Tootfinder

Improved Accuracy in Pelvic Tumor Resections Using a Real-Time Vision-Guided Surgical System
Vahid Danesh, Paul Arauz, Maede Boroji, Andrew Zhu, Mia Cottone, Elaine Gould, Fazel A. Khan, Imin Kao
https://arxiv.org/abs/2505.23984

Improved Accuracy in Pelvic Tumor Resections Using a Real-Time Vision-Guided Surgical System
Pelvic bone tumor resections remain significantly challenging due to complex three-dimensional anatomy and limited surgical visualization. Current navigation systems and patient-specific instruments, while accurate, present limitations including high costs, radiation exposure, workflow disruption, long production time, and lack of reusability. This study evaluates a real-time vision-guided surgical system combined with modular jigs to improve accuracy in pelvic bone tumor resections. A vision-g…

Vision-Based Assistive Technologies for People with Cerebral Visual Impairment: A Review and Focus Study
Bhanuka Gamage, Leona Holloway, Nicola McDowell, Thanh-Toan Do, Nicholas Price, Arthur Lowery, Kim Marriott
https://arxiv.org/abs/2505.22983

Vision-Based Assistive Technologies for People with Cerebral Visual Impairment: A Review and Focus Study
Over the past decade, considerable research has investigated Vision-Based Assistive Technologies (VBAT) to support people with vision impairments to understand and interact with their immediate environment using machine learning, computer vision, image enhancement, and/or augmented/virtual reality. However, this has almost totally overlooked a growing demographic: people with Cerebral Visual Impairment (CVI). Unlike ocular vision impairments, CVI arises from damage to the brain's visual process…

This https://arxiv.org/abs/2505.13062 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMM_…

Hearing from Silence: Reasoning Audio Descriptions from Silent Videos via Vision-Language Model
Humans can intuitively infer sounds from silent videos, but whether multimodal large language models can perform modal-mismatch reasoning without accessing target modalities remains relatively unexplored. Current text-assisted-video-to-audio (VT2A) methods excel in video foley tasks but struggle to acquire audio descriptions during inference. We introduce the task of Reasoning Audio Descriptions from Silent Videos (SVAD) to address this challenge and investigate vision-language models' (VLMs) c…

Refining Datapath for Microscaling ViTs
Can Xiao, Jianyi Cheng, Aaron Zhao
https://arxiv.org/abs/2505.22194 https://arxiv.org/pdf/250…

Refining Datapath for Microscaling ViTs
Vision Transformers (ViTs) leverage the transformer architecture to effectively capture global context, demonstrating strong performance in computer vision tasks. A major challenge in ViT hardware acceleration is that the model family contains complex arithmetic operations that are sensitive to model accuracy, such as the Softmax and LayerNorm operations, which cannot be mapped onto efficient hardware with low precision. Existing methods only exploit parallelism in the matrix multiplication ope…

L'économie russe va mal, et c'est une bonne nouvelle pour l'Ukraine et l'Europe.
https://legrandcontinent.eu/fr/2025/05/23/economie-russe-pour-comp…

Var har alla kallbadande influensers tagit vägen? https://traningslara.se/var-har-alla-kallbadande-influensers-tagit-vagen/

Plasma refilling of the lunar wake: plasma-vacuum interactions, electrostatic shocks, and electromagnetic instabilities
Xin An, Vassilis Angelopoulos, Terry Z Liu, Anton Artemyev, Andrew R. Poppe, Donglai Ma
https://arxiv.org/abs/2505.12497

Plasma refilling of the lunar wake: plasma-vacuum interactions, electrostatic shocks, and electromagnetic instabilities
A plasma void forms downstream of the Moon when the solar wind impacts the lunar surface. This void gradually refills as the solar wind passes by, forming the lunar wake. We investigate this refilling process using a fully kinetic particle-in-cell (PIC) simulation. The early stage of refilling follows plasma-vacuum interaction theory, characterized by exponential decay of plasma density into the wake, along with ion acceleration and cooling in the expansion direction. Our PIC simulation confirm…

Våra grannländer tar nu konkreta steg mot ökad digital suveränitet. I Danmark samarbetar 81 kommuner för att minska beroendet av globala teknikjättar, medan Schleswig-Holstein i Tyskland bygger sin digitala arbetsmiljö på öppen källkod. Vad kan Sverige lära av detta?
https://carlhe…