Tootfinder

Apple updates the Vision Pro with an M5 chip, rendering 10% more pixels, and a Dual Knit Band for a more comfortable fit, available on October 22 for $3,499 (Apple)
https://www.apple.com/newsroom/2025/10/apple-vision-pro-upgraded-with-th…

Apple Vision Pro upgraded with the powerful M5 chip and comfortable Dual Knit Band
Apple introduced the upgraded Apple Vision Pro, featuring the powerful M5 chip, the Dual Knit Band, and innovative features with visionOS 26.

The Verge: These smart glasses use AI to help low-vision users #Envision Al…

These smart glasses use AI to help low-vision users
Accessibility-focused tech provider Envision has partnered with Solos to launch new smart glasses specifically designed for blind and low-vision users.

VARCO-VISION-2.0 Technical Report
Young-rok Cha, Jeongho Ju, SunYoung Park, Jong-Hyeon Lee, Younghyun Yu, Youngjune Kim
https://arxiv.org/abs/2509.10105 https://

VARCO-VISION-2.0 Technical Report
We introduce VARCO-VISION-2.0, an open-weight bilingual vision-language model (VLM) for Korean and English with improved capabilities compared to the previous model VARCO-VISION-14B. The model supports multi-image understanding for complex inputs such as documents, charts, and tables, and delivers layoutaware OCR by predicting both textual content and its spatial location. Trained with a four-stage curriculum with memory-efficient techniques, the model achieves enhanced multimodal alignment, wh…

Apple to start selling Vision Pro-compatible PlayStation VR2 Sense controllers for $250 on November 11 and the $130 Logitech Muse digital pen on October 22 (Zac Hall/9to5Mac)
https://9to5mac.com/2025/10/15/apple-v

Apple Vision Pro: PlayStation VR2 Sense controller in November, Logitech Muse and standalone Dual Knit Band available to order - 9to5Mac
Apple Vision Pro is officially being upgraded from the M2 to the new M5, but existing customers don’t need an...

The U.S. Department of Education has pulled funding for programs in eight states
aimed at supporting students who have both hearing and vision loss,
a move that could affect some of the country’s most vulnerable students.
The programs are considered vital in those states but represent only a little over $1 million a year in federal money.
Nonetheless, they got caught in the Trump administration’s attacks on diversity, equity and inclusion,
with an Education Dep…

Programs for Students With Hearing and Vision Loss Harmed by Trump’s Anti-Diversity Push
Citing concerns about DEI, the U.S. Department of Education has halted funding for programs that support students with combined hearing and vision loss in eight states. “How low can you go?” one advocate asked. “How can you do this to children?”

Withings bringt smarten Blutdruckmesser mit HD-Display zur einfachen Bedienung
Der Farbbildschirm des BPM Vision unterstützt den Nutzer beim Messvorgang von Blutdruck und EKG. Das smarte Gerät mit extra langer Akkulaufzeit kostet 180 Euro.

I read UCL's Vision for Inclusive Innovation and Transformation: 'our vision for a ‘data empowered society’ is one in which these advances enrich our society and enable us to make informed, inclusive decisions about technological advances' ht…

Building a Data-Empowered Society: UCL’s Vision for Inclusive Innovation and Transformation
Written by Professor James Hetherington and Professor Alison Littlejohn, Pro-Vice-Provosts to the UCL Grand Challenges theme of Data and…

Image reconstruction with the #JWST Interferometer / AMIGO - a Data-Driven Calibration of the JWST Interferometer: https://arxiv.org/abs/2510.10924 / https://arxiv.org/abs/2510.09806 -> How we sharpened the James Webb telescope’s vision from a million kilometres away: https://theconversation.com/how-we-sharpened-the-james-webb-telescopes-vision-from-a-million-kilometres-away-262510 -> thread https://bsky.app/profile/benjaminpope.bsky.social/post/3m34san6dd22m

Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations
Shresth Grover, Akshay Gopalkrishnan, Bo Ai, Henrik I. Christensen, Hao Su, Xuanlin Li
https://arxiv.org/abs/2509.11417

Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations
Vision-language-action (VLA) models finetuned from vision-language models (VLMs) hold the promise of leveraging rich pretrained representations to build generalist robots across diverse tasks and environments. However, direct fine-tuning on robot data often disrupts these representations and limits generalization. We present a framework that better preserves pretrained features while adapting them for robot manipulation. Our approach introduces three components: (i) a dual-encoder design with o…

Static or Temporal? Semantic Scene Simplification to Aid Wayfinding in Immersive Simulations of Bionic Vision
Justin M. Kasowski, Apurv Varshney, Michael Beyeler
https://arxiv.org/abs/2507.10813

Static or Temporal? Semantic Scene Simplification to Aid Wayfinding in Immersive Simulations of Bionic Vision
Visual neuroprostheses (bionic eye) aim to restore a rudimentary form of vision by translating camera input into patterns of electrical stimulation. To improve scene understanding under extreme resolution and bandwidth constraints, prior work has explored computer vision techniques such as semantic segmentation and depth estimation. However, presenting all task-relevant information simultaneously can overwhelm users in cluttered environments. We compare two complementary approaches to semantic …

Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs
Amir Taherin, Juyi Lin, Arash Akbari, Arman Akbari, Pu Zhao, Weiwei Chen, David Kaeli, Yanzhi Wang
https://arxiv.org/abs/2509.11480

Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs
Vision-Language-Action (VLA) models have emerged as powerful generalist policies for robotic control, yet their performance scaling across model architectures and hardware platforms, as well as their associated power budgets, remain poorly understood. This work presents an evaluation of five representative VLA models -- spanning state-of-the-art baselines and two newly proposed architectures -- targeting edge and datacenter GPU platforms. Using the LIBERO benchmark, we measure accuracy alongsid…

Mit Apple M5: MacBook Pro und iPad Pro 2025 sagen Hallo
Der M5 gibt sein Debüt in Macs, iPads und der Vision Pro. Apple verspricht mehr Leistung, primär für KI-Aufgaben. M5 Pro und M5 Max fehlen allerdings.
https://w…

Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding
Mingxiao Huo, Jiayi Zhang, Hewei Wang, Jinfeng Xu, Zheyu Chen, Huilin Tai, Yijun Chen
https://arxiv.org/abs/2509.11961

Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding
Vision-Language Models (VLMs) enable powerful multimodal reasoning but suffer from slow autoregressive inference, limiting their deployment in real-time applications. We introduce Spec-LLaVA, a system that applies speculative decoding to accelerate VLMs without sacrificing output quality. Spec-LLaVA pairs a lightweight draft VLM with a large target model: the draft speculates future tokens, which the target verifies in parallel, allowing multiple tokens to be generated per step. To maximize eff…

Residual Gaze Behavior During Navigation in Blindness and Low Vision
Junchi Feng, Fernanda Garcia-Pina, Mahya Beheshti, Todd E Hudson, William Seiple, John-Ross Rizzo
https://arxiv.org/abs/2509.11530

Residual Gaze Behavior During Navigation in Blindness and Low Vision
Background: Outdoor navigation poses significant challenges for people with blindness or low vision, yet the role of gaze behavior in supporting mobility remains underexplored. Fully sighted individuals typically adopt consistent scanning strategies, whereas those with visual impairments rely on heterogeneous adaptations shaped by residual vision and experience. Methods: We conducted a comparative eye-tracking study of fully sighted, low vision, blind, and fully blind participants navigating …

Hybrid Vision Transformer and Quantum Convolutional Neural Network for Image Classification
Mingzhu Wang, Yun Shang
https://arxiv.org/abs/2510.12291 https://

Hybrid Vision Transformer and Quantum Convolutional Neural Network for Image Classification
Quantum machine learning (QML) holds promise for computational advantage, yet progress on real-world tasks is hindered by classical preprocessing and noisy devices. We introduce ViT-QCNN-FT, a hybrid framework that integrates a fine-tuned Vision Transformer with a quantum convolutional neural network (QCNN) to compress high-dimensional images into features suited for noisy intermediate-scale quantum (NISQ) devices. By systematically probing entanglement, we show that ansatzes with uniformly dis…

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities
Yiting Qu, Michael Backes, Yang Zhang
https://arxiv.org/abs/2507.11155

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities
Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However, it is still unclear whether they can recognize various unsafe concepts when presented in different modalities, such as text and images. To address this, we first compile the UnsafeConcepts dataset, featuring 75 unsafe concepts, i.e., ``Swastika,'' ``Sexual Harassment,'' and ``Assaults,'' along with associated 1.5K im…

Adapting Medical Vision Foundation Models for Volumetric Medical Image Segmentation via Active Learning and Selective Semi-supervised Fine-tuning
Jin Yang, Daniel S. Marcus, Aristeidis Sotiras
https://arxiv.org/abs/2509.10784

Adapting Medical Vision Foundation Models for Volumetric Medical Image Segmentation via Active Learning and Selective Semi-supervised Fine-tuning
Medical Vision Foundation Models (Med-VFMs) have superior capabilities of interpreting medical images due to the knowledge learned from self-supervised pre-training with extensive unannotated images. To improve their performance on adaptive downstream evaluations, especially segmentation, a few samples from target domains are selected randomly for fine-tuning them. However, there lacks works to explore the way of adapting Med-VFMs to achieve the optimal performance on target domains efficiently…

Lost in Embeddings: Information Loss in Vision-Language Models
Wenyan Li, Raphael Tang, Chengzu Li, Caiqi Zhang, Ivan Vuli\'c, Anders S{\o}gaard
https://arxiv.org/abs/2509.11986

Lost in Embeddings: Information Loss in Vision-Language Models
Vision--language models (VLMs) often process visual inputs through a pretrained vision encoder, followed by a projection into the language model's embedding space via a connector component. While crucial for modality fusion, the potential information loss induced by this projection step and its direct impact on model capabilities remain understudied. We introduce two complementary approaches to examine and quantify this loss by analyzing the latent representation space. First, we evaluate seman…

Uncertainty Aware Mapping for Vision-Based Underwater Robots
Abhimanyu Bhowmik, Mohit Singh, Madhushree Sannigrahi, Martin Ludvigsen, Kostas Alexis
https://arxiv.org/abs/2507.10991

Uncertainty Aware Mapping for Vision-Based Underwater Robots
Vision-based underwater robots can be useful in inspecting and exploring confined spaces where traditional sensors and preplanned paths cannot be followed. Sensor noise and situational change can cause significant uncertainty in environmental representation. Thus, this paper explores how to represent mapping inconsistency in vision-based sensing and incorporate depth estimation confidence into the mapping framework. The scene depth and the confidence are estimated using the RAFT-Stereo model an…

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding
Yuhang Li, Chenchen Zhang, Ruilin Lv, Ao Liu, Ken Deng, Yuanxing Zhang, Jiaheng Liu, Wiggin Zhou, Bo Zhou
https://arxiv.org/abs/2510.11498

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding
While Large Language Models (LLMs) excel at algorithmic code generation, they struggle with front-end development, where correctness is judged on rendered pixels and interaction. We present ReLook, an agentic, vision-grounded reinforcement learning framework that empowers an agent to close a robust generate--diagnose--refine loop by invoking a multimodal LLM (MLLM) as a tool. During training, the agent uses the MLLM-in-the-loop both as a visual critic--scoring code with screenshots--and as a so…

A Research Vision for Web Search on Emerging Topics
Alisa Rieger, Stefan Dietze, Ran Yu
https://arxiv.org/abs/2509.10212 https://arxiv.org/pdf/2509.10212…

A Research Vision for Web Search on Emerging Topics
We regularly encounter information on novel, emerging topics for which the body of knowledge is still evolving, which can be linked, for instance, to current events. A primary way to learn more about such topics is through web search. However, information on emerging topics is sparse and evolves dynamically as knowledge grows, making it uncertain and variable in quality and trustworthiness and prone to deliberate or accidental manipulation, misinformation, and bias. In this paper, we outline a …

This robot is still quite bad at folding towels but think about the amount of computation, the vision, models, algorithms that are necessary to do this, it is very impressive.
#helix #laundry #ai

Nvidia says it is donating the Vera Rubin NVL144 server rack architecture to the Open Compute Project and outlines its vision for "gigawatt AI factories" (Mike Wheatley/SiliconANGLE)
https://siliconangle.com/2025/10/13/nv

Nvidia unveils its vision for gigawatt 'AI factories' based on its Vera Rubin architecture - SiliconANGLE
Nvidia unveils its vision for gigawatt 'AI factories' based on its Vera Rubin architecture - SiliconANGLE

Understanding AI Evaluation Patterns: How Different GPT Models Assess Vision-Language Descriptions
Sajjad Abdoli, Rudi Cilibrasi, Rima Al-Shikh
https://arxiv.org/abs/2509.10707 …

