Six months into his first year in high school, he dropped out. For more than a year, he isolated himself in his Huntington Beach bedroom where he became addicted to video games and anonymously vented his anger online with racist and misogynistic screeds, haunted by suicidal thoughts and fantasies about hurting others. His health deteriorated as he binged on pepperoni pizza, grew obese and developed terrible rashes. Today, Chida, 38, is Gov. Gavin Newsom's chief deputy Cabinet secretary, a key member of the team building an ambitious plan to reshape public education through a 50-billion continuum of services to create a healthy foundation for children and a path to meaningful jobs at the end. Chida was the chief architect of five-year compacts with the University of California and California State University, pledging financial stability in exchange for gains in graduation rates, access and affordability.

Before dawn, Father Paolo Benanti climbed to the bell tower of his 16th-century monastery, admired the sunrise over the ruins of the Roman forum and reflected on a world in flux. "It was a wonderful meditation on what is going on inside," he said, stepping onto the street in his friar robe. There is a lot is going on for Benanti, who, as both the Vatican's and the Italian government's go-to artificial intelligence ethicist, spends his days thinking about the Holy Ghost and the ghosts in the machines.

Real-world black-box optimization often involves time-consuming or costly experiments and simulations. Multi-fidelity optimization (MFO) stands out as a cost-effective strategy that balances high-fidelity accuracy with computational efficiency through a hierarchical fidelity approach. This survey presents a systematic exploration of MFO, underpinned by a novel text mining framework based on a pre-trained language model. We delve deep into the foundational principles and methodologies of MFO, focusing on three core components -- multi-fidelity surrogate models, fidelity management strategies, and optimization techniques. Additionally, this survey highlights the diverse applications of MFO across several key domains, including machine learning, engineering design optimization, and scientific discovery, showcasing the adaptability and effectiveness of MFO in tackling complex computational challenges. Furthermore, we also envision several emerging challenges and prospects in the MFO landscape, spanning scalability, the composition of lower fidelities, and the integration of human-in-the-loop approaches at the algorithmic level. We also address critical issues related to benchmarking and the advancement of open science within the MFO community. Overall, this survey aims to catalyze further research and foster collaborations in MFO, setting the stage for future innovations and breakthroughs in the field.

We study the problem of reward poisoning attacks against general offline reinforcement learning with deep neural networks for function approximation. We consider a black-box threat model where the attacker is completely oblivious to the learning algorithm and its budget is limited by constraining both the amount of corruption at each data point, and the total perturbation. We propose an attack strategy called `policy contrast attack'. The high-level idea is to make some low-performing policies appear as high-performing while making high-performing policies appear as low-performing. To the best of our knowledge, we propose the first black-box reward poisoning attack in the general offline RL setting. We provide theoretical insights on the attack design and empirically show that our attack is efficient against current state-of-the-art offline RL algorithms in different kinds of learning datasets.

Particle tracking is crucial for almost all physics analysis programs at the Large Hadron Collider. Deep learning models are pervasively used in particle tracking related tasks. However, the current practice is to design and train one deep learning model for one task with supervised learning techniques. The trained models work well for tasks they are trained on but show no or little generalization capabilities. We propose to unify these models with a language model. In this paper, we present a tokenized detector representation that allows us to train a BERT model for particle tracking. The trained BERT model, namely TrackingBERT, offers latent detector module embedding that can be used for other tasks. This work represents the first step towards developing a foundational model for particle detector understanding.

Large Language Models (LLMs) have surged in popularity in recent months, but they have demonstrated concerning capabilities to generate harmful content when manipulated. While techniques like safety fine-tuning aim to minimize harmful use, recent works have shown that LLMs remain vulnerable to attacks that elicit toxic responses. In this work, we introduce the Proxy-Guided Attack on LLMs (PAL), the first optimization-based attack on LLMs in a black-box query-only setting. In particular, it relies on a surrogate model to guide the optimization and a sophisticated loss designed for real-world LLM APIs. Our attack achieves 84% attack success rate (ASR) on GPT-3.5-Turbo and 48% on Llama-2-7B, compared to 4% for the current state of the art. We also propose GCG++, an improvement to the GCG attack that reaches 94% ASR on white-box Llama-2-7B, and the Random-Search Attack on LLMs (RAL), a strong but simple baseline for query-based attacks. We believe the techniques proposed in this work will enable more comprehensive safety testing of LLMs and, in the long term, the development of better security guardrails. The code can be found at https://github.com/chawins/pal.

