Tootfinder

Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments
Xuan Wang, Siyuan Liang, Zhe Liu, Yi Yu, Yuliang Lu, Xiaochun Cao, Ee-Chien Chang
https://arxiv.org/abs/2506.13205

Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments
With the growing integration of vision-language models (VLMs), mobile agents are now widely used for tasks like UI automation and camera-based user assistance. These agents are often fine-tuned on limited user-generated datasets, leaving them vulnerable to covert threats during the training process. In this work we present GHOST, the first clean-label backdoor attack specifically designed for mobile agents built upon VLMs. Our method manipulates only the visual inputs of a portion of the traini…

FEWSim: A Visual Analytic Framework for Exploring the Nexus of Food-Energy-Water Simulations
Fan Lei, David A. Sampson, Jiayi Hong, Yuxin Ma, Giuseppe Mascaro, Dave White, Rimjhim Agarwal, Ross Maciejewski
https://arxiv.org/abs/2506.14056

FEWSim: A Visual Analytic Framework for Exploring the Nexus of Food-Energy-Water Simulations
The interdependencies of food, energy, and water (FEW) systems create a nexus opportunity to explore the strengths and vulnerabilities of individual and cross-sector interactions within FEW systems. However, the variables quantifying nexus interactions are hard to observe, which hinders the cross-sector analysis. To overcome such challenges, we present FEWSim, a visual analytics framework designed to support domain experts in exploring and interpreting simulation results from a coupled FEW mode…

#Windows11's new #StickyNotes app (a thinly disguised #OneNote) is fucking annoying. Since it is so-called "smart", and it attempts to provide context around the "source" of your note, its window is…

Narrate2Nav: Real-Time Visual Navigation with Implicit Language Reasoning in Human-Centric Environments
Amirreza Payandeh, Anuj Pokhrel, Daeun Song, Marcos Zampieri, Xuesu Xiao
https://arxiv.org/abs/2506.14233

Narrate2Nav: Real-Time Visual Navigation with Implicit Language Reasoning in Human-Centric Environments
Large Vision-Language Models (VLMs) have demonstrated potential in enhancing mobile robot navigation in human-centric environments by understanding contextual cues, human intentions, and social dynamics while exhibiting reasoning capabilities. However, their computational complexity and limited sensitivity to continuous numerical data impede real-time performance and precise motion control. To this end, we propose Narrate2Nav, a novel real-time vision-action model that leverages a novel self-su…

ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models
Sibo Dong, Ismail Shaheen, Maggie Shen, Rupayan Mallick, Sarah Adel Bargal
https://arxiv.org/abs/2506.12198

ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models
Text-to-image diffusion models have achieved remarkable success, yet generating coherent image sequences for visual storytelling remains challenging. A key challenge is effectively leveraging all previous text-image pairs, referred to as history text-image pairs, which provide contextual information for maintaining consistency across frames. Existing auto-regressive methods condition on all past image-text pairs but require extensive training, while training-free subject-specific approaches ens…

XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation
Ke Wang, Bo Pan, Yingchaojie Feng, Yuwei Wu, Jieyi Chen, Minfeng Zhu, Wei Chen
https://arxiv.org/abs/2506.13782

XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation
Graph-based Retrieval-Augmented Generation (RAG) has shown great capability in enhancing Large Language Model (LLM)'s answer with an external knowledge base. Compared to traditional RAG, it introduces a graph as an intermediate representation to capture better structured relational knowledge in the corpus, elevating the precision and comprehensiveness of generation results. However, developers usually face challenges in analyzing the effectiveness of GraphRAG on their dataset due to GraphRAG's …

An Empirical Study of Bugs in Data Visualization Libraries
Weiqi Lu, Yongqiang Tian, Xiaohan Zhong, Haoyang Ma, Zhenyang Xu, Shing-Chi Cheung, Chengnian Sun
https://arxiv.org/abs/2506.15084

An Empirical Study of Bugs in Data Visualization Libraries
Data visualization (DataViz) libraries play a crucial role in presentation, data analysis, and application development, underscoring the importance of their accuracy in transforming data into visual representations. Incorrect visualizations can adversely impact user experience, distort information conveyance, and influence user perception and decision-making processes. Visual bugs in these libraries can be particularly insidious as they may not cause obvious errors like crashes, but instead mis…

A post from the archive 📫:
Find the address of an object in Visual Studio
https://www.poppastring.com/blog/find-the-address-of-an-object-in-visual-studio

Oh hey, it's #ScreenshotSaturday , here's the latest mockup from the video game adaptation of Battle of Tarot I'm working on with some lovely people.
Everything is still a work-in-progress and not final at all, but trying to get the visual style nailed down.
#GameDev

Audio-Visual Driven Compression for Low-Bitrate Talking Head Videos
Riku Takahashi, Ryugo Morita, Jinjia Zhou
https://arxiv.org/abs/2506.13419 https://

Audio-Visual Driven Compression for Low-Bitrate Talking Head Videos
Talking head video compression has advanced with neural rendering and keypoint-based methods, but challenges remain, especially at low bit rates, including handling large head movements, suboptimal lip synchronization, and distorted facial reconstructions. To address these problems, we propose a novel audio-visual driven video codec that integrates compact 3D motion features and audio signals. This approach robustly models significant head rotations and aligns lip movements with speech, improvi…

Navigating High-Dimensional Backstage: A Guide for Exploring Literature for the Reliable Use of Dimensionality Reduction
Hyeon Jeon, Hyunwook Lee, Yun-Hsin Kuo, Taehyun Yang, Daniel Archambault, Sungahn Ko, Takanori Fujiwara, Kwan-Liu Ma, Jinwook Seo
https://arxiv.org/abs/2506.14820

Navigating High-Dimensional Backstage: A Guide for Exploring Literature for the Reliable Use of Dimensionality Reduction
Visual analytics using dimensionality reduction (DR) can easily be unreliable for various reasons, e.g., inherent distortions in representing the original data. The literature has thus proposed a wide range of methodologies to make DR-based visual analytics reliable. However, the diversity and extensiveness of the literature can leave novice analysts and researchers uncertain about where to begin and proceed. To address this problem, we propose a guide for reading papers for reliable visual ana…

Apple says Visual Intelligence will now be able to search on-screen content in addition to analyzing real world objects, expanding on camera search (Tim Hardwick/MacRumors)
https://www.macrumors.com/2025/06/09/ios-26-visual-intellige…

iOS 26: Visual Intelligence Now Searches On-Screen Content
Apple has announced a major Visual Intelligence update at WWDC 2025, enabling users to search and take action on anything displayed across their...