Understanding AI Evaluation Patterns: How Different GPT Models Assess Vision-Language Descriptions
As AI systems increasingly evaluate other AI outputs, understanding their assessment behavior becomes crucial for preventing cascading biases. This study analyzes vision-language descriptions generated by NVIDIA's Describe Anything Model and evaluated by three GPT variants (GPT-4o, GPT-4o-mini, GPT-5) to uncover distinct "evaluation personalities" the underlying assessment strategies and biases each model demonstrates. GPT-4o-mini exhibits systematic consistency with minimal variance, GPT-4o ex…

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
Haiyang Yu, Yuchuan Wu, Fan Shi, Lei Liao, Jinghui Lu, Xiaodong Ge, Han Wang, Minghan Zhuo, Xuecheng Wu, Xiang Fei, Hao Feng, Guozhi Tang, An-Lan Wang, Hanshen Zhu, Yangfan He, Quanhuan Liang, Liyuan Meng, Chao Feng, Can Huang, Jingqun Tang, Bin Li
https://

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and understanding, i.e., traditional methods only scan images, while current Vision-Language Models (VLMs) struggle with their visual and linguistic complexity. Existing document benchmarks focus on English printed texts or simplified Chinese, leaving a gap for evaluating VLMs on ancient Chinese documents. To address this, we p…

The main factors in student satisfaction with a campus environment: A mixed approach vs. a quantitative approach
Mohammed Eddaou
https://arxiv.org/abs/2509.10571 https://…

The main factors in student satisfaction with a campus environment: A mixed approach vs. a quantitative approach
University dropout rates in Morocco continue to increase, with approximately 49 percent of students leaving university before graduating, despite the successive reforms and measures taken to achieve Morocco's 2015_2030 strategic vision in the higher education sector : For a university of equity, quality and promotion, which raises questions about the state of knowledge on social inclusion at the university, capable of informing decision-making and the achievement of this strategic vision. While…

Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation
Zhen Xu, Hongyu Zhou, Sida Peng, Haotong Lin, Haoyu Guo, Jiahao Shao, Peishan Yang, Qinglin Yang, Sheng Miao, Xingyi He, Yifan Wang, Yue Wang, Ruizhen Hu, Yiyi Liao, Xiaowei Zhou, Hujun Bao
https://arxiv.org/abs/2507.11540

Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation
Depth estimation is a fundamental task in 3D computer vision, crucial for applications such as 3D reconstruction, free-viewpoint rendering, robotics, autonomous driving, and AR/VR technologies. Traditional methods relying on hardware sensors like LiDAR are often limited by high costs, low resolution, and environmental sensitivity, limiting their applicability in real-world scenarios. Recent advances in vision-based methods offer a promising alternative, yet they face challenges in generalizatio…

Inclusive by design: Developing Barrier-Free Authentication for Blind and Low Vision Users through the ALIAS Project
Clara Toussaint (CeRCA), Benjamin Chateau (CeRCA), Pierre-Guillaume Gourio-Jewell (CeRCA), Emilie Bonnefoy (CeRCA), Nicolas Louveton (CeRCA)
https://arxiv.org/abs/2509.10043

Inclusive by design: Developing Barrier-Free Authentication for Blind and Low Vision Users through the ALIAS Project
Authentication is the cornerstone of information security in our daily lives. However, disabled users such as Blind and Low-Vision (BLV) ones are left behind in digital services due to the lack of accessibility. According to the World Health Organization, 36 million people are blind worldwide. It is estimated that there will be 115 million by 2050, due to the ageing of the population. Yet accessing digital services has become increasingly essential. At the same time, cyber threats targeting ind…

All Eyes, no IMU: Learning Flight Attitude from Vision Alone
Jesse J. Hagenaars, Stein Stroobants, Sander M. Bohte, Guido C. H. E. De Croon
https://arxiv.org/abs/2507.11302

All Eyes, no IMU: Learning Flight Attitude from Vision Alone
Vision is an essential part of attitude control for many flying animals, some of which have no dedicated sense of gravity. Flying robots, on the other hand, typically depend heavily on accelerometers and gyroscopes for attitude stabilization. In this work, we present the first vision-only approach to flight control for use in generic environments. We show that a quadrotor drone equipped with a downward-facing event camera can estimate its attitude and rotation rate from just the event stream, e…

The Microwave Rainbow: How Geometry Paints Colours in Microwave Vision
Huizhang Yang
https://arxiv.org/abs/2509.11099 https://arxiv.org/pdf/2509.11099

The Microwave Rainbow: How Geometry Paints Colours in Microwave Vision
Microwave vision from spaceborne synthetic aperture radar (SAR) provides an all-weather, day-and-night capability to observe Earth, yet much of the information encoded in its signals remains undeciphered. Recent high-resolution imagery has revealed a striking phenomenon: man-made structures systematically appear in a spectrum of colours, the physical origin of which has been an open question. Here we show that this effect, which we term the microwave rainbow, is a form of geometric dispersion a…

Following public outcry,
the U.S. Department of Education has restored funding for students who have both hearing and vision loss,
about a month after cutting it.
But rather than sending the money directly to the four programs that are part of a national network helping students who are deaf and blind, a condition known as deafblindness,
the department has instead rerouted the grants to a different organization
The Trump administration targeted the programs in …

Students With Hearing and Vision Loss Get Funding Back Despite Trump’s Anti-DEI Campaign
Following public outcry, the Department of Education has reversed its decision to cut funding for students who have both hearing and vision loss, opting instead to reroute grants to an organization that will provide funding to these students.

Ganze Basketball-Spiele der NBA bald immersiv auf der Vision Pro
Apple wird zusammen mit einem US-Kabelanbieter erstmals komplette Basketballpartien mit der Blackmagic URSA abfilmen. Das Problem sind Copyright-Restriktionen.

Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander
Li Wang, Qizhen Wu, Lei Chen
https://arxiv.org/abs/2507.11079 ht…

Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander
In multiple unmanned ground vehicle confrontations, autonomously evolving multi-agent tactical decisions from situational awareness remain a significant challenge. Traditional handcraft rule-based methods become vulnerable in the complicated and transient battlefield environment, and current reinforcement learning methods mainly focus on action manipulation instead of strategic decisions due to lack of interpretability. Here, we propose a vision-language model-based commander to address the iss…

It is unclear to what extent Wicab's BrainPort Vision Pro tongue display (sensory substitution device) is still on the market https://www.wicab.com/brainport-vision-pro because there has been very little news about it since around 2019, judging also from their own website. Note that the BrainPor…

Sources say Meta's chaotic culture and lack of vision have led to AI brain drain; Meta strongly denies it has had issues with talent and retention (Rashi Shrivastava/Forbes)
https://www.forbes.com/sites/rashishrivast

How Meta Lost Its Way With AI Talent
At Meta, a chaotic culture and lack of vision have led to brain drain, with rivals saying its AI talent is lackluster. But Zuckerberg’s frenzied hiring spree hasn’t stopped the departures.

