Teams of mobile [aerial, ground, or aquatic] robots have applications in resource delivery, patrolling, information-gathering, agriculture, forest fire fighting, chemical plume source localization and mapping, and search-and-rescue. Robot teams traversing hazardous environments -- with e.g. rough terrain or seas, strong winds, or adversaries capable of attacking or capturing robots -- should plan and coordinate their trails in consideration of risks of disablement, destruction, or capture. Specifically, the robots should take the safest trails, coordinate their trails to cooperatively achieve the team-level objective with robustness to robot failures, and balance the reward from visiting locations against risks of robot losses. Herein, we consider bi-objective trail-planning for a mobile team of robots orienteering in a hazardous environment. The hazardous environment is abstracted as a directed graph whose arcs, when traversed by a robot, present known probabilities of survival. Each node of the graph offers a reward to the team if visited by a robot (which e.g. delivers a good to or images the node). We wish to search for the Pareto-optimal robot-team trail plans that maximize two [conflicting] team objectives: the expected (i) team reward and (ii) number of robots that survive the mission. A human decision-maker can then select trail plans that balance, according to their values, reward and robot survival. We implement ant colony optimization, guided by heuristics, to search for the Pareto-optimal set of robot team trail plans. As a case study, we illustrate with an information-gathering mission in an art museum.

Offline multi-agent reinforcement learning (MARL) is an exciting direction of research that uses static datasets to find optimal control policies for multi-agent systems. Though the field is by definition data-driven, efforts have thus far neglected data in their drive to achieve state-of-the-art results. We first substantiate this claim by surveying the literature, showing how the majority of works generate their own datasets without consistent methodology and provide sparse information about the characteristics of these datasets. We then show why neglecting the nature of the data is problematic, through salient examples of how tightly algorithmic performance is coupled to the dataset used, necessitating a common foundation for experiments in the field. In response, we take a big step towards improving data usage and data awareness in offline MARL, with three key contributions: (1) a clear guideline for generating novel datasets; (2) a standardisation of over 80 existing datasets, hosted in a publicly available repository, using a consistent storage format and easy-to-use API; and (3) a suite of analysis tools that allow us to understand these datasets better, aiding further development. These contributions are all publicly available on our website.

Autonomous driving technology has witnessed rapid advancements, with foundation models improving interactivity and user experiences. However, current autonomous vehicles (AVs) face significant limitations in delivering command-based driving styles. Most existing methods either rely on predefined driving styles that require expert input or use data-driven techniques like Inverse Reinforcement Learning to extract styles from driving data. These approaches, though effective in some cases, face challenges: difficulty obtaining specific driving data for style matching (e.g., in Robotaxis), inability to align driving style metrics with user preferences, and limitations to pre-existing styles, restricting customization and generalization to new commands. This paper introduces Words2Wheels, a framework that automatically generates customized driving policies based on natural language user commands. Words2Wheels employs a Style-Customized Reward Function to generate a Style-Customized Driving Policy without relying on prior driving data. By leveraging large language models and a Driving Style Database, the framework efficiently retrieves, adapts, and generalizes driving styles. A Statistical Evaluation module ensures alignment with user preferences. Experimental results demonstrate that Words2Wheels outperforms existing methods in accuracy, generalization, and adaptability, offering a novel solution for customized AV driving behavior. Code and demo available at https://yokhon.github.io/Words2Wheels/.

We propose a new benchmark to measure a language model's linguistic reasoning skills without relying on pre-existing language-specific knowledge. The test covers 894 questions grouped in 160 problems across 75 (mostly) extremely low-resource languages, extracted from the International Linguistic Olympiad corpus. To attain high accuracy on this benchmark, models don't need previous knowledge of the tested language, as all the information needed to solve the linguistic puzzle is presented in the context. We find that, while all analyzed models rank below 25% accuracy, there is a significant gap between open and closed models, with the best-performing proprietary model at 24.05% and the best-performing open model at 8.84%.

Federated learning offers a paradigm to the challenge of preserving privacy in distributed machine learning. However, datasets distributed across each client in the real world are inevitably heterogeneous, and if the datasets can be globally aggregated, they tend to be long-tailed distributed, which greatly affects the performance of the model. The traditional approach to federated learning primarily addresses the heterogeneity of data among clients, yet it fails to address the phenomenon of class-wise bias in global long-tailed data. This results in the trained model focusing on the head classes while neglecting the equally important tail classes. Consequently, it is essential to develop a methodology that considers classes holistically. To address the above problems, we propose a new method FedLF, which introduces three modifications in the local training phase: adaptive logit adjustment, continuous class centred optimization, and feature decorrelation. We compare seven state-of-the-art methods with varying degrees of data heterogeneity and long-tailed distribution. Extensive experiments on benchmark datasets CIFAR-10-LT and CIFAR-100-LT demonstrate that our approach effectively mitigates the problem of model performance degradation due to data heterogeneity and long-tailed distribution.