KI bei Apple: Sorry wegen Siri, bessere Visual Intelligence, mehr ChatGPT
Apple hat auf der WWDC 2025 Details zur verschobenen Siri genannt. Außerdem gibt es mehr Visual Intelligence und ChatGPT-Integration.

GHAR: GeoPose-based Handheld Augmented Reality for Architectural Positioning, Manipulation and Visual Exploration
Sabahat Israr, Dawar Khan, Zhanglin Cheng, Mukhtaj Khan, Kiyoshi Kiyokawa
https://arxiv.org/abs/2506.14414

GHAR: GeoPose-based Handheld Augmented Reality for Architectural Positioning, Manipulation and Visual Exploration
Handheld Augmented Reality (HAR) is revolutionizing the civil infrastructure application domain. The current trend in HAR relies on marker tracking technology. However, marker-based systems have several limitations, such as difficulty in use and installation, sensitivity to light, and marker design. In this paper, we propose a markerless HAR framework with GeoPose-based tracking. We use different gestures for manipulation and achieve 7 DOF (3 DOF each for translation and rotation, and 1 DOF for…

Series B, Episode 09 - Countdown
VETNOR: All right, come with me, we're searching the next level.
PROVINE: Right, sir.
[Teleport section. Avon and Grant are suited up]
AVON: You adjust the temperature with this [Points to knob on suit] You all set?
https://blake.torpidity.net/m/209/356

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

If you are working in #word with a reference manager like #zotero or #mendeley, you probably get the Error 4707 since five days.
Here's how to fix it:

Office Hacks - Livia's Notes
Office Hacks #typ/Cheatsheet #tool/macos Shortcuts Word - Update all fields macOS: select all, press F9 (fn + F9 respectively) Word - Show/Hide invisible characters: ⌘ + 8 Roll Back to previous vers…

What's in the Box? Reasoning about Unseen Objects from Multimodal Cues
Lance Ying, Daniel Xu, Alicia Zhang, Katherine M. Collins, Max H. Siegel, Joshua B. Tenenbaum
https://arxiv.org/abs/2506.14212

What's in the Box? Reasoning about Unseen Objects from Multimodal Cues
People regularly make inferences about objects in the world that they cannot see by flexibly integrating information from multiple sources: auditory and visual cues, language, and our prior beliefs and knowledge about the scene. How are we able to so flexibly integrate many sources of information to make sense of the world around us, even if we have no direct knowledge? In this work, we propose a neurosymbolic model that uses neural networks to parse open-ended multimodal inputs and then applie…

GRaD-Nav : Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics
Qianzhong Chen, Naixiang Gao, Suning Huang, JunEn Low, Timothy Chen, Jiankai Sun, Mac Schwager
https://arxiv.org/abs/2506.14009

GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics
Autonomous drones capable of interpreting and executing high-level language instructions in unstructured environments remain a long-standing goal. Yet existing approaches are constrained by their dependence on hand-crafted skills, extensive parameter tuning, or computationally intensive models unsuitable for onboard use. We introduce GRaD-Nav++, a lightweight Vision-Language-Action (VLA) framework that runs fully onboard and follows natural-language commands in real time. Our policy is trained …

Feature Complementation Architecture for Visual Place Recognition
Weiwei Wang, Meijia Wang, Haoyi Wang, Wenqiang Guo, Jiapan Guo, Changming Sun, Lingkun Ma, Weichuan Zhang
https://arxiv.org/abs/2506.12401

Feature Complementation Architecture for Visual Place Recognition
Visual place recognition (VPR) plays a crucial role in robotic localization and navigation. The key challenge lies in constructing feature representations that are robust to environmental changes. Existing methods typically adopt convolutional neural networks (CNNs) or vision Transformers (ViTs) as feature extractors. However, these architectures excel in different aspects -- CNNs are effective at capturing local details. At the same time, ViTs are better suited for modeling global context, mak…

Sigh, Visual Studio Installer has the feature to "rollback" to a previous version with just one click. But only for one step back. (For me, it was from 17.14.5 to 17.14.2.) When you have done that, it doesn't offer any further rollbacks. Irritating. #VisualStudio
Edit: But oh well, I figured out another way to work around my problem.

Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models
Jinming Wen, Xinyi Wu, Shuai Zhao, Yanhao Jia, Yuwen Li
https://arxiv.org/abs/2506.11521

Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models
Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity of high-quality audio-visual training data and computational resources necessitates the utilization of third-party data and open-source MLLMs, a trend that is increasingly observed in contemporary research. This prosperity masks significant security risks. E…

D\'ej\`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse
Jinwoo Hwang, Daeun Kim, Sangyeop Lee, Yoonsung Kim, Guseul Heo, Hojoon Kim, Yunseok Jeong, Tadiwos Meaza, Eunhyeok Park, Jeongseob Ahn, Jongse Park
https://arxiv.org/abs/2506.14107

Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse
Recently, Video-Language Models (VideoLMs) have demonstrated remarkable capabilities, offering significant potential for flexible and powerful video query systems. These models typically rely on Vision Transformers (ViTs), which process video frames individually to extract visual embeddings. However, generating embeddings for large-scale videos requires ViT inferencing across numerous frames, posing a major hurdle to real-world deployment and necessitating solutions for integration into scalabl…

The neurological basis for non-visual illustration https://intellectdiscover.com/content/journals/10.1386/jill_00117_7 "this article poses the question of whether there is a theoretical precedent for creating visual imagery in the minds of blind peopl…

Replaced article(s) found for astro-ph.HE. https://arxiv.org/list/astro-ph.HE/new
[1/1]:
- Exploring blazars through sonification. Visual and auditory insights into multifrequency variability
Gustavo Magallanes-Guij\'on, Sergio Mendoza

ATK: Automatic Task-driven Keypoint Selection for Robust Policy Learning
Yunchu Zhang, Shubham Mittal, Zhengyu Zhang, Liyiming Ke, Siddhartha Srinivasa, Abhishek Gupta
https://arxiv.org/abs/2506.13867

ATK: Automatic Task-driven Keypoint Selection for Robust Policy Learning
Visuomotor policies often suffer from perceptual challenges, where visual differences between training and evaluation environments degrade policy performance. Policies relying on state estimations, like 6D pose, require task-specific tracking and are difficult to scale, while raw sensor-based policies may lack robustness to small visual disturbances.In this work, we leverage 2D keypoints - spatially consistent features in the image frame - as a flexible state representation for robust policy le…

Learning From the Past with Cascading Eligibility Traces
Tokiniaina Raharison Ralambomihanta, Ivan Anokhin, Roman Pogodin, Samira Ebrahimi Kahou, Jonathan Cornford, Blake Aaron Richards
https://arxiv.org/abs/2506.14598