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
Fuhao Li, Wenxuan Song, Han Zhao, Jingbo Wang, Pengxiang Ding, Donglin Wang, Long Zeng, Haoang Li
https://arxiv.org/abs/2510.12276

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
Vision-language-action (VLA) models have recently shown strong potential in enabling robots to follow language instructions and execute precise actions. However, most VLAs are built upon vision-language models pretrained solely on 2D data, which lack accurate spatial awareness and hinder their ability to operate in the 3D physical world. Existing solutions attempt to incorporate explicit 3D sensor inputs such as depth maps or point clouds, but these approaches face challenges due to sensor nois…

I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
Jordan Sassoon, Michal Szczepanski, Martyna Poreba
https://arxiv.org/abs/2509.10334 https://

I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost. Quantization offers an effective strategy to improve efficiency, but ViT-based segmentation models are notoriously fragile under low precision, as quantization errors accumulate across deep encoder-decoder pipelines. We introduce I-Segmenter, the first fully integer-only ViT segm…

Bridging Modality Gaps in e-Commerce Products via Vision-Language Alignment
Yipeng Zhang, Hongju Yu, Aritra Mandal, Canran Xu, Qunzhi Zhou, Zhe Wu
https://arxiv.org/abs/2508.10116

Bridging Modality Gaps in e-Commerce Products via Vision-Language Alignment
Item information, such as titles and attributes, is essential for effective user engagement in e-commerce. However, manual or semi-manual entry of structured item specifics often produces inconsistent quality, errors, and slow turnaround, especially for Customer-to-Customer sellers. Generating accurate descriptions directly from item images offers a promising alternative. Existing retrieval-based solutions address some of these issues but often miss fine-grained visual details and struggle with…

TabVLA: Targeted Backdoor Attacks on Vision-Language-Action Models
Zonghuan Xu, Xiang Zheng, Xingjun Ma, Yu-Gang Jiang
https://arxiv.org/abs/2510.10932 https://

TabVLA: Targeted Backdoor Attacks on Vision-Language-Action Models
With the growing deployment of Vision-Language-Action (VLA) models in real-world embodied AI systems, their increasing vulnerability to backdoor attacks poses a serious safety threat. A backdoored VLA agent can be covertly triggered by a pre-injected backdoor to execute adversarial actions, potentially causing system failures or even physical harm. Although backdoor attacks on VLA models have been explored, prior work has focused only on untargeted attacks, leaving the more practically threaten…

EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Policy for Spatially Generalizable Contact-rich Tasks
Joohwan Seo, Arvind Kruthiventy, Soomi Lee, Megan Teng, Xiang Zhang, Seoyeon Choi, Jongeun Choi, Roberto Horowitz
https://arxiv.org/abs/2507.10961

EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Policy for Spatially Generalizable Contact-rich Tasks
This paper presents a framework for learning vision-based robotic policies for contact-rich manipulation tasks that generalize spatially across task configurations. We focus on achieving robust spatial generalization of the policy for the peg-in-hole (PiH) task trained from a small number of demonstrations. We propose EquiContact, a hierarchical policy composed of a high-level vision planner (Diffusion Equivariant Descriptor Field, Diff-EDF) and a novel low-level compliant visuomotor policy (Ge…

Implementing Adaptations for Vision AutoRegressive Model
Kaif Shaikh, Antoni Kowalczuk, Franziska Boenisch, Adam Dziedzic
https://arxiv.org/abs/2507.11441 …

Implementing Adaptations for Vision AutoRegressive Model
Vision AutoRegressive model (VAR) was recently introduced as an alternative to Diffusion Models (DMs) in image generation domain. In this work we focus on its adaptations, which aim to fine-tune pre-trained models to perform specific downstream tasks, like medical data generation. While for DMs there exist many techniques, adaptations for VAR remain underexplored. Similarly, differentially private (DP) adaptations-ones that aim to preserve privacy of the adaptation data-have been extensively st…

(video) NOVA: Artificial vision using brain implants https://www.pbslearningmedia.org/resource/nvbs-sci-artificialvision/artificial-vision-using-brain-implants-nova/nova-premium-collection/ on the I…

Super LiDAR Reflectance for Robotic Perception
Wei Gao, Jie Zhang, Mingle Zhao, Zhiyuan Zhang, Shu Kong, Maani Ghaffari, Dezhen Song, Cheng-Zhong Xu, Hui Kong
https://arxiv.org/abs/2508.10398

Super LiDAR Reflectance for Robotic Perception
Conventionally, human intuition often defines vision as a modality of passive optical sensing, while active optical sensing is typically regarded as measuring rather than the default modality of vision. However, the situation now changes: sensor technologies and data-driven paradigms empower active optical sensing to redefine the boundaries of vision, ushering in a new era of active vision. Light Detection and Ranging (LiDAR) sensors capture reflectance from object surfaces, which remains invar…

Comparative Analysis of Vision Transformers and Traditional Deep Learning Approaches for Automated Pneumonia Detection in Chest X-Rays
Gaurav Singh
https://arxiv.org/abs/2507.10589

Comparative Analysis of Vision Transformers and Traditional Deep Learning Approaches for Automated Pneumonia Detection in Chest X-Rays
Pneumonia, particularly when induced by diseases like COVID-19, remains a critical global health challenge requiring rapid and accurate diagnosis. This study presents a comprehensive comparison of traditional machine learning and state-of-the-art deep learning approaches for automated pneumonia detection using chest X-rays (CXRs). We evaluate multiple methodologies, ranging from conventional machine learning techniques (PCA-based clustering, Logistic Regression, and Support Vector Classificatio…

LoRA-fine-tuned Large Vision Models for Automated Assessment of Post-SBRT Lung Injury
M. Bolhassani, B. Veasey, E. Daugherty, S. Keltner, N. Kumar, N. Dunlap, A. Amini
https://arxiv.org/abs/2509.12155 …

LoRA-fine-tuned Large Vision Models for Automated Assessment of Post-SBRT Lung Injury
This study investigates the efficacy of Low-Rank Adaptation (LoRA) for fine-tuning large Vision Models, DinoV2 and SwinV2, to diagnose Radiation-Induced Lung Injury (RILI) from X-ray CT scans following Stereotactic Body Radiation Therapy (SBRT). To evaluate the robustness and efficiency of this approach, we compare LoRA with traditional full fine-tuning and inference-only (no fine-tuning) methods. Cropped images of two sizes (50 mm3 and 75 mm3), centered at the treatment isocenter, in addition …

Prozessor-Leaks: Diese SoCs und SiPs plant Apple in den kommenden Geräten
Welche Chips kommen in neue Modelle von HomePod mini, Apple TV, iPad mini und Vision Pro? Was ist mit dem Studio Display 2? Ein Code-Experte findet Hinweise.

