In this study, we aim to determine if generalized sounds and music can share a common emotional space, improving predictions of emotion in terms of arousal and valence. We propose the use of multiple datasets as a multi-domain learning technique. Our approach involves creating a common space encompassing features that characterize both generalized sounds and music, as they can evoke emotions in a similar manner. To achieve this, we utilized two publicly available datasets, namely IADS-E and PMEmo, following a standardized experimental protocol. We employed a wide variety of features that capture diverse aspects of the audio structure including key parameters of spectrum, energy, and voicing. Subsequently, we performed joint learning on the common feature space, leveraging heterogeneous model architectures. Interestingly, this synergistic scheme outperforms the state-of-the-art in both sound and music emotion prediction. The code enabling full replication of the presented experimental pipeline is available at https://github.com/LIMUNIMI/MusicSoundEmotions.

Data visualization (DV) is the fundamental and premise tool to improve the efficiency in conveying the insights behind the big data, which has been widely accepted in existing data-driven world. Task automation in DV, such as converting natural language queries to visualizations (i.e., text-to-vis), generating explanations from visualizations (i.e., vis-to-text), answering DV-related questions in free form (i.e. FeVisQA), and explicating tabular data (i.e., table-to-text), is vital for advancing the field. Despite their potential, the application of pre-trained language models (PLMs) like T5 and BERT in DV has been limited by high costs and challenges in handling cross-modal information, leading to few studies on PLMs for DV. We introduce \textbf{DataVisT5}, a novel PLM tailored for DV that enhances the T5 architecture through a hybrid objective pre-training and multi-task fine-tuning strategy, integrating text and DV datasets to effectively interpret cross-modal semantics. Extensive evaluations on public datasets show that DataVisT5 consistently outperforms current state-of-the-art models on various DV-related tasks. We anticipate that DataVisT5 will not only inspire further research on vertical PLMs but also expand the range of applications for PLMs.

The use of Large Language Models (LLMs) has become ubiquitous, with abundant applications in computational creativity. One such application is fictional story generation. Fiction is a narrative that occurs in a story world that is slightly different than ours. With LLMs becoming writing partners, we question how suitable they are to generate fiction. This study investigates the ability of LLMs to maintain a state of world essential to generate fiction. Through a series of questions to nine LLMs, we find that only two models exhibit consistent worldview, while the rest are self-conflicting. Subsequent analysis of stories generated by four models revealed a strikingly uniform narrative pattern. This uniformity across models further suggests a lack of `state' necessary for fiction. We highlight the limitations of current LLMs in fiction writing and advocate for future research to test and create story worlds for LLMs to reside in. All code, dataset, and the generated responses can be found in https://github.com/tanny411/llm-reliability-and-consistency-evaluation.

Formal languages are essential for computer programming and are constructed to be easily processed by computers. In contrast, natural languages are much more challenging and instigated the field of Natural Language Processing (NLP). One major obstacle is the ubiquity of ambiguities. Recent advances in NLP have led to the development of large language models, which can resolve ambiguities with high accuracy. At the same time, quantum computers have gained much attention in recent years as they can solve some computational problems faster than classical computers. This new computing paradigm has reached the fields of machine learning and NLP, where hybrid classical-quantum learning algorithms have emerged. However, more research is needed to identify which NLP tasks could benefit from a genuine quantum advantage. In this thesis, we applied formalisms arising from foundational quantum mechanics, such as contextuality and causality, to study ambiguities arising from linguistics. By doing so, we also reproduced psycholinguistic results relating to the human disambiguation process. These results were subsequently used to predict human behaviour and outperformed current NLP methods.

