Schools in the US are installing vape-detection tech in bathrooms to thwart student nicotine and cannabis use. A new investigation reveals the impact of using spying to solve a problem. It was in physical education class when Laila Gutierrez swapped out self-harm for a new vice. The freshman from Phoenix had long struggled with depression and would cut her arms to feel something. The first drag from a friend's vape several years ago offered the shy teenager a new way to escape. She quit cutting but got hooked on nicotine. Her sadness got harder to carry after her uncle died, and she felt she couldn't turn to her grieving parents for comfort. Bumming fruity vapes at school became part of her routine. "I would ask my friends who had them, 'I'm going through a lot, can I use it?'" Gutierrez, now 18, told The 74. "Or'I failed my test and I feel like smoking would be better than cutting my wrists.'"

Text-to-SQL tasks have gained attractive improvements since the release of ChatGPT. Among them, agent-based frameworks have been widely used in this field. However, the impact of data-centric strategies on text-to-SQL tasks has rarely been explored. In this paper, we systemically design a fully automated data-centric pipeline for text-to-SQL tasks, including \emph{adaptive data repair}, which can automatically find and fix errors in the training dataset; and \emph{error data augmentation}, where we specifically diffuse and enhance erroneous data predicted by the initially trained models. Meanwhile, we propose a Multi-Model collaboration training schema, aiming to train multiple models with different augmented data, enabling them to possess distinct capabilities and work together to complement each other, because it has been found that the capability of a single fine-tuned model is very limited. Furthermore, we utilize an ensemble strategy to integrate the capabilities of multiple models to solve a multiple-choice question, aiming to further improve the accuracy of text-to-SQL tasks. The experiment results and ablation study have demonstrated the effectiveness of data-centric pipeline and Multi-Model(MM) interactive iterative strategies, achieving first place in lightweight text-to-SQL models (within 70B).

Abstract--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. Our method samples multiple CAD objects, which are then optimized using an evolutionary approach with vision language and reasoning language models. We assess our method using GPT -4V and GPT -4o, evaluating it on the CAD-Prompt benchmark dataset and comparing it to prior methods. Additionally, we introduce two new metrics based on topological properties defined by the Euler characteristic, which capture a form of semantic similarity between 3D objects. Our results demonstrate that EvoCAD outperforms previous approaches on multiple metrics, particularly in generating topologically correct objects, which can be efficiently evaluated using our two novel metrics that complement existing spatial metrics. The use of generative AI tools powered by large language models (LLMs) has transformed the way humans work, create, and develop. However, while significant attention is directed towards textual knowledge tasks, comparatively little focus is devoted on working with symbolic representations, such as those utilized in computer-aided design (CAD). These code-like textual representations, in the following referred as CAD code, enable visual assets to be processed by LLMs [21].

Mitigating climate change requires transforming agriculture to minimize environ mental impact and build climate resilience. Regenerative agricultural practices enhance soil organic carbon (SOC) levels, thus improving soil health and sequestering carbon. A challenge to increasing regenerative agriculture practices is cheaply measuring SOC over time and understanding how SOC is affected by regenerative agricultural practices and other environmental factors and farm management practices. To address this challenge, we introduce an AI-driven Soil Organic Carbon Copilot that automates the ingestion of complex multi-resolution, multi-modal data to provide large-scale insights into soil health and regenerative practices. Our data includes extreme weather event data (e.g., drought and wildfire incidents), farm management data (e.g., cropland information and tillage predictions), and SOC predictions. We find that integrating public data and specialized models enables large-scale, localized analysis for sustainable agriculture. In comparisons of agricultural practices across California counties, we find evidence that diverse agricultural activity may mitigate the negative effects of tillage; and that while extreme weather conditions heavily affect SOC, composting may mitigate SOC loss. Finally, implementing role-specific personas empowers agronomists, farm consultants, policymakers, and other stakeholders to implement evidence-based strategies that promote sustainable agriculture and build climate resilience.