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
Lingjie Jiang, Shaohan Huang, Xun Wu, Yixia Li, Dongdong Zhang, Furu Wei
https://arxiv.org/abs/2508.09945

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
Multimodal large language models (MLLMs) have significantly advanced the integration of visual and textual understanding. However, their ability to generate code from multimodal inputs remains limited. In this work, we introduce VisCodex, a unified framework that seamlessly merges vision and coding language models to empower MLLMs with strong multimodal code generation abilities. Leveraging a task vector-based model merging technique, we integrate a state-of-the-art coding LLM into a strong vis…

Detecting Text Manipulation in Images using Vision Language Models
Vidit Vidit, Pavel Korshunov, Amir Mohammadi, Christophe Ecabert, Ketan Kotwal, S\'ebastien Marcel
https://arxiv.org/abs/2509.10278

Detecting Text Manipulation in Images using Vision Language Models
Recent works have shown the effectiveness of Large Vision Language Models (VLMs or LVLMs) in image manipulation detection. However, text manipulation detection is largely missing in these studies. We bridge this knowledge gap by analyzing closed- and open-source VLMs on different text manipulation datasets. Our results suggest that open-source models are getting closer, but still behind closed-source ones like GPT- 4o. Additionally, we benchmark image manipulation detection-specific VLMs for te…

Vision Language Action Models in Robotic Manipulation: A Systematic Review
Muhayy Ud Din, Waseem Akram, Lyes Saad Saoud, Jan Rosell, Irfan Hussain
https://arxiv.org/abs/2507.10672

Vision Language Action Models in Robotic Manipulation: A Systematic Review
Vision Language Action (VLA) models represent a transformative shift in robotics, with the aim of unifying visual perception, natural language understanding, and embodied control within a single learning framework. This review presents a comprehensive and forward-looking synthesis of the VLA paradigm, with a particular emphasis on robotic manipulation and instruction-driven autonomy. We comprehensively analyze 102 VLA models, 26 foundational datasets, and 12 simulation platforms that collective…

Reducto, which uses OCR with vision language models to convert complex documents into inputs for LLMs, raised a $75M Series B led by a16z at a $600M valuation (Stephanie Palazzolo/The Information)
https://www.theinformation.com/articles/startup-using-ai-tran…

The Startup Using AI to Translate Documents Into Data
If you’ve ever uploaded a picture of a receipt to an expense report or read a PDF of a book online, you’ve likely used optical character recognition, a decades-old technique that converts images of typed, handwritten or printed text into text that’s editable on a computer.OCR might not sound ...

A Computer Vision Pipeline for Individual-Level Behavior Analysis: Benchmarking on the Edinburgh Pig Dataset
Haiyu Yang, Enhong Liu, Jennifer Sun, Sumit Sharma, Meike van Leerdam, Sebastien Franceschini, Puchun Niu, Miel Hostens
https://arxiv.org/abs/2509.12047

A Computer Vision Pipeline for Individual-Level Behavior Analysis: Benchmarking on the Edinburgh Pig Dataset
Animal behavior analysis plays a crucial role in understanding animal welfare, health status, and productivity in agricultural settings. However, traditional manual observation methods are time-consuming, subjective, and limited in scalability. We present a modular pipeline that leverages open-sourced state-of-the-art computer vision techniques to automate animal behavior analysis in a group housing environment. Our approach combines state-of-the-art models for zero-shot object detection, motio…

On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation
Shuhei Tarashima, Yushan Wang, Norio Tagawa
https://arxiv.org/abs/2510.12660

On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation
In this work, we aim to develop simple and efficient models for human mesh recovery (HMR) and its predecessor task, human pose estimation (HPE). State-of-the-art HMR methods, such as HMR2.0 and its successors, rely on large, non-hierarchical vision transformers as encoders, which are inherited from the corresponding HPE models like ViTPose. To establish baselines across varying computational budgets, we first construct three lightweight HMR2.0 variants by adapting the corresponding ViTPose mode…

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
Wenxuan Song, Ziyang Zhou, Han Zhao, Jiayi Chen, Pengxiang Ding, Haodong Yan, Yuxin Huang, Feilong Tang, Donglin Wang, Haoang Li
https://arxiv.org/abs/2508.10333

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a …

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
Pu Jian, Junhong Wu, Wei Sun, Chen Wang, Shuo Ren, Jiajun Zhang
https://arxiv.org/abs/2509.12132 …

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\textbf{VRMs}). owever, such transfer faces critical challenges: Effective "slow thinking" in VRMs requires \textbf{visual reflection}, the ability to check the reasoning process based on visual information. Through quantitative analysis, we observe that current VRMs exhibit limited visual reflection, as their attention …

CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model
Zhuoyuan Yu, Yuxing Long, Zihan Yang, Chengyan Zeng, Hongwei Fan, Jiyao Zhang, Hao Dong
https://arxiv.org/abs/2508.10416

CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model
Existing vision-and-language navigation models often deviate from the correct trajectory when executing instructions. However, these models lack effective error correction capability, hindering their recovery from errors. To address this challenge, we propose Self-correction Flywheel, a novel post-training paradigm. Instead of considering the model's error trajectories on the training set as a drawback, our paradigm emphasizes their significance as a valuable data source. We have developed a me…

Apple debuts its M5 chip, with a 10-core GPU, a Neural Accelerator in each core, enabling 4x the performance of M4, and a 10-core CPU with six efficiency cores (Hartley Charlton/MacRumors)
https://www.macrumors.com/2025/10/15/apple-unveils-m5-chip-with-n…

Apple Unveils M5 Chip With Next-Generation GPU
Apple today announced the M5 chip, its next-generation chip for the MacBook Pro, iPad Pro, and Vision Pro. From Apple's press release: Built...

Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
Chao Chen, Zhixin Ma, Yongqi Li, Yupeng Hu, Yinwei Wei, Wenjie Li, Liqiang Nie
https://arxiv.org/abs/2510.12603

Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
Multimodal reasoning aims to enhance the capabilities of MLLMs by incorporating intermediate reasoning steps before reaching the final answer. It has evolved from text-only reasoning to the integration of visual information, enabling the thought process to be conveyed through both images and text. Despite its effectiveness, current multimodal reasoning methods depend on explicit reasoning steps that require labor-intensive vision-text annotations and inherently introduce significant inference l…

Two-stream network-driven vision-based tactile sensor for object feature extraction and fusion perception
Muxing Huang, Zibin Chen, Weiliang Xu, Zilan Li, Yuanzhi Zhou, Guoyuan Zhou, Wenjing Chen, Xinming Li
https://arxiv.org/abs/2510.12528

Two-stream network-driven vision-based tactile sensor for object feature extraction and fusion perception
Tactile perception is crucial for embodied intelligent robots to recognize objects. Vision-based tactile sensors extract object physical attributes multidimensionally using high spatial resolution; however, this process generates abundant redundant information. Furthermore, single-dimensional extraction, lacking effective fusion, fails to fully characterize object attributes. These challenges hinder the improvement of recognition accuracy. To address this issue, this study introduces a two-stre…

From Diagnosis to Improvement: Probing Spatio-Physical Reasoning in Vision Language Models
Tiancheng Han, Yunfei Gao, Yong Li, Wuzhou Yu, Qiaosheng Zhang, Wenqi Shao
https://arxiv.org/abs/2508.10770

From Diagnosis to Improvement: Probing Spatio-Physical Reasoning in Vision Language Models
Spatio-physical reasoning, a foundation capability for understanding the real physics world, is a critical step towards building robust world models. While recent vision language models (VLMs) have shown remarkable progress in specialized domains like multimodal mathematics and pure spatial understanding, their capability for spatio-physical reasoning remains largely unexplored. This paper provides a comprehensive diagnostic analysis of mainstream VLMs, revealing that current models perform ina…

DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigation
Yunheng Wang, Yuetong Fang, Taowen Wang, Yixiao Feng, Yawen Tan, Shuning Zhang, Peiran Liu, Yiding Ji, Renjing Xu
https://arxiv.org/abs/2509.11197

DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigation
Vision-and-Language Navigation in Continuous Environments (VLN-CE), which links language instructions to perception and control in the real world, is a core capability of embodied robots. Recently, large-scale pretrained foundation models have been leveraged as shared priors for perception, reasoning, and action, enabling zero-shot VLN without task-specific training. However, existing zero-shot VLN methods depend on costly perception and passive scene understanding, collapsing control to point-…

GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation
Hang Yin, Haoyu Wei, Xiuwei Xu, Wenxuan Guo, Jie Zhou, Jiwen Lu
https://arxiv.org/abs/2509.10454

GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation
In this paper, we propose a training-free framework for vision-and-language navigation (VLN). Existing zero-shot VLN methods are mainly designed for discrete environments or involve unsupervised training in continuous simulator environments, which makes it challenging to generalize and deploy them in real-world scenarios. To achieve a training-free framework in continuous environments, our framework formulates navigation guidance as graph constraint optimization by decomposing instructions into…

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
Long Cui, Weiyun Wang, Jie Shao, Zichen Wen, Gen Luo, Linfeng Zhang, Yanting Zhang, Yu Qiao, Wenhai Wang
https://arxiv.org/abs/2510.12793

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm that enables the model to represent images of varying semantic complexities using different numbers of vision tokens. The key idea behind our method is to employ multiple MLP connectors, each with a different image compression ratio, to downsample the vision …

Some LA Lakers games will be live streamed in the Apple Immersive format in the NBA app and the Spectrum SportsNet app on Vision Pro during the 2025-26 season (Jacob Krol/TechRadar)
https://www.techradar.com/streaming/entert…

Wish you could be courtside at a Lakers game? Put your Vision Pro back on and fire up the NBA app
Select games will be streamed live in Apple Immersive

From Production Logistics to Smart Manufacturing: The Vision for a New RoboCup Industrial League
Supun Dissanayaka, Alexander Ferrein, Till Hofmann, Kosuke Nakajima, Mario Sanz-Lopez, Jesus Savage, Daniel Swoboda, Matteo Tschesche, Wataru Uemura, Tarik Viehmann, Shohei Yasuda
https://arxiv.org/abs/2507.11402

From Production Logistics to Smart Manufacturing: The Vision for a New RoboCup Industrial League
The RoboCup Logistics League is a RoboCup competition in a smart factory scenario that has focused on task planning, job scheduling, and multi-agent coordination. The focus on production logistics allowed teams to develop highly competitive strategies, but also meant that some recent developments in the context of smart manufacturing are not reflected in the competition, weakening its relevance over the years. In this paper, we describe the vision for the RoboCup Smart Manufacturing League, a n…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/3]:
- Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation
Li, Du, Yu, Li, Zhao, Liu, Jiang, Zhu, Huang

UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Kevin Li, Manuel Brack, Sudeep Katakol, Hareesh Ravi, Ajinkya Kale
https://arxiv.org/abs/2510.12789 https…

UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Although recent advances in visual generation have been remarkable, most existing architectures still depend on distinct encoders for images and text. This separation constrains diffusion models' ability to perform cross-modal reasoning and knowledge transfer. Prior attempts to bridge this gap often use the last layer information from VLM, employ multiple visual encoders, or train large unified models jointly for text and image generation, which demands substantial computational resources and l…

Beyond conventional vision: RGB-event fusion for robust object detection in dynamic traffic scenarios
Zhanwen Liu, Yujing Sun, Yang Wang, Nan Yang, Shengbo Eben Li, Xiangmo Zhao
https://arxiv.org/abs/2508.10704

Beyond conventional vision: RGB-event fusion for robust object detection in dynamic traffic scenarios
The dynamic range limitation of conventional RGB cameras reduces global contrast and causes loss of high-frequency details such as textures and edges in complex traffic environments (e.g., nighttime driving, tunnels), hindering discriminative feature extraction and degrading frame-based object detection. To address this, we integrate a bio-inspired event camera with an RGB camera to provide high dynamic range information and propose a motion cue fusion network (MCFNet), which achieves optimal s…

Few-shot Vision-based Human Activity Recognition with MLLM-based Visual Reinforcement Learning
Wenqi Zheng, Yutaka Arakawa
https://arxiv.org/abs/2508.10371 https://