This work aims to build a text embedder that can capture characteristics of texts specified by user instructions. Despite its tremendous potential to deploy user-oriented embeddings, none of previous approaches provides a concrete solution for it. This paper offers a new viewpoint, which treats the instruction as a question about the input text and encodes the expected answers to obtain the representation accordingly. Intuitively, texts with the same (implicit) semantics would share similar answers following the instruction, thus leading to more similar embeddings. Specifically, we propose InBedder that instantiates this embed-via-answering idea by only fine-tuning language models on abstractive question answering tasks. InBedder demonstrates significantly improved instruction-following capabilities according to our proposed instruction awareness tests and instruction robustness tests, when applied to both large language models (LLMs) (e.g., llama-2-7b) and smaller encoder-based LMs (e.g., roberta-large). Additionally, our qualitative analysis of clustering outcomes, achieved by applying different instructions to the same corpus, demonstrates a high degree of interpretability.

The rapid progression in artificial intelligence has facilitated the emergence of large language models like ChatGPT, offering potential applications extending into specialized engineering modeling, especially physics-based building energy modeling. This paper investigates the innovative integration of large language models with building energy modeling software, focusing specifically on the fusion of ChatGPT with EnergyPlus. A literature review is first conducted to reveal a growing trend of incorporating of large language models in engineering modeling, albeit limited research on their application in building energy modeling. We underscore the potential of large language models in addressing building energy modeling challenges and outline potential applications including 1) simulation input generation, 2) simulation output analysis and visualization, 3) conducting error analysis, 4) co-simulation, 5) simulation knowledge extraction and training, and 6) simulation optimization. Three case studies reveal the transformative potential of large language models in automating and optimizing building energy modeling tasks, underscoring the pivotal role of artificial intelligence in advancing sustainable building practices and energy efficiency. The case studies demonstrate that selecting the right large language model techniques is essential to enhance performance and reduce engineering efforts. Besides direct use of large language models, three specific techniques were utilized: 1) prompt engineering, 2) retrieval-augmented generation, and 3) multi-agent large language models. The findings advocate a multidisciplinary approach in future artificial intelligence research, with implications extending beyond building energy modeling to other specialized engineering modeling.

We introduce a multi-agent simulator for economic systems comprised of heterogeneous Households, heterogeneous Firms, Central Bank and Government agents, that could be subjected to exogenous, stochastic shocks. The interaction between agents defines the production and consumption of goods in the economy alongside the flow of money. Each agent can be designed to act according to fixed, rule-based strategies or learn their strategies using interactions with others in the simulator. We ground our simulator by choosing agent heterogeneity parameters based on economic literature, while designing their action spaces in accordance with real data in the United States. Our simulator facilitates the use of reinforcement learning strategies for the agents via an OpenAI Gym style environment definition for the economic system. We demonstrate the utility of our simulator by simulating and analyzing two hypothetical (yet interesting) economic scenarios. The first scenario investigates the impact of heterogeneous household skills on their learned preferences to work at different firms. The second scenario examines the impact of a positive production shock to one of two firms on its pricing strategy in comparison to the second firm. We aspire that our platform sets a stage for subsequent research at the intersection of artificial intelligence and economics.

Emergency events in a city cause considerable economic loss to individuals, their families, and the community. Accurate and timely prediction of events can help the emergency fire and rescue services in preparing for and mitigating the consequences of emergency events. In this paper, we present a systematic development of predictive models for various types of emergency events in the City of Edmonton, Canada. We present methods for (i) data collection and dataset development; (ii) descriptive analysis of each event type and its characteristics at different spatiotemporal levels; (iii) feature analysis and selection based on correlation coefficient analysis and feature importance analysis; and (iv) development of prediction models for the likelihood of occurrence of each event type at different temporal and spatial resolutions. We analyze the association of event types with socioeconomic and demographic data at the neighborhood level, identify a set of predictors for each event type, and develop predictive models with negative binomial regression. We conduct evaluations at neighborhood and fire station service area levels. Our results show that the models perform well for most of the event types with acceptable prediction errors for weekly and monthly periods. The evaluation shows that the prediction accuracy is consistent at the level of the fire station, so the predictions can be used in management by fire rescue service departments for planning resource allocation for these time periods. We also examine the impact of the COVID-19 pandemic on the occurrence of events and on the accuracy of event predictor models. Our findings show that COVID-19 had a significant impact on the performance of the event prediction models.