亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

The building sector plays a crucial role in the worldwide decarbonization effort, accounting for significant portions of energy consumption and environmental effects. However, the scarcity of open data sources is a continuous challenge for built environment researchers and practitioners. Although several efforts have been made to consolidate existing open datasets, no database currently offers a comprehensive collection of building data types with all subcategories and time granularities (e.g., year, month, and sub-hour). This paper presents the Building Data Genome Directory, an open data-sharing platform serving as a one-stop shop for the data necessary for vital categories of building energy research. The data directory is an online portal (//buildingdatadirectory.org/) that allows filtering and discovering valuable datasets. The directory covers meter, building-level, and aggregated community-level data at the spatial scale and year-to-minute level at the temporal scale. The datasets were consolidated from a comprehensive exploration of sources, including governments, research institutes, and online energy dashboards. The results of this effort include the aggregation of 60 datasets pertaining to building energy ontologies, building energy models, building energy and water data, electric vehicle data, weather data, building information data, text-mining-based research data, image data of buildings, fault detection diagnosis data and occupant data. A crowdsourcing mechanism in the platform allows users to submit datasets they suggest for inclusion by filling out an online form. This directory can fuel research and applications on building energy efficiency, which is an essential step toward addressing the world's energy and environmental challenges.

With the emergence of deep learning techniques, smartphone apps are now embedded on-device AI features for enabling advanced tasks like speech translation, to attract users and increase market competitiveness. A good interaction design is important to make an AI feature usable and understandable. However, AI features have their unique challenges like sensitiveness to the input, dynamic behaviours and output uncertainty. Existing guidelines and tools either do not cover AI features or consider mobile apps which are confirmed by our informal interview with professional designers. To address these issues, we conducted the first empirical study to explore user-AI-interaction in mobile apps. We aim to understand the status of on-device AI usage by investigating 176 AI apps from 62,822 apps. We identified 255 AI features and summarised 759 implementations into three primary interaction pattern types. We further implemented our findings into a multi-faceted search-enabled gallery. The results of the user study demonstrate the usefulness of our findings.

Multi-objective recommender systems (MORS) provide suggestions to users according to multiple (and possibly conflicting) goals. When a system optimizes its results at the individual-user level, it tailors them on a user's propensity towards the different objectives. Hence, the capability to understand users' fine-grained needs towards each goal is crucial. In this paper, we present the results of a user study in which we monitored the way users interacted with recommended items, as well as their self-proclaimed propensities towards relevance, novelty and diversity objectives. The study was divided into several sessions, where users evaluated recommendation lists originating from a relevance-only single-objective baseline as well as MORS. We show that despite MORS-based recommendations attracted less selections, its presence in the early sessions is crucial for users' satisfaction in the later stages. Surprisingly, the self-proclaimed willingness of users to interact with novel and diverse items is not always reflected in the recommendations they accept. Post-study questionnaires provide insights on how to deal with this matter, suggesting that MORS-based results should be accompanied by elements that allow users to understand the recommendations, so as to facilitate their acceptance.

In recent years, large language models (LLM) have emerged as powerful tools for diverse natural language processing tasks. However, their potential for recommendation systems remains relatively unexplored. This paper presents an innovative approach to recommendation systems using large language models (LLMs) based on text data. In this paper, we present a novel text-based large language model for recommendation (TBLLMR) that utilized the expressive power of LLM to generate personalized recommendation. TBLLMR uses LLM's understanding ability to interpret context, learn user preferences, and generate relevant recommendation. Our proposed approach leverages the vast knowledge encoded in large language models to accomplish recommendation tasks. We first we formulate specialized prompts to enhance the ability of LLM to comprehend recommendation tasks. Subsequently, we use these prompts to fine-tune the model on a dataset of user-item interactions, represented by textual data, to capture user preferences and item characteristics. Our research underscores the potential of text-based LLMs in revolutionizing the domain of recommendation systems and offers a foundational framework for future explorations in this field. We conduct extensive experiments on benchmark datasets, and the experiments shows that our TBLLMR has significant better results on large dataset.

In this paper, we explore the feasibility of finding algorithm implementations from code. Successfully matching code and algorithms can help understand unknown code, provide reference implementations, and automatically collect data for learning-based program synthesis. To achieve the goal, we designed a new language named p-language to specify the algorithms and a static analyzer for the p-language to automatically extract control flow, math, and natural language information from the algorithm descriptions. We embedded the output of p-language (p-code) and source code in a common vector space using self-supervised machine learning methods to match algorithm with code without any manual annotation. We developed a tool named Beryllium. It takes pseudo code as a query and returns a list of ranked code snippets that likely match the algorithm query. Our evaluation on Stony Brook Algorithm Repository and popular GitHub projects show that Beryllium significantly outperformed the state-of-the-art code search tools in both C and Java. Specifically, for 98.5%, 93.8%, and 66.2% queries, we found the algorithm implementations in the top 25, 10, and 1 ranked list, respectively. Given 87 algorithm queries, we found implementations for 74 algorithms in the GitHub projects where we did not know the algorithms before.