Learning From the Past with Cascading Eligibility Traces
Animals often receive information about errors and rewards after a significant delay. For example, there is typically a delay of tens to hundreds of milliseconds between motor actions and visual feedback. The standard approach to handling delays in models of synaptic plasticity is to use eligibility traces. However, standard eligibility traces that decay exponentially mix together any events that happen during the delay, presenting a problem for any credit assignment signal that occurs with a s…

Series D, Episode 01 - Rescue
TARRANT: He will if Orac's working. Now come on. We're wasting time. [starts to climb]
[Dayna does not follow, but continues to explore the small room. A hatch slides open in the floor.]
DAYNA: I knew it. Tarrant.
https://blake.torpidity.net/m/401/422

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Omnidirectional Video Super-Resolution using Deep Learning
Arbind Agrahari Baniya, Tsz-Kwan Lee, Peter W. Eklund, Sunil Aryal
https://arxiv.org/abs/2506.14803

Omnidirectional Video Super-Resolution using Deep Learning
Omnidirectional Videos (or 360° videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360° videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution; however, these techniqu…

Visual metrics on boundaries of hyperbolic spaces
Emily Stark
https://arxiv.org/abs/2506.10108 https://arxiv.org/pdf/2506.10108

Visual metrics on boundaries of hyperbolic spaces
This is an expository article on visual metrics on boundaries of hyperbolic metric spaces. We discuss the construction of visual metrics, quasisymmetries and their invariants, Hausdorff and conformal dimension, and constructions and applications of Gromov's round trees. There is a focus on providing examples throughout. These notes are based on the material of a minicourse given by the author at the 2024 Riverside Workshop in Geometric Group Theory.

Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments
Xuan Wang, Siyuan Liang, Zhe Liu, Yi Yu, Yuliang Lu, Xiaochun Cao, Ee-Chien Chang
https://arxiv.org/abs/2506.13205

Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments
With the growing integration of vision-language models (VLMs), mobile agents are now widely used for tasks like UI automation and camera-based user assistance. These agents are often fine-tuned on limited user-generated datasets, leaving them vulnerable to covert threats during the training process. In this work we present GHOST, the first clean-label backdoor attack specifically designed for mobile agents built upon VLMs. Our method manipulates only the visual inputs of a portion of the traini…

Focusing on Students, not Machines: Grounded Question Generation and Automated Answer Grading
G\'er\^ome Meyer, Philip Breuer
https://arxiv.org/abs/2506.12066

Focusing on Students, not Machines: Grounded Question Generation and Automated Answer Grading
Digital technologies are increasingly used in education to reduce the workload of teachers and students. However, creating open-ended study or examination questions and grading their answers is still a tedious task. This thesis presents the foundation for a system that generates questions grounded in class materials and automatically grades student answers. It introduces a sophisticated method for chunking documents with a visual layout, specifically targeting PDF documents. This method enhance…

Just published 🚀: A Kind of Blue
#visualstudio

Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction
Wenxuan Wu, Shuai Wang, Xixin Wu, Helen Meng, Haizhou Li
https://arxiv.org/abs/2506.09792

Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction
Audio-visual target speaker extraction (AV-TSE) models primarily rely on target visual cues to isolate the target speaker's voice from others. We know that humans leverage linguistic knowledge, such as syntax and semantics, to support speech perception. Inspired by this, we explore the potential of pre-trained speech-language models (PSLMs) and pre-trained language models (PLMs) as auxiliary knowledge sources for AV-TSE. In this study, we propose incorporating the linguistic constraints from PS…

AMPLIFY: Actionless Motion Priors for Robot Learning from Videos
Jeremy A. Collins, Lor\'and Cheng, Kunal Aneja, Albert Wilcox, Benjamin Joffe, Animesh Garg
https://arxiv.org/abs/2506.14198

AMPLIFY: Actionless Motion Priors for Robot Learning from Videos
Action-labeled data for robotics is scarce and expensive, limiting the generalization of learned policies. In contrast, vast amounts of action-free video data are readily available, but translating these observations into effective policies remains a challenge. We introduce AMPLIFY, a novel framework that leverages large-scale video data by encoding visual dynamics into compact, discrete motion tokens derived from keypoint trajectories. Our modular approach separates visual motion prediction fr…

Breaking the Multi-Enhancement Bottleneck: Domain-Consistent Quality Enhancement for Compressed Images
Qunliang Xing, Mai Xu, Jing Yang, Shengxi Li
https://arxiv.org/abs/2506.14152

Breaking the Multi-Enhancement Bottleneck: Domain-Consistent Quality Enhancement for Compressed Images
Quality enhancement methods have been widely integrated into visual communication pipelines to mitigate artifacts in compressed images. Ideally, these quality enhancement methods should perform robustly when applied to images that have already undergone prior enhancement during transmission. We refer to this scenario as multi-enhancement, which generalizes the well-known multi-generation scenario of image compression. Unfortunately, current quality enhancement methods suffer from severe degrada…

VGR: Visual Grounded Reasoning
Jiacong Wang, Zijiang Kang, Haochen Wang, Haiyong Jiang, Jiawen Li, Bohong Wu, Ya Wang, Jiao Ran, Xiao Liang, Chao Feng, Jun Xiao
https://arxiv.org/abs/2506.11991

VGR: Visual Grounded Reasoning
In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This narrow focus limits their ability to handle complex visual reasoning tasks that demand comprehensive understanding of image details. To address these limitations, this paper introduces VGR, a novel reasoning multimodal large language model (MLLM) with enhanced …

A Study on Speech Assessment with Visual Cues
Shafique Ahmed, Ryandhimas E. Zezario, Nasir Saleem, Amir Hussain, Hsin-Min Wang, Yu Tsao
https://arxiv.org/abs/2506.09549

A Study on Speech Assessment with Visual Cues
Non-intrusive assessment of speech quality and intelligibility is essential when clean reference signals are unavailable. In this work, we propose a multimodal framework that integrates audio features and visual cues to predict PESQ and STOI scores. It employs a dual-branch architecture, where spectral features are extracted using STFT, and visual embeddings are obtained via a visual encoder. These features are then fused and processed by a CNN-BLSTM with attention, followed by multi-task learn…

However if I towel dry in the shower before getting out, and I am drying my face and hair, I instantly lose visual reference since the towel covers my eyes. So now I only have two points in space unless I use one hand on the towel, and one hand on a grab bar. (3)

