Recently, the concept of artificial assistants has evolved from science fiction into real-world applications. GPT-4o, the newest multimodal large language model (MLLM) across audio, vision, and text, has further blurred the line between fiction and reality by enabling more natural human-computer interactions. However, the advent of GPT-4o's voice mode may also introduce a new attack surface. In this paper, we present the first systematic measurement of jailbreak attacks against the voice mode of GPT-4o. We show that GPT-4o demonstrates good resistance to forbidden questions and text jailbreak prompts when directly transferring them to voice mode. This resistance is primarily due to GPT-4o's internal safeguards and the difficulty of adapting text jailbreak prompts to voice mode. Inspired by GPT-4o's human-like behaviors, we propose VoiceJailbreak, a novel voice jailbreak attack that humanizes GPT-4o and attempts to persuade it through fictional storytelling (setting, character, and plot). VoiceJailbreak is capable of generating simple, audible, yet effective jailbreak prompts, which significantly increases the average attack success rate (ASR) from 0.033 to 0.778 in six forbidden scenarios. We also conduct extensive experiments to explore the impacts of interaction steps, key elements of fictional writing, and different languages on VoiceJailbreak's effectiveness and further enhance the attack performance with advanced fictional writing techniques. We hope our study can assist the research community in building more secure and well-regulated MLLMs.

Advances in time series models are driving a shift from conventional deep learning methods to pre-trained foundational models. While pre-trained transformers and reprogrammed text-based LLMs report state-of-the-art results, the best-performing architectures vary significantly across tasks, and models often have limited scope, such as focusing only on time series forecasting. Models that unify predictive and generative time series tasks under a single framework remain challenging to achieve. We introduce UniTS, a multi-task time series model that uses task tokenization to express predictive and generative tasks within a single model. UniTS leverages a modified transformer block designed to obtain universal time series representations. This design induces transferability from a heterogeneous, multi-domain pre-training dataset-often with diverse dynamic patterns, sampling rates, and temporal scales-to many downstream datasets, which can also be diverse in task specifications and data domains. Across 38 datasets spanning human activity sensors, healthcare, engineering, and finance domains, UniTS model performs favorably against 12 forecasting models, 20 classification models, 18 anomaly detection models, and 16 imputation models, including repurposed text-based LLMs. UniTS demonstrates effective few-shot and prompt learning capabilities when evaluated on new data domains and tasks. In the conventional single-task setting, UniTS outperforms strong task-specialized time series models. The source code and datasets are available at https://github.com/mims-harvard/UniTS.

The long-standing one-to-many problem of gold standard responses in open-domain dialogue systems presents challenges for automatic evaluation metrics. Though prior works have demonstrated some success by applying powerful Large Language Models (LLMs), existing approaches still struggle with the one-to-many problem, and exhibit subpar performance in domain-specific scenarios. We assume the commonsense reasoning biases within LLMs may hinder their performance in domainspecific evaluations. To address both issues, we propose a novel framework SLIDE (Small and Large Integrated for Dialogue Evaluation), that leverages both a small, specialised model (SLM), and LLMs for the evaluation of open domain dialogues. Our approach introduces several techniques: (1) Contrastive learning to differentiate between robust and non-robust response embeddings; (2) A novel metric for semantic sensitivity that combines embedding cosine distances with similarity learned through neural networks, and (3) a strategy for incorporating the evaluation results from both the SLM and LLMs. Our empirical results demonstrate that our approach achieves state-of-the-art performance in both the classification and evaluation tasks, and additionally the SLIDE evaluator exhibits better correlation with human judgements. Our code is available at https:// github.com/hegehongcha/SLIDE-ACL2024.

Due to growing population and technological advances, global electricity consumption, and consequently also CO2 emissions are increasing. The residential sector makes up 25% of global electricity consumption and has great potential to increase efficiency and reduce CO2 footprint without sacrificing comfort. However, a lack of uniform consumption data at the household level spanning multiple regions hinders large-scale studies and robust multi-region model development. This paper introduces a multi-region dataset compiled from publicly available sources and presented in a uniform format. This data enables machine learning tasks such as disaggregation, demand forecasting, appliance ON/OFF classification, etc. Furthermore, we develop an RDF knowledge graph that characterizes the electricity consumption of the households and contextualizes it with household related properties enabling semantic queries and interoperability with other open knowledge bases like Wikidata and DBpedia. This structured data can be utilized to inform various stakeholders towards data-driven policy and business development.

Continuously optimizing sensor placement is essential for precise target localization in various military and civilian applications. While information theory has shown promise in optimizing sensor placement, many studies oversimplify sensor measurement models or neglect dynamic constraints of mobile sensors. To address these challenges, we employ a range measurement model that incorporates radar parameters and radar-target distance, coupled with Model Predictive Path Integral (MPPI) control to manage complex environmental obstacles and dynamic constraints. We compare the proposed approach against stationary radars or simplified range measurement models based on the root mean squared error (RMSE) of the Cubature Kalman Filter (CKF) estimator for the targets' state. Additionally, we visualize the evolving geometry of radars and targets over time, highlighting areas of highest measurement information gain, demonstrating the strengths of the approach. The proposed strategy outperforms stationary radars and simplified range measurement models in target localization, achieving a 38-74% reduction in mean RMSE and a 33-79% reduction in the upper tail of the 90% Highest Density Interval (HDI) over 500 Monte Carl (MC) trials across all time steps. Code will be made publicly available upon acceptance.

