python](<https://devfeed.tech/tags/python.md>), [spectroscopy](<https://devfeed.tech/tags/spectroscopy.md>), [visual-inspection](<https://devfeed.tech/tags/visual-inspection.md>)

### AI overview

The workflow uses 2D images of force-extension curves and a modified ResNet18 trained with focal loss to screen severely imbalanced SMFS datasets without system-specific physical priors. In a held-out set of 970 curves with 13 target P₂ events (1.34% prevalence), it detected 12 events (92.31% recall) and correctly rejected 880 of 957 negative traces (91.95% specificity), reducing manual review to 89 flagged curves. Grad-CAM provides a qualitative visual reference for regions informing predictions. The open-source Python pipeline includes an executable Google Colab notebook and does not require dedicated local GPU hardware. Results are reported for the Ruminococcus champanellensis XMod-Doc/Coh complex.

### Source excerpt

arXiv:2606.09541v2 Announce Type: replace-cross Abstract: Single-molecule force spectroscopy (SMFS) probes biomolecular mechanics at the single-molecule level, but high-throughput acquisition of force-extension curves creates a data processing bottleneck. Identifying rare specific unbinding events among thousands of noise-dominated traces still relies largely on manual visual inspection. Here, we present a deep learning workflow for the preliminary screening of severely imbalanced SMFS datasets. Using 2D image representations of force-extension curves without system-specific physical priors, we fine-tuned a modified ResNet18 architecture trained with focal loss and evaluated it on the mechanical unfolding pathways of the Ruminococcus champanellensis XMod-Doc/Coh complex. On a held-out test set with a 1.34% target prevalence (13 positive P_2 events among 970 curves), the model achieved 92.31% recall (12 of 13 events) and 91.95% specificity (880 of 957 negative traces), automatically discarding 90.82% of the dataset and reducing manual review from 970 to 89 flagged curves. We also integrated Gradient-weighted Class Activation Mapping (Grad-CAM) to provide a qualitative visual reference of the curve regions driving each prediction. The complete Python pipeline is released as open-source software with an executable Google Colab notebook, enabling reproducible SMFS screening without dedicated local GPU hardware.

## Big tech is already building datacentres in Australia. Why is Labor so desperate to give them loopholes?

DevFeed: [Big tech is already building datacentres in Australia. Why is Labor so desperate to give them loopholes?](<https://devfeed.tech/articles/big-tech-is-already-building-datacentres-in-australia-why-is-labor-so-desperate-to-give-them-loopholes-144833.md>)

Original publisher: [Read original article](<https://www.theguardian.com/technology/commentisfree/2026/nov/20/big-tech-is-already-building-datacentres-in-australia-why-is-labor-desperate-to-give-them-loopholes>)

Author: Sarah Hanson-Young

Published: 2026-11-20T02:00:18Z

Content type: opinion

Language: en

Sources: [The Guardian | Technology](<https://devfeed.tech/sources/the-guardian-technology.md>)

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

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-artificial-intelligence](<https://devfeed.tech/tags/ai-artificial-intelligence.md>), [ai-artificial-intelligence-anthony-albanese-intellectual-property-australia-news-technology](<https://devfeed.tech/tags/ai-artificial-intelligence-anthony-albanese-intellectual-property-australia-news-technology.md>), [ai-boom](<https://devfeed.tech/tags/ai-boom.md>), [ai-companies](<https://devfeed.tech/tags/ai-companies.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-slop](<https://devfeed.tech/tags/ai-slop.md>), [anthony-albanese](<https://devfeed.tech/tags/anthony-albanese.md>), [art](<https://devfeed.tech/tags/art.md>), [australia](<https://devfeed.tech/tags/australia.md>), [australia-news](<https://devfeed.tech/tags/australia-news.md>), [australian-music](<https://devfeed.tech/tags/australian-music.md>), [authors](<https://devfeed.tech/tags/authors.md>), [backdoor](<https://devfeed.tech/tags/backdoor.md>), [big-tech](<https://devfeed.tech/tags/big-tech.md>), [books](<https://devfeed.tech/tags/books.md>), [consent](<https://devfeed.tech/tags/consent.md>), [datacentres](<https://devfeed.tech/tags/datacentres.md>), [global](<https://devfeed.tech/tags/global.md>), [government](<https://devfeed.tech/tags/government.md>), [intellectual-property](<https://devfeed.tech/tags/intellectual-property.md>), [journalism](<https://devfeed.tech/tags/journalism.md>), [labor](<https://devfeed.tech/tags/labor.md>), [music](<https://devfeed.tech/tags/music.md>), [publishing](<https://devfeed.tech/tags/publishing.md>), [technology](<https://devfeed.tech/tags/technology.md>)