SkinCells: Sparse Skinning using Voronoi Cells
Egor Larionov, Igor Santesteban, Hsiao-yu Chen, Gene Lin, Philipp Herholz, Ryan Goldade, Ladislav Kavan, Doug Roble, Tuur Stuyck
https://arxiv.org/abs/2506.14714

SkinCells: Sparse Skinning using Voronoi Cells
For decades, efficient real-time skinning methods have played a crucial role in animating character rigs for visual effects and games. These methods remain a fundamental component of modern applications. However, animatable digital asset creation predominantly remains a manual process. Current automated tools often fall short of delivering the desired level of quality for intricate and complex geometries, requiring manual touch-ups. We propose a fully automatic and robust method for generating …

A post from the archive 📫:
Using Visual Studio to search objects in a memory dump
https://www.poppastring.com/blog/using-visual-studio-to-search-objects-in-a-memory-dump

Insights Informed Generative AI for Design: Incorporating Real-world Data for Text-to-Image Output
Richa Gupta, Alexander Htet Kyaw
https://arxiv.org/abs/2506.15008

Insights Informed Generative AI for Design: Incorporating Real-world Data for Text-to-Image Output
Generative AI, specifically text-to-image models, have revolutionized interior architectural design by enabling the rapid translation of conceptual ideas into visual representations from simple text prompts. While generative AI can produce visually appealing images they often lack actionable data for designers In this work, we propose a novel pipeline that integrates DALL-E 3 with a materials dataset to enrich AI-generated designs with sustainability metrics and material usage insights. After t…

Visual mental imagery and #aphantasia lesions map onto a convergent brain network https://www.medrxiv.org/content/10.1101/2025.05.23.25328072v1 by @…

Visual Mental Imagery and Aphantasia Lesions Map onto a Convergent Brain Network
Background Visual mental imagery, the ability to volitionally form perceptual representations without corresponding external stimuli, allows reliving of past events, solving problems and imagining the future. The absence of visual mental imagery, called aphantasia, has recently been recognized to occur in about 1% of the general population but the cause is uncertain. By studying rare cases of acquired aphantasia we can identify regions that when injured cause loss of visual mental imagery. Met…

Wow. Total surprise for me... this game looks amazing... & free to play for Xbox Game Pass!
✅ Clockwork Revolution: inXile on Time Travel, Visual Reactivity, that Foulmouthed Doll, and More — Exclusive Interview - Xbox Wire
https://news.xbox.com/en-us/2025/06/0…

Clockwork Revolution: inXile on Time Travel, Visual Reactivity, that Foulmouthed Doll, and More — Exclusive Interview - Xbox Wire
Clockwork Revolution’s stunning new trailer has a LOT to unwind. In this exclusive interview, inXile developers tell us how they’re crafting a reactive steampunk world, tailor-made for RPG players.

Binary Mixtures of Intelligent Active Brownian Particles with Visual Perception
Rajendra Singh Negi, Roland G. Winkler, Gerhard Gompper
https://arxiv.org/abs/2506.09698

Binary Mixtures of Intelligent Active Brownian Particles with Visual Perception
The collective properties of a binary mixture of A- and B-type self-steering particles endowed with visual perception are studied by computer simulations. Active Brownian particles are employed with an additional steering mechanism, which enables them to adjust their propulsion direction relative to the instantaneous positions of neighboring particles, depending on the species, either steering toward or away from them. Steering can be nonreciprocal between the A- and B-type particles. The under…

• 🔧 Extensible architecture via #PHP and #JavaScript plugins with lazy loading capabilities for performance
• 🎨 Visual #CMS functionality enabling live website content editing and drag & dr…

3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
Yuke Xing, Jiarui Wang, Peizhi Niu, Wenjie Huang, Guangtao Zhai, Yiling Xu
https://arxiv.org/abs/2506.14642

3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
3D Gaussian Splatting (3DGS) has emerged as a promising approach for novel view synthesis, offering real-time rendering with high visual fidelity. However, its substantial storage requirements present significant challenges for practical applications. While recent state-of-the-art (SOTA) 3DGS methods increasingly incorporate dedicated compression modules, there is a lack of a comprehensive framework to evaluate their perceptual impact. Therefore we present 3DGS-IEval-15K, the first large-scale …

Characterization of the Visual Binary TOI-6883AB and its dynamical implications for the planetary companion TOI-6883Ab
G. Conzo, F. Campos, F. Conti, I. Sharp
https://arxiv.org/abs/2506.08798

Characterization of the Visual Binary TOI-6883AB and its dynamical implications for the planetary companion TOI-6883Ab
We demonstrate that TOI-6883 is a physically bound visual binary system composed of two solar-type stars, TOI-6883A (TIC 393818343) and TOI-6883B (TIC 393818340), initially regarded as a single star hosting the exoplanet TOI-6883b. Gaia DR3 astrometry shows that both stars have nearly identical parallaxes 10.6 mas, consistent proper motions, and a projected separation of 616 AU, confirming their binary nature. Using astrometric and photometric data, we estimate the stellar masses, physical sepa…

ABC: Adaptive BayesNet Structure Learning for Computational Scalable Multi-task Image Compression
Yufeng Zhang, Wenrui Dai, Hang Yu, Shizhan Liu, Junhui Hou, Jianguo Li, Weiyao Lin
https://arxiv.org/abs/2506.15228

ABC: Adaptive BayesNet Structure Learning for Computational Scalable Multi-task Image Compression
Neural Image Compression (NIC) has revolutionized image compression with its superior rate-distortion performance and multi-task capabilities, supporting both human visual perception and machine vision tasks. However, its widespread adoption is hindered by substantial computational demands. While existing approaches attempt to address this challenge through module-specific optimizations or pre-defined complexity levels, they lack comprehensive control over computational complexity. We present A…

This https://arxiv.org/abs/2505.16933 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant in current multimodal approaches. Built upon LLaDA, a representative large language diffusion model, LLaDA-V incorporates a vision encoder and MLP connector that projects visual features into the language embedding space, enabling effective multimodal alignme…

DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models
Yunnong Chen, Shixian Ding, YingYing Zhang, Wenkai Chen, Jinzhou Du, Lingyun Sun, Liuqing Chen
https://arxiv.org/abs/2506.13663

DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models
Multimodal large language models (MLLMs) have streamlined front-end interface development by automating code generation. However, these models also introduce challenges in ensuring code quality. Existing approaches struggle to maintain both visual consistency and functional completeness in the generated components. Moreover, they lack mechanisms to assess the fidelity and correctness of the rendered pages. To address these issues, we propose DesignCoder, a novel hierarchical-aware and self-corr…

How Vox built a huge YouTube presence, becoming an incubator that invented its own visual language, as ex-staffers like Johnny Harris grow their own channels (Simon Owens/The Long Story with Simon Owens)
https://thelongstory.substack.com/p/why-the-best-jour…

Why the best journalists on YouTube are all former Vox employees
The company became a skunk works incubator that invented its own language of visual storytelling.

ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Yujun Wang, Jinhe Bi, Yunpu Ma, Soeren Pirk
https://arxiv.org/abs/2506.14766

ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Multimodal Large Language Model (MLLM) often suffer from hallucinations. They over-rely on partial cues and generate incorrect responses. Recently, methods like Visual Contrastive Decoding (VCD) and Instruction Contrastive Decoding (ICD) have been proposed to mitigate hallucinations by contrasting predictions from perturbed or negatively prefixed inputs against original outputs. In this work, we uncover that methods like VCD and ICD fundamentally influence internal attention dynamics of the mod…

#Blakes7 Series B, Episode 02 - Shadow
ZEN: Information. Main visual is available. [displays Space City on screen.]
VILA: So?
ZEN: You expressed a desire to see what it is like.
https://blake.torpidity.net/m/202…

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Foundation of Affective Computing and Interaction
Changzeng Fu
https://arxiv.org/abs/2506.15497 https://arxiv.org/pdf/2506.15497

Foundation of Affective Computing and Interaction
This book provides a comprehensive exploration of affective computing and human-computer interaction technologies. It begins with the historical development and basic concepts of human-computer interaction, delving into the technical frameworks and practical applications of emotional computing, visual interaction, voice interaction, brain-computer interfaces, physiological electrical signal analysis, and social robotics. The book covers a wide range of topics, including the psychological and ne…

Structured Graph Representations for Visual Narrative Reasoning: A Hierarchical Framework for Comics
Yi-Chun Chen
https://arxiv.org/abs/2506.10008 https://…

Structured Graph Representations for Visual Narrative Reasoning: A Hierarchical Framework for Comics
This paper presents a hierarchical knowledge graph framework for the structured understanding of visual narratives, focusing on multimodal media such as comics. The proposed method decomposes narrative content into multiple levels, from macro-level story arcs to fine-grained event segments. It represents them through integrated knowledge graphs that capture semantic, spatial, and temporal relationships. At the panel level, we construct multimodal graphs that link visual elements such as charact…

ViSAGe: Video-to-Spatial Audio Generation
Jaeyeon Kim, Heeseung Yun, Gunhee Kim
https://arxiv.org/abs/2506.12199 https://arxiv.org/pd…

ViSAGe: Video-to-Spatial Audio Generation
Spatial audio is essential for enhancing the immersiveness of audio-visual experiences, yet its production typically demands complex recording systems and specialized expertise. In this work, we address a novel problem of generating first-order ambisonics, a widely used spatial audio format, directly from silent videos. To support this task, we introduce YT-Ambigen, a dataset comprising 102K 5-second YouTube video clips paired with corresponding first-order ambisonics. We also propose new evalu…

In-Hand Object Pose Estimation via Visual-Tactile Fusion
Felix Nonnengie{\ss}er, Alap Kshirsagar, Boris Belousov, Jan Peters
https://arxiv.org/abs/2506.10787

In-Hand Object Pose Estimation via Visual-Tactile Fusion
Accurate in-hand pose estimation is crucial for robotic object manipulation, but visual occlusion remains a major challenge for vision-based approaches. This paper presents an approach to robotic in-hand object pose estimation, combining visual and tactile information to accurately determine the position and orientation of objects grasped by a robotic hand. We address the challenge of visual occlusion by fusing visual information from a wrist-mounted RGB-D camera with tactile information from v…

People keep making the same mistake, again and again and again and again forever, of thinking that it is syntax that makes software development hard.
Oh honey.
Re this from @mathaetaes:
https://infosec.exchange/@mathaetaes/114656764053846137
(P.S. Visual coding is actually really cool, and IMO an underexplored PL design space — but is very much coding, and very much tricky for the same reasons as any other kind of coding.)

ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies
Jinyan Yuan, Bangbang Yang, Keke Wang, Panwang Pan, Lin Ma, Xuehai Zhang, Xiao Liu, Zhaopeng Cui, Yuewen Ma
https://arxiv.org/abs/2506.14315

ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies
Automatic creation of 3D scenes for immersive VR presence has been a significant research focus for decades. However, existing methods often rely on either high-poly mesh modeling with post-hoc simplification or massive 3D Gaussians, resulting in a complex pipeline or limited visual realism. In this paper, we demonstrate that such exhaustive modeling is unnecessary for achieving compelling immersive experience. We introduce ImmerseGen, a novel agent-guided framework for compact and photorealist…

VisText-Mosquito: A Multimodal Dataset and Benchmark for AI-Based Mosquito Breeding Site Detection and Reasoning
Md. Adnanul Islam, Md. Faiyaz Abdullah Sayeedi, Md. Asaduzzaman Shuvo, Muhammad Ziaur Rahman, Shahanur Rahman Bappy, Raiyan Rahman, Swakkhar Shatabda
https://arxiv.org/abs/2506.14629

VisText-Mosquito: A Multimodal Dataset and Benchmark for AI-Based Mosquito Breeding Site Detection and Reasoning
Mosquito-borne diseases pose a major global health risk, requiring early detection and proactive control of breeding sites to prevent outbreaks. In this paper, we present VisText-Mosquito, a multimodal dataset that integrates visual and textual data to support automated detection, segmentation, and reasoning for mosquito breeding site analysis. The dataset includes 1,828 annotated images for object detection, 142 images for water surface segmentation, and natural language reasoning texts linked…

See What I Mean? CUE: A Cognitive Model of Understanding Explanations
Tobias Labarta, Nhi Hoang, Katharina Weitz, Wojciech Samek, Sebastian Lapuschkin, Leander Weber
https://arxiv.org/abs/2506.14775

See What I Mean? CUE: A Cognitive Model of Understanding Explanations
As machine learning systems increasingly inform critical decisions, the need for human-understandable explanations grows. Current evaluations of Explainable AI (XAI) often prioritize technical fidelity over cognitive accessibility which critically affects users, in particular those with visual impairments. We propose CUE, a model for Cognitive Understanding of Explanations, linking explanation properties to cognitive sub-processes: legibility (perception), readability (comprehension), and inter…

DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
Yitong Zhang, Jia Li, Liyi Cai, Ge Li
https://arxiv.org/abs/2506.09353

DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
Large Vision-Language Models (LVLMs) have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectively. To address these challenges, we propose Deep Aligned Visual Safety Prompt (DAVSP), which is built upon two key innovations. First, we introduce the Visual Safety Prompt, which appends a trainable p…

GAF: Gaussian Action Field as a Dvnamic World Model for Robotic Mlanipulation
Ying Chai, Litao Deng, Ruizhi Shao, Jiajun Zhang, Liangjun Xing, Hongwen Zhang, Yebin Liu
https://arxiv.org/abs/2506.14135

GAF: Gaussian Action Field as a Dvnamic World Model for Robotic Mlanipulation
Accurate action inference is critical for vision-based robotic manipulation. Existing approaches typically follow either a Vision-to-Action (V-A) paradigm, predicting actions directly from visual inputs, or a Vision-to-3D-to-Action (V-3D-A) paradigm, leveraging intermediate 3D representations. However, these methods often struggle with action inaccuracies due to the complexity and dynamic nature of manipulation scenes. In this paper, we propose a V-4D-A framework that enables direct action reas…

To ChatGPT: Brain implants in visual cortex such as Neuralink Blindsight cannot directly convey visual textures, shading and smooth surfaces, because simultaneously activating many electrodes above phosphene threshold would cause seizures. Any solutions? https://chatgpt.com/share/68469685-71c

ChatGPT - Neuralink Visual Limitations
Shared via ChatGPT

A novel visual data-based diagnostic approach for estimation of regime transition in pool boiling
Pranay Nirapure, Ayushman Singh, Srikanth Rangarajan, Bahgat Sammakia
https://arxiv.org/abs/2506.10832

A novel visual data-based diagnostic approach for estimation of regime transition in pool boiling
This study introduces a novel metric, the Index of Visual Similarity (IVS), to qualitatively characterize boiling heat transfer regimes using only visual data. The IVS is constructed by combining morphological similarity, through SIFT-based feature matching, with physical similarity, via vapor area estimation using Mask R-CNN. High-speed images of pool boiling on two distinct surfaces, polished copper and porous copper foam, are employed to demonstrate the generalizability of the approach. IVS …

We all keep our balance, our awareness of position in space, by analysing feedback we get from receivers in our skin and joints (proprioceptors) and from our visual assessment of our position in space. I am a below knee #amputee, so I have lost the position sensors in my foot, ankle, and leg. I gauge the location of my leg in space through my knee and secondarily, through my hip. 🧵

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
Ling Li, Yao Zhou, Yuxuan Liang, Fugee Tsung, Jiaheng Wei
https://arxiv.org/abs/2506.14674

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
Previous methods for image geo-localization have typically treated the task as either classification or retrieval, often relying on black-box decisions that lack interpretability. The rise of large vision-language models (LVLMs) has enabled a rethinking of geo-localization as a reasoning-driven task grounded in visual cues. However, two major challenges persist. On the data side, existing reasoning-focused datasets are primarily based on street-view imagery, offering limited scene diversity and…

UniDet-D: A Unified Dynamic Spectral Attention Model for Object Detection under Adverse Weathers
Yuantao Wang, Haowei Yang, Wei Zhang, Shijian Lu
https://arxiv.org/abs/2506.12324 …

UniDet-D: A Unified Dynamic Spectral Attention Model for Object Detection under Adverse Weathers
Real-world object detection is a challenging task where the captured images/videos often suffer from complex degradations due to various adverse weather conditions such as rain, fog, snow, low-light, etc. Despite extensive prior efforts, most existing methods are designed for one specific type of adverse weather with constraints of poor generalization, under-utilization of visual features while handling various image degradations. Leveraging a theoretical analysis on how critical visual details…

Video-Guided Text-to-Music Generation Using Public Domain Movie Collections
Haven Kim, Zachary Novack, Weihan Xu, Julian McAuley, Hao-Wen Dong
https://arxiv.org/abs/2506.12573

Video-Guided Text-to-Music Generation Using Public Domain Movie Collections
Despite recent advancements in music generation systems, their application in film production remains limited, as they struggle to capture the nuances of real-world filmmaking, where filmmakers consider multiple factors-such as visual content, dialogue, and emotional tone-when selecting or composing music for a scene. This limitation primarily stems from the absence of comprehensive datasets that integrate these elements. To address this gap, we introduce Open Screen Sound Library (OSSL), a dat…

Sparse Autoencoders Bridge The Deep Learning Model and The Brain
Ziming Mao, Jia Xu, Zeqi Zheng, Haofang Zheng, Dabing Sheng, Yaochu Jin, Guoyuan Yang
https://arxiv.org/abs/2506.11123

Sparse Autoencoders Bridge The Deep Learning Model and The Brain
We present SAE-BrainMap, a novel framework that directly aligns deep learning visual model representations with voxel-level fMRI responses using sparse autoencoders (SAEs). First, we train layer-wise SAEs on model activations and compute the correlations between SAE unit activations and cortical fMRI signals elicited by the same natural image stimuli with cosine similarity, revealing strong activation correspondence (maximum similarity up to 0.76). Depending on this alignment, we construct a vo…

This https://arxiv.org/abs/2310.17451 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings
Making neural visual generative models controllable by logical reasoning systems is promising for improving faithfulness, transparency, and generalizability. We propose the Abductive visual Generation (AbdGen) approach to build such logic-integrated models. A vector-quantized symbol grounding mechanism and the corresponding disentanglement training method are introduced to enhance the controllability of logical symbols over generation. Furthermore, we propose two logical abduction methods to ma…

Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu
https://arxiv.org/abs/2506.06242

Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations in visual form, a basic ability of human reasoning. To address this challenge, we introduce the Visual Graph Arena (VGA), a dataset featuring six graph-based tasks designed to evaluate and improve AI systems' capacity for visual abstraction. VGA uses diverse …

Control Architecture and Design for a Multi-robotic Visual Servoing System in Automated Manufacturing Environment
Rongfei Li
https://arxiv.org/abs/2506.11387

Control Architecture and Design for a Multi-robotic Visual Servoing System in Automated Manufacturing Environment
The use of robotic technology has drastically increased in manufacturing in the 21st century. But by utilizing their sensory cues, humans still outperform machines, especially in micro scale manufacturing, which requires high-precision robot manipulators. These sensory cues naturally compensate for high levels of uncertainties that exist in the manufacturing environment. Uncertainties in performing manufacturing tasks may come from measurement noise, model inaccuracy, joint compliance (e.g., el…

Can Sound Replace Vision in LLaVA With Token Substitution?
Ali Vosoughi, Jing Bi, Pinxin Liu, Yunlong Tang, Chenliang Xu
https://arxiv.org/abs/2506.10416 h…