The loss landscape of neural networks is a critical aspect of their training, and understanding its properties is essential for improving their performance. In this paper, we investigate how the loss surface changes when the sample size increases, a previously unexplored issue. We theoretically analyze the convergence of the loss landscape in a fully connected neural network and derive upper bounds for the difference in loss function values when adding a new object to the sample. Our empirical study confirms these results on various datasets, demonstrating the convergence of the loss function surface for image classification tasks. Our findings provide insights into the local geometry of neural loss landscapes and have implications for the development of sample size determination techniques.

In this paper, we study format biases in reinforcement learning from human feedback (RLHF). We observe that many widely-used preference models, including human evaluators, GPT-4, and top-ranking models on the RewardBench benchmark, exhibit strong biases towards specific format patterns, such as lists, links, bold text, and emojis. Furthermore, large language models (LLMs) can exploit these biases to achieve higher rankings on popular benchmarks like AlpacaEval and LMSYS Chatbot Arena. One notable example of this is verbosity bias, where current preference models favor longer responses that appear more comprehensive, even when their quality is equal to or lower than shorter, competing responses. However, format biases beyond verbosity remain largely underexplored in the literature. In this work, we extend the study of biases in preference learning beyond the commonly recognized length bias, offering a comprehensive analysis of a wider range of format biases. Additionally, we show that with a small amount of biased data (less than 1%), we can inject significant bias into the reward model. Moreover, these format biases can also be easily exploited by downstream alignment algorithms, such as best-of-n sampling and online iterative DPO, as it is usually easier to manipulate the format than to improve the quality of responses. Our findings emphasize the need to disentangle format and content both for designing alignment algorithms and evaluating models.

Recently, an increasing number of news organizations have integrated artificial intelligence (AI) into their workflows, leading to a further influx of AI technologists and data workers into the news industry. This has initiated cross-functional collaborations between these professionals and journalists. While prior research has explored the impact of AI-related roles entering the news industry, there is a lack of studies on how cross-functional collaboration unfolds between AI professionals and journalists. Through interviews with 17 journalists, 6 AI technologists, and 3 AI workers with cross-functional experience from leading news organizations, we investigate the current practices, challenges, and opportunities for cross-functional collaboration around AI in today's news industry. We first study how journalists and AI professionals perceive existing cross-collaboration strategies. We further explore the challenges of cross-functional collaboration and provide recommendations for enhancing future cross-functional collaboration around AI in the news industry.

While there has been a lot of research recently on robots in household environments, at the present time, most robots in existence can be found on shop floors, and most interactions between humans and robots happen there. ``Collaborative robots'' (cobots) designed to work alongside humans on assembly lines traditionally require expert programming, limiting ability to make changes, or manual guidance, limiting expressivity of the resulting programs. To address these limitations, we explore using Large Language Models (LLMs), and in particular, their abilities of doing in-context learning, for conversational code generation. As a first step, we define RATS, the ``Repetitive Assembly Task'', a 2D building task designed to lay the foundation for simulating industry assembly scenarios. In this task, a `programmer' instructs a cobot, using natural language, on how a certain assembly is to be built; that is, the programmer induces a program, through natural language. We create a dataset that pairs target structures with various example instructions (human-authored, template-based, and model-generated) and example code. With this, we systematically evaluate the capabilities of state-of-the-art LLMs for synthesising this kind of code, given in-context examples. Evaluating in a simulated environment, we find that LLMs are capable of generating accurate `first order code' (instruction sequences), but have problems producing `higher-order code' (abstractions such as functions, or use of loops).

Molecular dynamics (MD) employing machine-learned interatomic potentials (MLIPs) serve as an efficient, urgently needed complement to ab initio molecular dynamics (aiMD). By training these potentials on data generated from ab initio methods, their averaged predictions can exhibit comparable performance to ab initio methods at a fraction of the cost. However, insufficient training sets might lead to an improper description of the dynamics in strongly anharmonic materials, because critical effects might be overlooked in relevant cases, or only incorrectly captured, or hallucinated by the MLIP when they are not actually present. In this work, we show that an active learning scheme that combines MD with MLIPs (MLIP-MD) and uncertainty estimates can avoid such problematic predictions. In short, efficient MLIP-MD is used to explore configuration space quickly, whereby an acquisition function based on uncertainty estimates and on energetic viability is employed to maximize the value of the newly generated data and to focus on the most unfamiliar but reasonably accessible regions of phase space. To verify our methodology, we screen over 112 materials and identify 10 examples experiencing the aforementioned problems. Using CuI and AgGaSe$_2$ as archetypes for these problematic materials, we discuss the physical implications for strongly anharmonic effects and demonstrate how the developed active learning scheme can address these issues.