### AI overview

Sarah Hanson-Young argues that Labor should not create copyright loopholes to attract AI companies, since big tech is already building datacentres in Australia. She says the proposed bargain would give companies access to Australian creative works for model training without consent or payment, risking creators' livelihoods and weakening protections beyond Australia. She calls for laws that guarantee consent, credit and compensation, and warns against an opt-out system that leaves creators and small newsrooms to enforce their rights themselves. The piece presents this as an argument, not independent evidence that the government is pursuing a specific loophole.

### Source excerpt

If the government bends to AI companies, artists, creatives and journalists will be the sacrificial lamb - and Australia will become a global pariah Get our breaking news email, free app or daily news podcast Right now, the prime minister faces a choice. Does he stand with Jimmy Barnes and the Working Class Man or does he stand with Big AI? This week, some of the biggest names in Australian music, publishing, journalism and art have thrown down the gauntlet to the government. From Paul Kelly to Anna Funder and Peter Garrett, household names and Australian icons are all singing from the same song sheet. Continue reading...

## Apache Iceberg Integrates FILE Type for Images and Audio Into Next Specification: Gap Remains Between Google's Announcement and Implementation Status

DevFeed: [Apache Iceberg Integrates FILE Type for Images and Audio Into Next Specification: Gap Remains Between Google's Announcement and Implementation Status](<https://devfeed.tech/articles/apache-iceberg-integrates-file-type-for-images-and-audio-into-next-specification-gap-remains-between-google-s-announcement-and-implementation-status-144635.md>)

Original publisher: [Read original article](<https://joho-todai.com/en/apache-iceberg-file-type-image-audio-integration/>)

Author: Toru Misaki

Published: 2026-11-19T23:53:13Z

Content type: article

Language: en

Sources: [Joho no Todai](<https://devfeed.tech/sources/joho-no-todai.md>)

Topics: [Apache Iceberg](<https://devfeed.tech/topics/apache-iceberg.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [Image](<https://devfeed.tech/topics/image.md>), [Apache Flink](<https://devfeed.tech/topics/apache-flink.md>), [Apache Spark](<https://devfeed.tech/topics/spark.md>)

Tags: [apache-iceberg](<https://devfeed.tech/tags/apache-iceberg.md>), [audio](<https://devfeed.tech/tags/audio.md>), [file](<https://devfeed.tech/tags/file.md>), [google](<https://devfeed.tech/tags/google.md>), [images](<https://devfeed.tech/tags/images.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [specification](<https://devfeed.tech/tags/specification.md>)

### AI overview

Apache Iceberg's FILE type standardizes references to images, audio, and documents as table values, with fields for uri, byte range, MIME type, checksum, and optional inline data. Subfield statistics may help engines filter data by content type. This could reduce reliance on engine-specific file handling and auxiliary metadata, but it does not guarantee that referenced files exist or manage their ownership, access, deletion, or relocation; readers must compare checksums to detect changes. The specification text was merged into Iceberg's main branch, but v4 remains under development and has not been formally adopted. An initial Java API implementation is merged; serialization, Avro/Parquet/ORC support, Spark and Flink support, and other work remain. The excerpt therefore describes a developing standard, not established cross-engine interoperability.

### Source excerpt

The Apache Iceberg FILE type, introduced by Google on November 19, describes images, audio, and documents as typed table data. The specification has been merged into the main branch, but v4 has not yet been formally adopted and processing-engine implementation remains at an early stage.

[Next page](<https://devfeed.tech/topics/image.md?cursor=WyIyMDI2LTExLTE5VDIzOjUzOjEzKzAwOjAwIiwgIjk5NjhjMDQxLWIxODQtNGMxNC05YmY3LTgxNjRiMTYwMmJiYiJd>)