Can Sound Replace Vision in LLaVA With Token Substitution?
While multimodal systems have achieved impressive advances, they typically rely on text-aligned representations rather than directly integrating audio and visual inputs. This reliance can limit the use of acoustic information in tasks requiring nuanced audio understanding. In response, SoundCLIP explores direct audio-visual integration within multimodal large language models (MLLMs) by substituting CLIP's visual tokens with audio representations and selecting sound-relevant patch tokens in mode…

Our body always wants to have three reference points since we live in 3D space. This can be a combination of two position sensors, and vision. Here is an interesting situation. When I shower, and am standing up, I place my normal leg and foot on the floor of the shower, and kneel on a shower stool. Combine that with my visual reference of my position in space, and I am golden. (2)

A post from the archive 📫:
Debug managed Linux core dumps with Visual Studio
https://www.poppastring.com/blog/debug-managed-linux-core-dumps-with-visual-studio

Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation
Shizhe Chen, Ricardo Garcia, Paul Pacaud, Cordelia Schmid
https://arxiv.org/abs/2506.11261

Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation
Robotic manipulation faces a significant challenge in generalizing across unseen objects, environments and tasks specified by diverse language instructions. To improve generalization capabilities, recent research has incorporated large language models (LLMs) for planning and action execution. While promising, these methods often fall short in generating grounded plans in visual environments. Although efforts have been made to perform visual instructional tuning on LLMs for robotic manipulation,…

Series B, Episode 03 - Weapon
COSER: Now, even if Security trace us to this planet, they'll assume the ship crashed and we died in the explosion. Did you hear what I said?
RASHEL: Yes.
COSER: Well?
RASHEL: It's a very clever plan, sir.
https://blake.torpidity.net/m/203/2

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Replaced article(s) found for cs.MM. https://arxiv.org/list/cs.MM/new
[1/1]:
Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual ...

TermSight: Making Service Contracts Approachable
Ziheng Huang, Tal August, Hari Sundaram
https://arxiv.org/abs/2506.12332 https://arx…

TermSight: Making Service Contracts Approachable
Terms of Service (ToS) are ubiquitous, legally binding contracts that govern consumers' digital interactions. However, ToS are not designed to be read: they are filled with pages of ambiguous and complex legal terminology that burden potential users. We introduce TermSight, an intelligent reading interface designed to make ToS more approachable. TermSight offers visual summaries that highlight the relevance and power balance of information in a ToS. TermSight also categorizes and simplifies inf…

To ChatGPT: Write a pitch against the use of visual-to-auditory sensory substitution for the blind. https://chatgpt.com/share/684c2ab3-2c68-8004-bf53-c3b401c10064 "Let's stop romanticizing sensory substitution and start prioritizing solutions that actu…

Phone Flooding Protest

Cross-attention and Self-attention for Audio-visual Speaker Diarization in MISP-Meeting Challenge
Zhaoyang Li, Haodong Zhou, Longjie Luo, Xiaoxiao Li, Yongxin Chen, Lin Li, Qingyang Hong
https://arxiv.org/abs/2506.02621

Cross-attention and Self-attention for Audio-visual Speaker Diarization in MISP-Meeting Challenge
This paper presents the system developed for Task 1 of the Multi-modal Information-based Speech Processing (MISP) 2025 Challenge. We introduce CASA-Net, an embedding fusion method designed for end-to-end audio-visual speaker diarization (AVSD) systems. CASA-Net incorporates a cross-attention (CA) module to effectively capture cross-modal interactions in audio-visual signals and employs a self-attention (SA) module to learn contextual relationships among audio-visual frames. To further enhance p…

Innovative Adaptive Imaged Based Visual Servoing Control of 6 DoFs Industrial Robot Manipulators
Rongfei Li, Francis Assadian
https://arxiv.org/abs/2506.10240

Innovative Adaptive Imaged Based Visual Servoing Control of 6 DoFs Industrial Robot Manipulators
Image-based visual servoing (IBVS) methods have been well developed and used in many applications, especially in pose (position and orientation) alignment. However, most research papers focused on developing control solutions when 3D point features can be detected inside the field of view. This work proposes an innovative feedforward-feedback adaptive control algorithm structure with the Youla Parameterization method. A designed feature estimation loop ensures stable and fast motion control whe…

Stop Misusing t-SNE and UMAP for Visual Analytics
Hyeon Jeon, Jeongin Park, Sungbok Shin, Jinwook Seo
https://arxiv.org/abs/2506.08725 https://

Stop Misusing t-SNE and UMAP for Visual Analytics
Misuses of t-SNE and UMAP in visual analytics have become increasingly common. For example, although t-SNE and UMAP projections often do not faithfully reflect true distances between clusters, practitioners frequently use them to investigate inter-cluster relationships. In this paper, we bring this issue to the surface and comprehensively investigate why such misuse occurs and how to prevent it. We conduct a literature review of 114 papers to verify the prevalence of the misuse and analyze the …

Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation
Runhao Zeng, Qi Deng, Ronghao Zhang, Shuaicheng Niu, Jian Chen, Xiping Hu, Victor C. M. Leung
https://arxiv.org/abs/2506.12481

Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation
Test-time adaptation (TTA) aims to boost the generalization capability of a trained model by conducting self-/unsupervised learning during the testing phase. While most existing TTA methods for video primarily utilize visual supervisory signals, they often overlook the potential contribution of inherent audio data. To address this gap, we propose a novel approach that incorporates audio information into video TTA. Our method capitalizes on the rich semantic content of audio to generate audio-as…

A Novel Feedforward Youla Parameterization Method for Avoiding Local Minima in Stereo Image Based Visual Servoing Control
Rongfei Li, Francis Assadian
https://arxiv.org/abs/2506.10252

A Novel Feedforward Youla Parameterization Method for Avoiding Local Minima in Stereo Image Based Visual Servoing Control
In robot navigation and manipulation, accurately determining the camera's pose relative to the environment is crucial for effective task execution. In this paper, we systematically prove that this problem corresponds to the Perspective-3-Point (P3P) formulation, where exactly three known 3D points and their corresponding 2D image projections are used to estimate the pose of a stereo camera. In image-based visual servoing (IBVS) control, the system becomes overdetermined, as the 6 degrees of fre…

Object knowledge representation in the human visual cortex requires a connection with the language system https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3003161 "Our experiments reveal the contribution of the vision-la…

Object knowledge representation in the human visual cortex requires a connection with the language system
This study shows that communication between the visual cortex and the brain language system is necessary for the representation of object knowledge in the visual cortex and for corresponding behaviors in humans. This highlights the significance of connections between sensory and language systems for object knowledge in the human brain.