Long-Context Question Answering (LCQA), a challenging task, aims to reason over long-context documents to yield accurate answers to questions. Existing long-context Large Language Models (LLMs) for LCQA often struggle with the "lost in the middle" issue. Retrieval-Augmented Generation (RAG) mitigates this issue by providing external factual evidence. However, its chunking strategy disrupts the global long-context information, and its low-quality retrieval in long contexts hinders LLMs from identifying effective factual details due to substantial noise. To this end, we propose LongRAG, a general, dual-perspective, and robust LLM-based RAG system paradigm for LCQA to enhance RAG's understanding of complex long-context knowledge (i.e., global information and factual details). We design LongRAG as a plug-and-play paradigm, facilitating adaptation to various domains and LLMs. Extensive experiments on three multi-hop datasets demonstrate that LongRAG significantly outperforms long-context LLMs (up by 6.94%), advanced RAG (up by 6.16%), and Vanilla RAG (up by 17.25%). Furthermore, we conduct quantitative ablation studies and multi-dimensional analyses, highlighting the effectiveness of the system's components and fine-tuning strategies. Data and code are available at https://github.com/QingFei1/LongRAG.

Silicon Valley billionaires and anti-poverty activists don't have a lot in common, but in recent years they've joined forces around a shared enthusiasm: programs that guarantee a basic income. Tech entrepreneurs like Sam Altman, chief executive of OpenAI, have promoted direct cash transfers to low-income Americans as a way to cushion them from what the entrepreneurs anticipate could be widespread job losses caused by artificial intelligence. Some local politicians and community leaders, concerned about growing wealth inequality, have also put their faith in these stipends, known as unconditional cash or, in their most ambitious form, a universal basic income. Dozens of small pilot projects testing unconditional cash transfers have popped up in communities around the country, from Alaska to Stockton, Calif. Andrew Yang, an entrepreneur, put the idea of 1,000 monthly payments for all adults at the center of his 2020 presidential campaign.

Dog guides are favored by blind and low-vision (BLV) individuals for their ability to enhance independence and confidence by reducing safety concerns and increasing navigation efficiency compared to traditional mobility aids. However, only a relatively small proportion of BLV individuals work with dog guides due to their limited availability and associated maintenance responsibilities. There is considerable recent interest in addressing this challenge by developing legged guide dog robots. This study was designed to determine critical aspects of the handler-guide dog interaction and better understand handler needs to inform guide dog robot development. We conducted semi-structured interviews and observation sessions with 23 dog guide handlers and 5 trainers. Thematic analysis revealed critical limitations in guide dog work, desired personalization in handler-guide dog interaction, and important perspectives on future guide dog robots. Grounded on these findings, we discuss pivotal design insights for guide dog robots aimed for adoption within the BLV community.

Fixed point lattice actions are designed to have continuum classical properties unaffected by discretization effects and reduced lattice artifacts at the quantum level. They provide a possible way to extract continuum physics with coarser lattices, thereby allowing to circumvent problems with critical slowing down and topological freezing toward the continuum limit. A crucial ingredient for practical applications is to find an accurate and compact parametrization of a fixed point action, since many of its properties are only implicitly defined. Here we use machine learning methods to revisit the question of how to parametrize fixed point actions. In particular, we obtain a fixed point action for four-dimensional SU(3) gauge theory using convolutional neural networks with exact gauge invariance. The large operator space allows us to find superior parametrizations compared to previous studies, a necessary first step for future Monte Carlo simulations.

Lattice gauge-equivariant convolutional neural networks (L-CNNs) can be used to form arbitrarily shaped Wilson loops and can approximate any gauge-covariant or gauge-invariant function on the lattice. Here we use L-CNNs to describe fixed point (FP) actions which are based on renormalization group transformations. FP actions are classically perfect, i.e., they have no lattice artifacts on classical gauge-field configurations satisfying the equations of motion, and therefore possess scale invariant instanton solutions. FP actions are tree-level Symanzik-improved to all orders in the lattice spacing and can produce physical predictions with very small lattice artifacts even on coarse lattices. We find that L-CNNs are much more accurate at parametrizing the FP action compared to older approaches. They may therefore provide a way to circumvent critical slowing down and topological freezing towards the continuum limit.

The application of Artificial Intelligence in the medical market brings up increasing concerns but aids in more timely diagnosis of silent progressing diseases like Diabetic Retinopathy. In order to diagnose Diabetic Retinopathy (DR), ophthalmologists use color fundus images, or pictures of the back of the retina, to identify small distinct features through a difficult and time-consuming process. Our work creates a novel CNN model and identifies the severity of DR through fundus image input. We classified 4 known DR features, including micro-aneurysms, cotton wools, exudates, and hemorrhages, through convolutional layers and were able to provide an accurate diagnostic without additional user input. The proposed model is more interpretable and robust to overfitting. We present initial results with a sensitivity of 97% and an accuracy of 71%. Our contribution is an interpretable model with similar accuracy to more complex models. With that, our model advances the field of DR detection and proves to be a key step towards AI-focused medical diagnosis.