Tootfinder

Towards Reliable and Interpretable Document Question Answering via VLMs
Alessio Chen, Simone Giovannini, Andrea Gemelli, Fabio Coppini, Simone Marinai
https://arxiv.org/abs/2509.10129

Towards Reliable and Interpretable Document Question Answering via VLMs
Vision-Language Models (VLMs) have shown strong capabilities in document understanding, particularly in identifying and extracting textual information from complex documents. Despite this, accurately localizing answers within documents remains a major challenge, limiting both interpretability and real-world applicability. To address this, we introduce \textit{DocExplainerV0}, a plug-and-play bounding-box prediction module that decouples answer generation from spatial localization. This design m…

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…

Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers
Ruben Belo, Claudia Soares, Marta Guimaraes
https://arxiv.org/abs/2510.12672

Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers
Large Language Models are susceptible to jailbreak attacks that bypass built-in safety guardrails (e.g., by tricking the model with adversarial prompts). We propose Concept Alignment and Concept Manipulation \textbf{CALM}, an inference-time method that suppresses harmful concepts by modifying latent representations of the last layer of the model, without retraining. Leveraging \gls*{cw} technique from Computer Vision combined with orthogonal projection, CALM removes unwanted latent directions a…

Here’s a healthcare lawyer answering some common questions including if it is ethical to get the COVID vaccine, are you taking a dose away from someone who really needs it, etc
(free and shareable link)
https://www.patreon.com/posts/138476876/

gNB-based Local Breakout for URLLC in industrial 5G
Rajendra Paudyal, Rajendra Upadhyay, Al Nahian Bin Emran, Duminda Wijesekera
https://arxiv.org/abs/2509.10617 https://…

gNB-based Local Breakout for URLLC in industrial 5G
Industrial URLLC workloads-coordinated robotics, automated guided vehicles, machine-vision collaboration require sub-5 ms latency and five-nines reliability. In standardized 5G Multicast/Broadcast Services, intra-cell group traffic remains anchored in the core using MB-SMF/MB-UPF, and the Application Function. This incurs a core network path and packet delay that is avoidable when data transmitters and receivers share a cell. We propose a gNB-local multicast breakout that pivots eligible uplink…

And that's another trip to the Specsavers in Andover done, until I go pick up the new glasses in ~2 weeks.
Once more the staff were lovely, professional and both offered good information and answered any questions I had.
My bank account is wincing, as I've refreshed all *three* pairs; "intermediate vision" for computer work (most of my day), normal varifocals, and another varifocal pair with a polaroid tint for if it's sunny.

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

LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
Jing Huang, Zhiya Tan, Shutao Gong, Fanwei Zeng, Jianshu Li
https://arxiv.org/abs/2509.10026

LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
As large vision language models (VLMs) advance, their capabilities in multilingual visual question answering (mVQA) have significantly improved. Chain-of-thought (CoT) reasoning has been proven to enhance interpretability and complex reasoning. However, most existing approaches rely primarily on textual CoT and provide limited support for multilingual multimodal reasoning, constraining their deployment in real-world applications. To address this gap, we introduce \textbf{LaV-CoT}, the first Lan…

Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy
Patrick Wienholt, Sophie Caselitz, Robert Siepmann, Philipp Bruners, Keno Bressem, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
https://arxiv.org/abs/2510.09256

Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy
To determine whether using discrete semantic entropy (DSE) to reject questions likely to generate hallucinations can improve the accuracy of black-box vision-language models (VLMs) in radiologic image based visual question answering (VQA). This retrospective study evaluated DSE using two publicly available, de-identified datasets: (i) the VQA-Med 2019 benchmark (500 images with clinical questions and short-text answers) and (ii) a diagnostic radiology dataset (206 cases: 60 computed tomography …

Examining Vision Language Models through Multi-dimensional Experiments with Vision and Text Features
Saurav Sengupta, Nazanin Moradinasab, Jiebei Liu, Donald E. Brown
https://arxiv.org/abs/2509.08266

Examining Vision Language Models through Multi-dimensional Experiments with Vision and Text Features
Recent research on Vision Language Models (VLMs) suggests that they rely on inherent biases learned during training to respond to questions about visual properties of an image. These biases are exacerbated when VLMs are asked highly specific questions that require focusing on specific areas of the image. For example, a VLM tasked with counting stars on a modified American flag (e.g., with more than 50 stars) will often disregard the visual evidence and fail to answer accurately. We build upon t…