$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
Sarthak Kumar Maharana, Saksham Singh Kushwaha, Baoming Zhang, Adrian Rodriguez, Songtao Wei, Yapeng Tian, Yunhui Guo
https://arxiv.org/abs/2506.00358

$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
While recent audio-visual models have demonstrated impressive performance, their robustness to distributional shifts at test-time remains not fully understood. Existing robustness benchmarks mainly focus on single modalities, making them insufficient for thoroughly assessing the robustness of audio-visual models. Motivated by real-world scenarios where shifts can occur $\textit{simultaneously}$ in both audio and visual modalities, we introduce $\texttt{AVROBUSTBENCH}$, a comprehensive benchmark…

This https://arxiv.org/abs/2505.18675 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps
Multimodal large language models (MLLMs) have recently achieved significant progress in visual tasks, including semantic scene understanding and text-image alignment, with reasoning variants enhancing performance on complex tasks involving mathematics and logic. However, their capacity for reasoning tasks involving fine-grained visual understanding remains insufficiently evaluated. To address this gap, we introduce ReasonMap, a benchmark designed to assess the fine-grained visual understanding …

Hotel stays of individuals with a visual impairment: a qualitative study with a focus on sensory substitution https://www.tandfonline.com/doi/full/10.1080/17483107.2025.2511982 "Sensory substitution devices (SSDs) hold the potential to aid individuals …

This https://arxiv.org/abs/2505.18700 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
Recent advances in Visual Language Models (VLMs) have demonstrated exceptional performance in visual reasoning tasks. However, geo-localization presents unique challenges, requiring the extraction of multigranular visual cues from images and their integration with external world knowledge for systematic reasoning. Current approaches to geo-localization tasks often lack robust reasoning mechanisms and explainability, limiting their effectiveness. To address these limitations, we propose the Geo …

This https://arxiv.org/abs/2506.03589 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance
Text-video retrieval (TVR) systems often suffer from visual-linguistic biases present in datasets, which cause pre-trained vision-language models to overlook key details. To address this, we propose BiMa, a novel framework designed to mitigate biases in both visual and textual representations. Our approach begins by generating scene elements that characterize each video by identifying relevant entities/objects and activities. For visual debiasing, we integrate these scene elements into the vide…

This https://arxiv.org/abs/2505.03448 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

AquaticVision: Benchmarking Visual SLAM in Underwater Environment with Events and Frames
Many underwater applications, such as offshore asset inspections, rely on visual inspection and detailed 3D reconstruction. Recent advancements in underwater visual SLAM systems for aquatic environments have garnered significant attention in marine robotics research. However, existing underwater visual SLAM datasets often lack groundtruth trajectory data, making it difficult to objectively compare the performance of different SLAM algorithms based solely on qualitative results or COLMAP reconst…

SEMNAV: A Semantic Segmentation-Driven Approach to Visual Semantic Navigation
Rafael Flor-Rodr\'iguez, Carlos Guti\'errez-\'Alvarez, Francisco Javier Acevedo-Rodr\'iguez, Sergio Lafuente-Arroyo, Roberto J. L\'opez-Sastre
https://arxiv.org/abs/2506.01418

SEMNAV: A Semantic Segmentation-Driven Approach to Visual Semantic Navigation
Visual Semantic Navigation (VSN) is a fundamental problem in robotics, where an agent must navigate toward a target object in an unknown environment, mainly using visual information. Most state-of-the-art VSN models are trained in simulation environments, where rendered scenes of the real world are used, at best. These approaches typically rely on raw RGB data from the virtual scenes, which limits their ability to generalize to real-world environments due to domain adaptation issues. To tackle …

This https://arxiv.org/abs/2505.19028 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts
Understanding infographic charts with design-driven visual elements (e.g., pictograms, icons) requires both visual recognition and reasoning, posing challenges for multimodal large language models (MLLMs). However, existing visual-question answering benchmarks fall short in evaluating these capabilities of MLLMs due to the lack of paired plain charts and visual-element-based questions. To bridge this gap, we introduce InfoChartQA, a benchmark for evaluating MLLMs on infographic chart understand…

GenIR: Generative Visual Feedback for Mental Image Retrieval
Diji Yang, Minghao Liu, Chung-Hsiang Lo, Yi Zhang, James Davis
https://arxiv.org/abs/2506.06220

GenIR: Generative Visual Feedback for Mental Image Retrieval
Vision-language models (VLMs) have shown strong performance on text-to-image retrieval benchmarks. However, bridging this success to real-world applications remains a challenge. In practice, human search behavior is rarely a one-shot action. Instead, it is often a multi-round process guided by clues in mind, that is, a mental image ranging from vague recollections to vivid mental representations of the target image. Motivated by this gap, we study the task of Mental Image Retrieval (MIR), which…

This https://arxiv.org/abs/2505.21036 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy
Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion}, a novel training-free sparse attention method that exploits inherent sparsity nature in visual data to accelerate attention computation while preserving video quality. Specifically, we identify three unique sparse patterns in video generation attention calcu…

This https://arxiv.org/abs/2505.18668 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
Infographic charts are a powerful medium for communicating abstract data by combining visual elements (e.g., charts, images) with textual information. However, their visual and structural richness poses challenges for large vision-language models (LVLMs), which are typically trained on plain charts. To bridge this gap, we introduce ChartGalaxy, a million-scale dataset designed to advance the understanding and generation of infographic charts. The dataset is constructed through an inductive proc…

This https://arxiv.org/abs/2505.17132 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Robustifying Vision-Language Models via Dynamic Token Reweighting
Large vision-language models (VLMs) are highly vulnerable to jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we present DTR, a novel inference-time defense that mitigates multimodal jailbreak attacks through optimizing the model's key-value (KV) caches. Rather than relying on curated safety-specific data or costly image-to-text conversion, we introduce a new formulation of the safety-relevant distributional shift induced by the visual modal…

CoMemo: LVLMs Need Image Context with Image Memory
Shi Liu, Weijie Su, Xizhou Zhu, Wenhai Wang, Jifeng Dai
https://arxiv.org/abs/2506.06279 https://…

CoMemo: LVLMs Need Image Context with Image Memory
Recent advancements in Large Vision-Language Models built upon Large Language Models have established aligning visual features with LLM representations as the dominant paradigm. However, inherited LLM architectural designs introduce suboptimal characteristics for multimodal processing. First, LVLMs exhibit a bimodal distribution in attention allocation, leading to the progressive neglect of middle visual content as context expands. Second, conventional positional encoding schemes fail to preser…