We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

Fonts are integral to creative endeavors, design processes, and artistic productions. The appropriate selection of a font can significantly enhance artwork and endow advertisements with a higher level of expressivity. Despite the availability of numerous diverse font designs online, traditional retrieval-based methods for font selection are increasingly being supplanted by generation-based approaches. These newer methods offer enhanced flexibility, catering to specific user preferences and capturing unique stylistic impressions. However, current impression font techniques based on Generative Adversarial Networks (GANs) necessitate the utilization of multiple auxiliary losses to provide guidance during generation. Furthermore, these methods commonly employ weighted summation for the fusion of impression-related keywords. This leads to generic vectors with the addition of more impression keywords, ultimately lacking in detail generation capacity. In this paper, we introduce a diffusion-based method, termed \ourmethod, to generate fonts that vividly embody specific impressions, utilizing an input consisting of a single letter and a set of descriptive impression keywords. The core innovation of \ourmethod lies in the development of dual cross-attention modules, which process the characteristics of the letters and impression keywords independently but synergistically, ensuring effective integration of both types of information. Our experimental results, conducted on the MyFonts dataset, affirm that this method is capable of producing realistic, vibrant, and high-fidelity fonts that are closely aligned with user specifications. This confirms the potential of our approach to revolutionize font generation by accommodating a broad spectrum of user-driven design requirements. Our code is publicly available at \url{https://github.com/leitro/GRIF-DM}.

Schenkerian Analysis (SchA) is a uniquely expressive method of music analysis, combining elements of melody, harmony, counterpoint, and form to describe the hierarchical structure supporting a work of music. However, despite its powerful analytical utility and potential to improve music understanding and generation, SchA has rarely been utilized by the computer music community. This is in large part due to the paucity of available high-quality data in a computer-readable format. With a larger corpus of Schenkerian data, it may be possible to infuse machine learning models with a deeper understanding of musical structure, thus leading to more "human" results. To encourage further research in Schenkerian analysis and its potential benefits for music informatics and generation, this paper presents three main contributions: 1) a new and growing dataset of SchAs, the largest in human- and computer-readable formats to date (>140 excerpts), 2) a novel software for visualization and collection of SchA data, and 3) a novel, flexible representation of SchA as a heterogeneous-edge graph data structure.

Slate recommendation is a technique commonly used on streaming platforms and e-commerce sites to present multiple items together. A significant challenge with slate recommendation is managing the complex combinatorial choice space. Traditional methods often simplify this problem by assuming users engage with only one item at a time. However, this simplification does not reflect the reality, as users often interact with multiple items simultaneously. In this paper, we address the general slate recommendation problem, which accounts for simultaneous engagement with multiple items. We propose a generative approach using Diffusion Models, leveraging their ability to learn structures in high-dimensional data. Our model generates high-quality slates that maximize user satisfaction by overcoming the challenges of the combinatorial choice space. Furthermore, our approach enhances the diversity of recommendations. Extensive offline evaluations on applications such as music playlist generation and e-commerce bundle recommendations show that our model outperforms state-of-the-art baselines in both relevance and diversity.

Image editing is an iterative process that requires precise visual evaluation and manipulation for the output to match the editing intent. However, current image editing tools do not provide accessible interaction nor sufficient feedback for blind and low vision individuals to achieve this level of control. To address this, we developed EditScribe, a prototype system that makes image editing accessible using natural language verification loops powered by large multimodal models. Using EditScribe, the user first comprehends the image content through initial general and object descriptions, then specifies edit actions using open-ended natural language prompts. EditScribe performs the image edit, and provides four types of verification feedback for the user to verify the performed edit, including a summary of visual changes, AI judgement, and updated general and object descriptions. The user can ask follow-up questions to clarify and probe into the edits or verification feedback, before performing another edit. In a study with ten blind or low-vision users, we found that EditScribe supported participants to perform and verify image edit actions non-visually. We observed different prompting strategies from participants, and their perceptions on the various types of verification feedback. Finally, we discuss the implications of leveraging natural language verification loops to make visual authoring non-visually accessible.

This pictorial aims to critically consider the nature of text-to-audio and text-to-music generative tools in the context of explainable AI. As a group of experimental musicians and researchers, we are enthusiastic about the creative potential of these tools and have sought to understand and evaluate them from perspectives of prompt creation, control, usability, understandability, explainability of the AI process, and overall aesthetic effectiveness of the results. One of the challenges we have identified that is not explicitly addressed by these tools is the inherent semantic gap in using text-based tools to describe something as abstract as music. Other gaps include explainability vs. useability, and user control and input vs. the human creative process. The aim of this pictorial is to raise questions for discussion and make a few general suggestions on the kinds of improvements we would like to see in generative AI music tools.