Semantic Bird's Eye View (BEV) maps offer a rich representation with strong occlusion reasoning for various decision making tasks in autonomous driving. However, most BEV mapping approaches employ a fully supervised learning paradigm that relies on large amounts of human-annotated BEV ground truth data. In this work, we address this limitation by proposing the first unsupervised representation learning approach to generate semantic BEV maps from a monocular frontal view (FV) image in a label-efficient manner. Our approach pretrains the network to independently reason about scene geometry and scene semantics using two disjoint neural pathways in an unsupervised manner and then finetunes it for the task of semantic BEV mapping using only a small fraction of labels in the BEV. We achieve label-free pretraining by exploiting spatial and temporal consistency of FV images to learn scene geometry while relying on a novel temporal masked autoencoder formulation to encode the scene representation. Extensive evaluations on the KITTI-360 and nuScenes datasets demonstrate that our approach performs on par with the existing state-of-the-art approaches while using only 1% of BEV labels and no additional labeled data.

In density functional theory, charge density is the core attribute of atomic systems from which all chemical properties can be derived. Machine learning methods are promising in significantly accelerating charge density prediction, yet existing approaches either lack accuracy or scalability. We propose a recipe that can achieve both. In particular, we identify three key ingredients: (1) representing the charge density with atomic and virtual orbitals (spherical fields centered at atom/virtual coordinates); (2) using expressive and learnable orbital basis sets (basis function for the spherical fields); and (3) using high-capacity equivariant neural network architecture. Our method achieves state-of-the-art accuracy while being more than an order of magnitude faster than existing methods. Furthermore, our method enables flexible efficiency-accuracy trade-offs by adjusting the model/basis sizes.

Large Language Models (LLMs) have exhibited remarkable proficiency in generating code. However, the misuse of LLM-generated (Synthetic) code has prompted concerns within both educational and industrial domains, highlighting the imperative need for the development of synthetic code detectors. Existing methods for detecting LLM-generated content are primarily tailored for general text and often struggle with code content due to the distinct grammatical structure of programming languages and massive "low-entropy" tokens. Building upon this, our work proposes a novel zero-shot synthetic code detector based on the similarity between the code and its rewritten variants. Our method relies on the intuition that the differences between the LLM-rewritten and original codes tend to be smaller when the original code is synthetic. We utilize self-supervised contrastive learning to train a code similarity model and assess our approach on two synthetic code detection benchmarks. Our results demonstrate a notable enhancement over existing synthetic content detectors designed for general texts, with an improvement of 20.5% in the APPS benchmark and 29.1% in the MBPP benchmark.

Growing interest and investment in the capabilities of foundation models has positioned such systems to impact a wide array of public services. Alongside these opportunities is the risk that these systems reify existing power imbalances and cause disproportionate harm to marginalized communities. Participatory approaches hold promise to instead lend agency and decision-making power to marginalized stakeholders. But existing approaches in participatory AI/ML are typically deeply grounded in context - how do we apply these approaches to foundation models, which are, by design, disconnected from context? Our paper interrogates this question. First, we examine existing attempts at incorporating participation into foundation models. We highlight the tension between participation and scale, demonstrating that it is intractable for impacted communities to meaningfully shape a foundation model that is intended to be universally applicable. In response, we develop a blueprint for participatory foundation models that identifies more local, application-oriented opportunities for meaningful participation. In addition to the "foundation" layer, our framework proposes the "subfloor'' layer, in which stakeholders develop shared technical infrastructure, norms and governance for a grounded domain, and the "surface'' layer, in which affected communities shape the use of a foundation model for a specific downstream task. The intermediate "subfloor'' layer scopes the range of potential harms to consider, and affords communities more concrete avenues for deliberation and intervention. At the same time, it avoids duplicative effort by scaling input across relevant use cases. Through three case studies in clinical care, financial services, and journalism, we illustrate how this multi-layer model can create more meaningful opportunities for participation than solely intervening at the foundation layer.

Recent end-to-end approaches have shown promise in extending large language models (LLMs) to speech inputs, but face limitations in directly assessing and optimizing alignment quality and fail to achieve fine-grained alignment due to speech-text length mismatch. We introduce BLSP-KD, a novel approach for Bootstrapping Language-Speech Pretraining via Knowledge Distillation, which addresses these limitations through two key techniques. First, it optimizes speech-text alignment by minimizing the divergence between the LLM's next-token prediction distributions for speech and text inputs using knowledge distillation. Second, it employs a continuous-integrate-andfire strategy to segment speech into tokens that correspond one-to-one with text tokens, enabling fine-grained alignment. We also introduce Partial LoRA (PLoRA), a new adaptation method supporting LLM finetuning for speech inputs under knowledge distillation. Quantitative evaluation shows that BLSP-KD outperforms previous end-to-end baselines and cascaded systems with comparable scale of parameters, facilitating general instruction-following capabilities for LLMs with speech inputs. This approach provides new possibilities for extending LLMs to spoken language interactions.