Few-shot Vision-based Human Activity Recognition with MLLM-based Visual Reinforcement Learning
Reinforcement learning in large reasoning models enables learning from feedback on their outputs, making it particularly valuable in scenarios where fine-tuning data is limited. However, its application in multi-modal human activity recognition (HAR) domains remains largely underexplored. Our work extends reinforcement learning to the human activity recognition domain with multimodal large language models. By incorporating visual reinforcement learning in the training process, the model's gener…

3DViT-GAT: A Unified Atlas-Based 3D Vision Transformer and Graph Learning Framework for Major Depressive Disorder Detection Using Structural MRI Data
Nojod M. Alotaibi, Areej M. Alhothali, Manar S. Ali
https://arxiv.org/abs/2509.12143

3DViT-GAT: A Unified Atlas-Based 3D Vision Transformer and Graph Learning Framework for Major Depressive Disorder Detection Using Structural MRI Data
Major depressive disorder (MDD) is a prevalent mental health condition that negatively impacts both individual well-being and global public health. Automated detection of MDD using structural magnetic resonance imaging (sMRI) and deep learning (DL) methods holds increasing promise for improving diagnostic accuracy and enabling early intervention. Most existing methods employ either voxel-level features or handcrafted regional representations built from predefined brain atlases, limiting their a…

Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare
Adam Tupper, Christian Gagn\'e
https://arxiv.org/abs/2510.12741 https://a…

Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare
Foundation models open up new possibilities for the use of AI in healthcare. However, even when pre-trained on health data, they still need to be fine-tuned for specific downstream tasks. Furthermore, although foundation models reduce the amount of training data required to achieve good performance, obtaining sufficient data is still a challenge. This is due, in part, to restrictions on sharing and aggregating data from different sources to protect patients' privacy. One possible solution to th…

Igniting VLMs toward the Embodied Space
Andy Zhai, Brae Liu, Bruno Fang, Chalse Cai, Ellie Ma, Ethan Yin, Hao Wang, Hugo Zhou, James Wang, Lights Shi, Lucy Liang, Make Wang, Qian Wang, Roy Gan, Ryan Yu, Shalfun Li, Starrick Liu, Sylas Chen, Vincent Chen, Zach Xu
https://arxiv.org/abs/2509.11766

Igniting VLMs toward the Embodied Space
While foundation models show remarkable progress in language and vision, existing vision-language models (VLMs) still have limited spatial and embodiment understanding. Transferring VLMs to embodied domains reveals fundamental mismatches between modalities, pretraining distributions, and training objectives, leaving action comprehension and generation as a central bottleneck on the path to AGI. We introduce WALL-OSS, an end-to-end embodied foundation model that leverages large-scale multimoda…

Open-ended Hierarchical Streaming Video Understanding with Vision Language Models
Hyolim Kang, Yunsu Park, Youngbeom Yoo, Yeeun Choi, Seon Joo Kim
https://arxiv.org/abs/2509.12145

Open-ended Hierarchical Streaming Video Understanding with Vision Language Models
We introduce Hierarchical Streaming Video Understanding, a task that combines online temporal action localization with free-form description generation. Given the scarcity of datasets with hierarchical and fine-grained temporal annotations, we demonstrate that LLMs can effectively group atomic actions into higher-level events, enriching existing datasets. We then propose OpenHOUSE (Open-ended Hierarchical Online Understanding System for Events), which extends streaming action perception beyond …

Data or Language Supervision: What Makes CLIP Better than DINO?
Yiming Liu, Yuhui Zhang, Dhruba Ghosh, Ludwig Schmidt, Serena Yeung-Levy
https://arxiv.org/abs/2510.11835 https:/…

Data or Language Supervision: What Makes CLIP Better than DINO?
CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP's language supervision or its much larger training data. To disentangle these factors, we pre-train CLIP and DINO under controlled settings -- using the same architecture, dataset, and training configuration -- achieving similar ImageNet accuracy. Embedding analysis shows that CLIP captures high-level semantics (e.g., object catego…

Embodied Navigation Foundation Model
Jiazhao Zhang, Anqi Li, Yunpeng Qi, Minghan Li, Jiahang Liu, Shaoan Wang, Haoran Liu, Gengze Zhou, Yuze Wu, Xingxing Li, Yuxin Fan, Wenjun Li, Zhibo Chen, Fei Gao, Qi Wu, Zhizheng Zhang, He Wang
https://arxiv.org/abs/2509.12129

Embodied Navigation Foundation Model
Navigation is a fundamental capability in embodied AI, representing the intelligence required to perceive and interact within physical environments following language instructions. Despite significant progress in large Vision-Language Models (VLMs), which exhibit remarkable zero-shot performance on general vision-language tasks, their generalization ability in embodied navigation remains largely confined to narrow task settings and embodiment-specific architectures. In this work, we introduce a…

Adversarial robustness through Lipschitz-Guided Stochastic Depth in Neural Networks
Laith Nayal, Mahmoud Mousatat, Bader Rasheed
https://arxiv.org/abs/2509.10298 https://…

Adversarial robustness through Lipschitz-Guided Stochastic Depth in Neural Networks
Deep neural networks and Vision Transformers achieve state-of-the-art performance in computer vision but are highly vulnerable to adversarial perturbations. Standard defenses often incur high computational cost or lack formal guarantees. We propose a Lipschitz-guided stochastic depth (DropPath) method, where drop probabilities increase with depth to control the effective Lipschitz constant of the network. This approach regularizes deeper layers, improving robustness while preserving clean accur…

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
Wenpu Li, Bangyan Liao, Yi Zhou, Qi Xu, Pian Wan, Peidong Liu
https://arxiv.org/abs/2510.12753

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
The estimation of optical flow and 6-DoF ego-motion, two fundamental tasks in 3D vision, has typically been addressed independently. For neuromorphic vision (e.g., event cameras), however, the lack of robust data association makes solving the two problems separately an ill-posed challenge, especially in the absence of supervision via ground truth. Existing works mitigate this ill-posedness by either enforcing the smoothness of the flow field via an explicit variational regularizer or leveraging…

Vision-driven River Following of UAV via Safe Reinforcement Learning using Semantic Dynamics Model
Zihan Wang, Nina Mahmoudian
https://arxiv.org/abs/2508.09971 https://

