The Game Developer's Conference, the largest event in the games industry, has hosted over 50 talks in the last decade about procedural generation, from small-scale independent speakers to large AAA companies, covering disciplines from programming to art to writing. Correspondingly, procedural generation has been an increasingly hot topic among game AI researchers in the last two decades. The Procedural Generation Workshop at FDG, now in its twelfth year, is one of the longest-running workshops in the field of game AI, and dedicated paper tracks at conferences are a regular occurrence. Despite the huge importance of content generation, and the wealth of time invested into developing practical techniques, the analysis of procedural generators is a relatively underdeveloped area of study. A few notable techniques have emerged over the last two decades of research [7, 8], as well as studies of efficacy [4, 9], but many of the techniques used by game researchers have changed little in that time. As a result, a lot of procedural generation work is done by'feel', with postmortems shared at events such as the Roguelike Celebration

Current image generation models struggle to reliably produce well-formed visual text. In this paper, we investigate a key contributing factor: popular text-to-image models lack character-level input features, making it much harder to predict a word's visual makeup as a series of glyphs. To quantify this effect, we conduct a series of experiments comparing character-aware vs. character-blind text encoders. In the text-only domain, we find that character-aware models provide large gains on a novel spelling task (WikiSpell). Applying our learnings to the visual domain, we train a suite of image generation models, and show that character-aware variants outperform their character-blind counterparts across a range of novel text rendering tasks (our DrawText benchmark). Our models set a much higher state-of-the-art on visual spelling, with 30+ point accuracy gains over competitors on rare words, despite training on far fewer examples.

Controller synthesis is in essence a case of model-based planning for non-deterministic environments in which plans (actually ''strategies'') are meant to preserve system goals indefinitely. In the case of supervisory control environments are specified as the parallel composition of state machines and valid strategies are required to be ''non-blocking'' (i.e., always enabling the environment to reach certain marked states) in addition to safe (i.e., keep the system within a safe zone). Recently, On-the-fly Directed Controller Synthesis techniques were proposed to avoid the exploration of the entire -and exponentially large-environment space, at the cost of non-maximal permissiveness, to either find a strategy or conclude that there is none. The incremental exploration of the plant is currently guided by a domain-independent human-designed heuristic. In this work, we propose a new method for obtaining heuristics based on Reinforcement Learning (RL). The synthesis algorithm is thus framed as an RL task with an unbounded action space and a modified version of DQN is used. With a simple and general set of features that abstracts both states and actions, we show that it is possible to learn heuristics on small versions of a problem that generalize to the larger instances, effectively doing zero-shot policy transfer. Our agents learn from scratch in a highly partially observable RL task and outperform the existing heuristic overall, in instances unseen during training.

While the systemic brutality used by Colombian police to quell national protests in 2021 was real and is well documented, photos recently used by Amnesty International to highlight the issue were not. The international human rights advocacy group has come under fire for posting images generated by artificial intelligence in order to promote their reports on social media – and has since removed them. The images, including one of a woman being dragged away by police officers, depict the scenes during protests that swept across Colombia in 2021. But any more than a momentary glance at the images reveals that something is off. The faces of the protesters and police are smoothed-off and warped, giving the image a dystopian aura.

Sentence Boundary Detection (SBD) is one of the foundational building blocks of Natural Language Processing (NLP), with incorrectly split sentences heavily influencing the output quality of downstream tasks. It is a challenging task for algorithms, especially in the legal domain, considering the complex and different sentence structures used. In this work, we curated a diverse multilingual legal dataset consisting of over 130'000 annotated sentences in 6 languages. Our experimental results indicate that the performance of existing SBD models is subpar on multilingual legal data. We trained and tested monolingual and multilingual models based on CRF, BiLSTM-CRF, and transformers, demonstrating state-of-the-art performance. We also show that our multilingual models outperform all baselines in the zero-shot setting on a Portuguese test set. To encourage further research and development by the community, we have made our dataset, models, and code publicly available.

We employ Natural Language Processing techniques to analyse 377808 English song lyrics from the "Two Million Song Database" corpus, focusing on the expression of sexism across five decades (1960-2010) and the measurement of gender biases. Using a sexism classifier, we identify sexist lyrics at a larger scale than previous studies using small samples of manually annotated popular songs. Furthermore, we reveal gender biases by measuring associations in word embeddings learned on song lyrics. We find sexist content to increase across time, especially from male artists and for popular songs appearing in Billboard charts. Songs are also shown to contain different language biases depending on the gender of the performer, with male solo artist songs containing more and stronger biases. This is the first large scale analysis of this type, giving insights into language usage in such an influential part of popular culture.

