Tootfinder

Researchers have given people a taste of superhuman vision
after creating contact lenses that allow them to see infrared light.
Unlike night vision goggles,
the contact lenses need no power source,
and because they are transparent,
wearers can see infrared and all the normal visible colours of light at the same time

CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation
Zhanhang Xiong, Dongxia Wang, Yuekang Li, Xinyuan An, Wenhai Wang
https://arxiv.org/abs/2507.19904

CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation
As large language models (LLMs) become increasingly embedded in software engineering workflows, a critical capability remains underexplored: generating correct code that enables cross-programming-language (CPL) interoperability. This skill is essential for building complex systems that integrate components written in multiple languages via mechanisms like inter-process communication (IPC). To bridge this gap, we present CrossPL, the first benchmark designed to systematically evaluate LLMs' abil…

Harmonic, an AI math startup co-founded by Robinhood CEO Vlad Tenev, unveils its model Aristotle, saying it achieved gold medal performance on the 2025 IMO (Maxwell Zeff/TechCrunch)
https://techcrunch.com/2025/07/28/harmonic-the-robin…

Harmonic, the Robinhood CEO's AI math startup, launches an AI chatbot app | TechCrunch
The chatbot app, which is available in beta on iOS and Android, lets users access its AI model, Aristotle.

Leveraging Open-Source Large Language Models for Clinical Information Extraction in Resource-Constrained Settings
Luc Builtjes, Joeran Bosma, Mathias Prokop, Bram van Ginneken, Alessa Hering
https://arxiv.org/abs/2507.20859

Leveraging Open-Source Large Language Models for Clinical Information Extraction in Resource-Constrained Settings
Medical reports contain rich clinical information but are often unstructured and written in domain-specific language, posing challenges for information extraction. While proprietary large language models (LLMs) have shown promise in clinical natural language processing, their lack of transparency and data privacy concerns limit their utility in healthcare. This study therefore evaluates nine open-source generative LLMs on the DRAGON benchmark, which includes 28 clinical information extraction t…

EMERGENCY EPISODE: Trump Regime Launches Full-Scale Assault on CDC - Meidas Health (Ben Meiselas/Meidas )
https://www.meidasplus.com/p/emergency-episode-trump-regime-launches
http://www.memeorandum.com/250828/p44#a250828p44

Bookmarked: Talking About Muslims in Middle French: The Potential of Word-to-Vector Models for Studying Semantic Relationships in Medieval Languages – DH Lab #Digital_Humanities

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
Chunlong Xie, Jialing He, Shangwei Guo, Jiacheng Wang, Shudong Zhang, Tianwei Zhang, Tao Xiang
https://arxiv.org/abs/2505.23266

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
We present Adversarial Object Fusion (AdvOF), a novel attack framework targeting vision-and-language navigation (VLN) agents in service-oriented environments by generating adversarial 3D objects. While foundational models like Large Language Models (LLMs) and Vision Language Models (VLMs) have enhanced service-oriented navigation systems through improved perception and decision-making, their integration introduces vulnerabilities in mission-critical service workflows. Existing adversarial attac…

NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks
Aritra Dutta, Swapnanil Mukherjee, Deepanway Ghosal, Somak Aditya
https://arxiv.org/abs/2508.19724

NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks
Commonsense visual-question answering often hinges on knowledge that is missing from the image or the question. Small vision-language models (sVLMs) such as ViLT, VisualBERT and FLAVA therefore lag behind their larger generative counterparts. To study the effect of careful commonsense knowledge integration on sVLMs, we present an end-to-end framework (NLKI) that (i) retrieves natural language facts, (ii) prompts an LLM to craft natural language explanations, and (iii) feeds both signals to sVLM…

LastMerge: A language-agnostic structured tool for code integration
Joao Pedro Duarte, Paulo Borba, Guilherme Cavalcanti
https://arxiv.org/abs/2507.19687 https://

LastMerge: A language-agnostic structured tool for code integration
Unstructured line-based merge tools are widely used in practice. Structured AST-based merge tools show significantly improved merge accuracy, but are rarely used in practice because they are language specific and costly, consequently not being available for many programming languages. To improve merge accuracy for a wide range of languages, we propose LastMerge, a generic structured merge tool that can be configured through a thin interface that significantly reduces the effort of supporting st…