Vision-driven River Following of UAV via Safe Reinforcement Learning using Semantic Dynamics Model
Vision-driven autonomous river following by Unmanned Aerial Vehicles is critical for applications such as rescue, surveillance, and environmental monitoring, particularly in dense riverine environments where GPS signals are unreliable. We formalize river following as a coverage control problem in which the reward function is submodular, yielding diminishing returns as more unique river segments are visited, thereby framing the task as a Submodular Markov Decision Process. First, we introduce Ma…

Large Language Models Facilitate Vision Reflection in Image Classification
Guoyuan An, JaeYoon Kim, SungEui Yoon
https://arxiv.org/abs/2508.06525 https://a…

Large Language Models Facilitate Vision Reflection in Image Classification
This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition accuracy, even on benchmarks like ImageNet, despite prior evidence that LMMs typically underperform dedicated vision encoders. Second, we analyze the internal behavior of vision reflection and find that the vision-language connector maps visual features into exp…

LLMC : Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
Chengtao Lv, Bilang Zhang, Yang Yong, Ruihao Gong, Yushi Huang, Shiqiao Gu, Jiajun Wu, Yumeng Shi, Jinyang Guo, Wenya Wang
https://arxiv.org/abs/2508.09981

LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
Large Vision-Language Models (VLMs) exhibit impressive multi-modal capabilities but suffer from prohibitive computational and memory demands, due to their long visual token sequences and massive parameter sizes. To address these issues, recent works have proposed training-free compression methods. However, existing efforts often suffer from three major limitations: (1) Current approaches do not decompose techniques into comparable modules, hindering fair evaluation across spatial and temporal r…

EvoCAD: Evolutionary CAD Code Generation with Vision Language Models
Tobias Preintner, Weixuan Yuan, Adrian K\"onig, Thomas B\"ack, Elena Raponi, Niki van Stein
https://arxiv.org/abs/2510.11631

EvoCAD: Evolutionary CAD Code Generation with Vision Language Models
Combining large language models with evolutionary computation algorithms represents a promising research direction leveraging the remarkable generative and in-context learning capabilities of LLMs with the strengths of evolutionary algorithms. In this work, we present EvoCAD, a method for generating computer-aided design (CAD) objects through their symbolic representations using vision language models and evolutionary optimization. Our method samples multiple CAD objects, which are then optimiz…

Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users
Jeffri Murrugarra-LLerena, Haoran Niu, K. Suzanne Barber, Hal Daum\'e III, Yang Trista Cao, Paola Cascante-Bonilla
https://arxiv.org/abs/2508.09245

Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users
As visual assistant systems powered by visual language models (VLMs) become more prevalent, concerns over user privacy have grown, particularly for blind and low vision users who may unknowingly capture personal private information in their images. Existing privacy protection methods rely on coarse-grained segmentation, which uniformly masks entire private objects, often at the cost of usability. In this work, we propose FiGPriv, a fine-grained privacy protection framework that selectively mask…

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
Shaoqi Dong, Chaoyou Fu, Haihan Gao, Yi-Fan Zhang, Chi Yan, Chu Wu, Xiaoyu Liu, Yunhang Shen, Jing Huo, Deqiang Jiang, Haoyu Cao, Yang Gao, Xing Sun, Ran He, Caifeng Shan
https://arxiv.org/abs/2510.09607

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
Vision-Language Action (VLA) models significantly advance robotic manipulation by leveraging the strong perception capabilities of pretrained vision-language models (VLMs). By integrating action modules into these pretrained models, VLA methods exhibit improved generalization. However, training them from scratch is costly. In this work, we propose a simple yet effective distillation-based framework that equips VLMs with action-execution capability by transferring knowledge from pretrained small…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[8/8]:
- TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores
Liao, Ding, Cui, Gong, Hu, Wang, Li, Zhang, Wang, Fu

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[7/8]:
- MultiCOIN: Multi-Modal COntrollable Video INbetweening
Tanveer, Zhou, Niklaus, Amiri, Zhang, Singh, Zhao

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[6/8]:
- GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning
Mustansar Fiaz, Hiyam Debary, Paolo Fraccaro, Danda Paudel, Luc Van Gool, Fahad Khan, Salman Khan

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/8]:
- Context Guided Transformer Entropy Modeling for Video Compression
Junlong Tong, Wei Zhang, Yaohui Jin, Xiaoyu Shen

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/8]:
- Boosting Adversarial Transferability via Commonality-Oriented Gradient Optimization
Yanting Gao, Yepeng Liu, Junming Liu, Qi Zhang, Hongyun Zhang, Duoqian Miao, Cairong Zhao

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/8]:
- Learning to Instruct for Visual Instruction Tuning
Zhihan Zhou, Feng Hong, Jiaan Luo, Jiangchao Yao, Dongsheng Li, Bo Han, Ya Zhang, Yanfeng Wang

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/8]:
- Multimodal Alignment and Fusion: A Survey
Songtao Li, Hao Tang
https://

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/8]:
- Invariant Feature Learning for Generalized Long-Tailed Classification
Kaihua Tang, Mingyuan Tao, Jiaxin Qi, Zhenguang Liu, Hanwang Zhang

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/3]:
- Adversarial Attacks Leverage Interference Between Features in Superposition
Edward Stevinson, Lucas Prieto, Melih Barsbey, Tolga Birdal

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/3]:
- ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test
Guan-Yan Yang, Tzu-Yu Cheng, Ya-Wen Teng, Farn Wanga, Kuo-Hui Yeh

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/3]:
- Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models
Rinaldi, Panariello, Salici, Liu, Ciccone, Porrello, Calderara

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/5]:
- Modular Embedding Recomposition for Incremental Learning
Panariello, Frascaroli, Buzzega, Bonicelli, Porrello, Calderara

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/5]:
- J-RAS: Enhancing Medical Image Segmentation via Retrieval-Augmented Joint Training
Salma J. Ahmed, Emad A. Mohammed, Azam Asilian Bidgoli

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/5]:
- STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes
Keishi Ishihara, Kento Sasaki, Tsubasa Takahashi, Daiki Shiono, Yu Yamaguchi

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/5]:
- Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) ...
Marin, et al.

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/5]:
- Enhancing Representations through Heterogeneous Self-Supervised Learning
Zhong-Yu Li, Bo-Wen Yin, Yongxiang Liu, Li Liu, Ming-Ming Cheng

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/1]:
- SeeingSounds: Learning Audio-to-Visual Alignment via Text
Carnemolla, Pennisi, Russo, Palazzo, Giordano, Spampinato

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/3]:
- Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image
Pufan Li, Bi'an Du, Wei Hu