Related papers: Building Implicit Vector Representations of Indivi…
Interpretability of deep reinforcement learning systems could assist operators with understanding how they interact with their environment. Vector quantization methods -- also called codebook methods -- discretize a neural network's latent…
Vector embeddings have been successfully applied in several domains to obtain effective representations of non-numeric data which can then be used in various downstream tasks. We present a novel application of vector embeddings in…
Visualization plays a relevant role for discovering patterns in big sets of data. In fact, the most common way to help a human with a pattern interpretation is through a graphic. In 2D/3D virtual environments for procedural training the…
Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised…
In this paper, we present a novel implicit glyph shape representation, which models glyphs as shape primitives enclosed by quadratic curves, and naturally enables generating glyph images at arbitrary high resolutions. Experiments on font…
What defines a visual style? Fashion styles emerge organically from how people assemble outfits of clothing, making them difficult to pin down with a computational model. Low-level visual similarity can be too specific to detect…
We see that the collaborative and participatory nature of software development continues to evolve, shape and be shaped by communication channels that are used by developer communities of practice--both by traditional communication channels…
The way developers collaborate inside and particularly across teams often escapes management's attention, despite a formal organization with designated teams being defined. Observability of the actual, organically formed engineering…
Learning from source code usually requires a large amount of labeled data. Despite the possible scarcity of labeled data, the trained model is highly task-specific and lacks transferability to different tasks. In this work, we present…
This abstract aims at presenting an ongoing effort to apply a novel typing mechanism stemming from Implicit Computational Complexity (ICC), that tracks dependencies between variables in three different ways, at different stages of…
In standard methodology for natural language processing, entities in text are typically embedded in dense vector spaces with pre-trained models. The embeddings produced this way are effective when fed into downstream models, but they…
With the advent of large language models, research in automated software engineering has increasingly focused on leveraging these models to achieve a deeper semantic understanding of code or to engineer sophisticated agent-based processes.…
Written text often provides sufficient clues to identify the author, their gender, age, and other important attributes. Consequently, the authorship of training and evaluation corpora can have unforeseen impacts, including differing model…
Self-supervised models create representation spaces that lack clear semantic meaning. This interpretability problem of representations makes traditional explainability methods ineffective in this context. In this paper, we introduce a novel…
Label differential privacy (DP) is a framework that protects the privacy of labels in training datasets, while the feature vectors are public. Existing approaches protect the privacy of labels by flipping them randomly, and then train a…
Recognizing elementary underlying concepts from observations (disentanglement) and generating novel combinations of these concepts (compositional generalization) are fundamental abilities for humans to support rapid knowledge learning and…
Understanding collaboration patterns in introductory programming courses is essential, as teamwork is a critical skill in computer science. In professional environments, software development relies on effective teamwork, navigating diverse…
While visual imitation learning offers one of the most effective ways of learning from visual demonstrations, generalizing from them requires either hundreds of diverse demonstrations, task specific priors, or large, hard-to-train…
AI assistants that support humans in daily life are becoming increasingly feasible, driven by the rapid advancements in multimodal language models. A key challenge lies in overcoming the generic nature of these models to deliver…
Inductive families provide a convenient way of programming with dependent types. Yet, when it comes to compilation, their default linked-tree runtime representations, as well as the need to convert between different indexed views of the…