In this paper, we explore self-supervised learning (SSL) for analyzing a first-of-its-kind database of cry recordings containing clinical indications of more than a thousand newborns. Specifically, we target cry-based detection of neurological injury as well as identification of cry triggers such as pain, hunger, and discomfort. Annotating a large database in the medical setting is expensive and time-consuming, typically requiring the collaboration of several experts over years. Leveraging large amounts of unlabeled audio data to learn useful representations can lower the cost of building robust models and, ultimately, clinical solutions. In this work, we experiment with self-supervised pre-training of a convolutional neural network on large audio datasets. We show that pre-training with SSL contrastive loss (SimCLR) performs significantly better than supervised pre-training for both neuro injury and cry triggers. In addition, we demonstrate further performance gains through SSL-based domain adaptation using unlabeled infant cries. We also show that using such SSL-based pre-training for adaptation to cry sounds decreases the need for labeled data of the overall system.

Symbolic Regression (SR) is a rapidly growing subfield within machine learning (ML) to infer symbolic mathematical expressions from data [1, 2]. Interest in SR is being driven by the observation that it is not sufficient to only have accurate predictive models; however, it is often necessary that the learned models be interpretable [3]. A model is interpretable if the relationship between the input and output of the model can be logically or mathematically traced in a succinct manner. In other words, learnable models are interpretable if expressed as mathematical equations. As "disciplines" become increasingly data-rich and adopt ML techniques, the demand for interpretable models is likely to grow. For example, in the natural sciences (e.g., physics), mathematical models derived from first principles make it possible to reason about the underlying phenomenon in a way that is not possible with predictive models like deep neural networks. In critical disciplines like healthcare, non-interpretable models may never be allowed to be deployed - however accurate they maybe [4].

Stance detection is the identification of an author's beliefs about a subject from a document. Researchers widely rely on sentiment analysis to accomplish this. However, recent research has show that sentiment analysis is only loosely correlated with stance, if at all. This paper advances methods in text analysis by precisely defining the task of stance detection, providing a generalized framework for the task, and then presenting three distinct approaches for performing stance detection: supervised classification, zero-shot classification with NLI classifiers, and in-context learning. In doing so, I demonstrate how zero-shot and few-shot language classifiers can replace human labelers for a variety of tasks and discuss how their application and limitations differ from supervised classifiers. Finally, I demonstrate an application of zero-shot stance detection by replicating Block Jr et al. (2022).

Ground-air negotiation via speech communication is a vital prerequisite for ensuring safety and efficiency in air traffic control (ATC) operations. However, with the increase in traffic flow, incorrect instructions caused by human factors bring a great threat to ATC safety. Existing flight trajectory prediction (FTP) approaches primarily rely on the flight status of historical trajectory, leading to significant delays in the prediction of real-time maneuvering instruction, which is not conducive to conflict detection. A major reason is that spoken instructions and flight trajectories are presented in different modalities in the current air traffic control (ATC) system, bringing great challenges to considering the maneuvering instruction in the FTP tasks. In this paper, a spoken instruction-aware FTP framework, called SIA-FTP, is innovatively proposed to support high-maneuvering FTP tasks by incorporating instant spoken instruction. To address the modality gap and minimize the data requirements, a 3-stage learning paradigm is proposed to implement the SIA-FTP framework in a progressive manner, including trajectory-based FTP pretraining, intent-oriented instruction embedding learning, and multi-modal finetuning. Specifically, the FTP model and the instruction embedding with maneuvering semantics are pre-trained using volumes of well-resourced trajectory and text data in the 1st and 2nd stages. In succession, a multi-modal fusion strategy is proposed to incorporate the pre-trained instruction embedding into the FTP model and integrate the two pre-trained networks into a joint model. Finally, the joint model is finetuned using the limited trajectory-instruction data to enhance the FTP performance within maneuvering instruction scenarios. The experimental results demonstrated that the proposed framework presents an impressive performance improvement in high-maneuvering scenarios.