Recommendation foundation model utilizes large language models (LLM) for recommendation by converting recommendation tasks into natural language tasks. It enables generative recommendation which directly generates the item(s) to recommend rather than calculating a ranking score for each and every candidate item in traditional recommendation models, simplifying the recommendation pipeline from multi-stage filtering to single-stage filtering. To avoid generating excessively long text when deciding which item(s) to recommend, creating LLM-compatible item IDs is essential for recommendation foundation models. In this study, we systematically examine the item indexing problem for recommendation foundation models, using P5 as the representative backbone model and replicating its results with various indexing methods. To emphasize the importance of item indexing, we first discuss the issues of several trivial item indexing methods, such as independent indexing, title indexing, and random indexing. We then propose four simple yet effective solutions, including sequential indexing, collaborative indexing, semantic (content-based) indexing, and hybrid indexing. Our reproducibility study of P5 highlights the significant influence of item indexing methods on the model performance, and our results on real-world datasets validate the effectiveness of our proposed solutions.

We present LLM-Blender, an ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths of multiple open-source large language models (LLMs). Our framework consists of two modules: PairRanker and GenFuser, addressing the observation that optimal LLMs for different examples can significantly vary. PairRanker employs a specialized pairwise comparison method to distinguish subtle differences between candidate outputs. It jointly encodes the input text and a pair of candidates, using cross-attention encoders to determine the superior one. Our results demonstrate that PairRanker exhibits the highest correlation with ChatGPT-based ranking. Then, GenFuser aims to merge the top-ranked candidates, generating an improved output by capitalizing on their strengths and mitigating their weaknesses. To facilitate large-scale evaluation, we introduce a benchmark dataset, MixInstruct, which is a mixture of multiple instruction datasets featuring oracle pairwise comparisons. Our LLM-Blender significantly outperform individual LLMs and baseline methods across various metrics, establishing a substantial performance gap.

It is an open secret that ImageNet is treated as the panacea of pretraining. Particularly in medical machine learning, models not trained from scratch are often finetuned based on ImageNet-pretrained models. We posit that pretraining on data from the domain of the downstream task should almost always be preferred instead. We leverage RadNet-12M, a dataset containing more than 12 million computed tomography (CT) image slices, to explore the efficacy of self-supervised pretraining on medical and natural images. Our experiments cover intra- and cross-domain transfer scenarios, varying data scales, finetuning vs. linear evaluation, and feature space analysis. We observe that intra-domain transfer compares favorably to cross-domain transfer, achieving comparable or improved performance (0.44% - 2.07% performance increase using RadNet pretraining, depending on the experiment) and demonstrate the existence of a domain boundary-related generalization gap and domain-specific learned features.

Along with the increasing availability of health data has come the rise of data-driven models to inform decision-making and policy. These models have the potential to benefit both patients and health care providers but can also exacerbate health inequities. Existing "algorithmic fairness" methods for measuring and correcting model bias fall short of what is needed for health policy in two key ways. First, methods typically focus on a single grouping along which discrimination may occur rather than considering multiple, intersecting groups. Second, in clinical applications, risk prediction is typically used to guide treatment, creating distinct statistical issues that invalidate most existing techniques. We present summary unfairness metrics that build on existing techniques in "counterfactual fairness" to address both challenges. We also develop a complete framework of estimation and inference tools for our metrics, including the unfairness value ("u-value"), used to determine the relative extremity of unfairness, and standard errors and confidence intervals employing an alternative to the standard bootstrap. We demonstrate application of our framework to a COVID-19 risk prediction model deployed in a major Midwestern health system.

Unsupervised domain adaptation has recently emerged as an effective paradigm for generalizing deep neural networks to new target domains. However, there is still enormous potential to be tapped to reach the fully supervised performance. In this paper, we present a novel active learning strategy to assist knowledge transfer in the target domain, dubbed active domain adaptation. We start from an observation that energy-based models exhibit free energy biases when training (source) and test (target) data come from different distributions. Inspired by this inherent mechanism, we empirically reveal that a simple yet efficient energy-based sampling strategy sheds light on selecting the most valuable target samples than existing approaches requiring particular architectures or computation of the distances. Our algorithm, Energy-based Active Domain Adaptation (EADA), queries groups of targe data that incorporate both domain characteristic and instance uncertainty into every selection round. Meanwhile, by aligning the free energy of target data compact around the source domain via a regularization term, domain gap can be implicitly diminished. Through extensive experiments, we show that EADA surpasses state-of-the-art methods on well-known challenging benchmarks with substantial improvements, making it a useful option in the open world. Code is available at //github.com/BIT-DA/EADA.