Tootfinder

Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation
Yejin Choi, Jaewoo Park, Janghan Yoon, Saejin Kim, Jaehyun Jeon, Youngjae Yu
https://arxiv.org/abs/2508.17079

Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation
Rapid advances in Multimodal Large Language Models (MLLMs) have expanded information retrieval beyond purely textual inputs, enabling retrieval from complex real world documents that combine text and visuals. However, most documents are private either owned by individuals or confined within corporate silos and current retrievers struggle when faced with unseen domains or languages. To address this gap, we introduce PREMIR, a simple yet effective framework that leverages the broad knowledge of a…

S2Sent: Nested Selectivity Aware Sentence Representation Learning
Jianxiang Zang, Nijia Mo, Yonda Wei, Meiling Ning, Hui Liu
https://arxiv.org/abs/2508.18164 https://

S2Sent: Nested Selectivity Aware Sentence Representation Learning
The combination of Transformer-based encoders with contrastive learning represents the current mainstream paradigm for sentence representation learning. This paradigm is typically based on the hidden states of the last Transformer block of the encoder. However, within Transformer-based encoders, different blocks exhibit varying degrees of semantic perception ability. From the perspective of interpretability, the semantic perception potential of knowledge neurons is modulated by stimuli, thus ra…

Boltzina: Efficient and Accurate Virtual Screening via Docking-Guided Binding Prediction with Boltz-2
Kairi Furui, Masahito Ohue
https://arxiv.org/abs/2508.17555 https://…

Boltzina: Efficient and Accurate Virtual Screening via Docking-Guided Binding Prediction with Boltz-2
In structure-based drug discovery, virtual screening using conventional molecular docking methods can be performed rapidly but suffers from limitations in prediction accuracy. Recently, Boltz-2 was proposed, achieving extremely high accuracy in binding affinity prediction, but requiring approximately 20 seconds per compound per GPU, making it difficult to apply to large-scale screening of hundreds of thousands to millions of compounds. This study proposes Boltzina, a novel framework that levera…

Mojo: MLIR-Based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem
William F. Godoy, Tatiana Melnichenko, Pedro Valero-Lara, Wael Elwasif, Philip Fackler, Rafael Ferreira Da Silva, Keita Teranishi, Jeffrey S. Vetter
https://arxiv.org/abs/2509.21039

Mojo: MLIR-Based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem
We explore the performance and portability of the novel Mojo language for scientific computing workloads on GPUs. As the first language based on the LLVM's Multi-Level Intermediate Representation (MLIR) compiler infrastructure, Mojo aims to close performance and productivity gaps by combining Python's interoperability and CUDA-like syntax for compile-time portable GPU programming. We target four scientific workloads: a seven-point stencil (memory-bound), BabelStream (memory-bound), miniBUDE (co…

Fantastic reporting (as usual) from @… for @… :

How Tea’s Founder Convinced Millions of Women to Spill Their Secrets, Then Exposed Them to the World
A 404 Media investigation reveals how the man who started Tea, the ‘women dating safety’ app, tried to hire a female ‘face’ for the company and then hijack her grassroots community.

If it’s anything like their “dire wolf,” they’ll sink millions into bringing the world… a fat kiwi. https://rssfeed.media/@abcfeeds/114910888061846217

“Since the boycotts of ABC and Disney began, Disney has now lost millions of dollars in market cap. In addition, the company has lost hundreds of thousands, if not millions of paid subscriptions to its services.”
As it should. Iger earned this.
https://aaronparnas.substack.com/p/new

AI-Supported Mini-Labs: Combining Smartphone-Based Experiments and Multimodal AI
Jochen Kuhn, David J. Rakestraw, Stefan K\"uchemann, Patrik Vogt
https://arxiv.org/abs/2508.16320

AI-Supported Mini-Labs: Combining Smartphone-Based Experiments and Multimodal AI
This paper presents the concept of AI-supported Mini-Labs, combining smartphone-based experiments with multimodal large language models (MLLMs). Smartphones, with their integrated sensors and computational power, function as versatile mobile laboratories for physics education. While they enable the collection of rich experimental data, the analysis of complex everyday phenomena has often been limited in the classroom. Advances in MLLMs now allow learners to process multimodal data, text, images…

An Indicator analysis of 85 AI "nudify" websites: the sites averaged 18.5M monthly visitors, may generate up to $36M annually, and rely on Big Tech services (Matt Burgess/Wired)
https://www.wired.com/story/ai-nudify-websites-are-raking-in-millions-…

AI 'Nudify' Websites Are Raking in Millions of Dollars
Millions of people are accessing harmful AI “nudify” websites. New analysis says the sites are making millions and rely on tech from US companies.

Efficient and Reuseable Cloud Configuration Search Using Discovery Spaces
Michael Johnston, Burkhard Ringlein, Christoph Hagleitner, Alessandro Pomponio, Vassilis Vassiliadis, Christian Pinto, Srikumar Venugopal
https://arxiv.org/abs/2506.21467

Efficient and Reuseable Cloud Configuration Search Using Discovery Spaces
Finding the optimal set of cloud resources to deploy a given workload at minimal cost while meeting a defined service level agreement is an active area of research. Combining tens of parameters applicable across a large selection of compute, storage, and services offered by cloud providers with similar numbers of application-specific parameters leads to configuration spaces with millions of deployment options. In this paper, we propose Discovery Space, an abstraction that formalizes the descr…